[2025-03-25 11:12:15,356][__main__][INFO] - cache_dir: /media/data/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 post_training_results: model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59 experiments: model: name: microsoft/Phi-3.5-mini-instruct type: phi35_classification_lora num_labels: 6 output_dir: ./results/phi35-balanced/C4 logging_dir: ./logs/phi35-balanced/C4 best_model_dir: ./results/phi35-balanced/C4/best_model lora_r: 8 lora_dropout: 0.05 lora_alpha: 16 lora_target_modules: all-linear dataset: grade_index: 3 training_id: phi35-balanced-C4 training_params: weight_decay: 0.01 warmup_ratio: 0.1 learning_rate: 5.0e-05 train_batch_size: 2 eval_batch_size: 16 gradient_accumulation_steps: 8 gradient_checkpointing: false [2025-03-25 11:12:15,359][__main__][INFO] - Starting the Fine Tuning training process. [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file tokenizer.model from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.model [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.json [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/added_tokens.json [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/special_tokens_map.json [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer_config.json [2025-03-25 11:12:26,140][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-03-25 11:12:26,207][transformers.tokenization_utils_base][INFO] - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. [2025-03-25 11:12:26,214][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False [2025-03-25 11:12:26,892][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:12:26,893][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "id2label": { "0": 0, "1": 40, "2": 80, "3": 120, "4": 160, "5": 200 }, "initializer_range": 0.02, "intermediate_size": 8192, "label2id": { "0": 0, "40": 1, "80": 2, "120": 3, "160": 4, "200": 5 }, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:12:26,894][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /media/data/tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/model.safetensors.index.json [2025-03-25 11:12:26,894][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object [2025-03-25 11:12:26,894][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16. [2025-03-25 11:12:48,122][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at microsoft/Phi-3.5-mini-instruct were not used when initializing Phi3ForSequenceClassification: ['lm_head.weight'] - This IS expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). [2025-03-25 11:12:48,122][transformers.modeling_utils][WARNING] - Some weights of Phi3ForSequenceClassification were not initialized from the model checkpoint at microsoft/Phi-3.5-mini-instruct and are newly initialized: ['score.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. [2025-03-25 11:13:11,668][__main__][INFO] - None [2025-03-25 11:13:11,670][transformers.training_args][INFO] - PyTorch: setting up devices [2025-03-25 11:13:11,691][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-03-25 11:13:11,698][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. [2025-03-25 11:13:11,793][transformers.trainer][INFO] - Using auto half precision backend [2025-03-25 11:13:11,794][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. [2025-03-25 11:13:11,801][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:13:11,812][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:13:11,812][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:13:11,812][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:13:25,794][transformers][INFO] - {'accuracy': 0.17424242424242425, 'RMSE': 82.46211251235322, 'QWK': -0.15756893640967928, 'HDIV': 0.2803030303030303, 'Macro_F1': 0.0638888888888889, 'Micro_F1': 0.17424242424242425, 'Weighted_F1': 0.1393939393939394, 'Macro_F1_(ignoring_nan)': np.float64(0.38333333333333336)} [2025-03-25 11:13:25,797][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:13:26,037][transformers.trainer][INFO] - The following columns in the training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:13:26,063][transformers.trainer][INFO] - ***** Running training ***** [2025-03-25 11:13:26,063][transformers.trainer][INFO] - Num examples = 500 [2025-03-25 11:13:26,063][transformers.trainer][INFO] - Num Epochs = 20 [2025-03-25 11:13:26,064][transformers.trainer][INFO] - Instantaneous batch size per device = 2 [2025-03-25 11:13:26,064][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-03-25 11:13:26,064][transformers.trainer][INFO] - Gradient Accumulation steps = 8 [2025-03-25 11:13:26,064][transformers.trainer][INFO] - Total optimization steps = 620 [2025-03-25 11:13:26,065][transformers.trainer][INFO] - Number of trainable parameters = 12,601,344 [2025-03-25 11:18:00,813][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:18:00,816][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:18:00,816][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:18:00,816][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:18:14,692][transformers][INFO] - {'accuracy': 0.5075757575757576, 'RMSE': 37.335497772755005, 'QWK': 0.04720060256088365, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.1564102564102564, 'Micro_F1': 0.5075757575757576, 'Weighted_F1': 0.3651903651903652, 'Macro_F1_(ignoring_nan)': np.float64(0.391025641025641)} [2025-03-25 11:18:14,693][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:18:14,696][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-32 [2025-03-25 11:18:15,659][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:18:15,660][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:22:56,037][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:22:56,039][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:22:56,039][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:22:56,039][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:23:09,486][transformers][INFO] - {'accuracy': 0.6060606060606061, 'RMSE': 28.91995221924885, 'QWK': 0.4387478432339166, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.3021052631578947, 'Micro_F1': 0.6060606060606061, 'Weighted_F1': 0.5774587985114301, 'Macro_F1_(ignoring_nan)': np.float64(0.5035087719298245)} [2025-03-25 11:23:09,487][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:23:09,489][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-64 [2025-03-25 11:23:09,925][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:23:09,926][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:23:15,511][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-32] due to args.save_total_limit [2025-03-25 11:27:49,639][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:27:49,642][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:27:49,642][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:27:49,642][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:28:03,302][transformers][INFO] - {'accuracy': 0.553030303030303, 'RMSE': 30.944720996896347, 'QWK': 0.33153846153846167, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.23943977591036414, 'Micro_F1': 0.553030303030303, 'Weighted_F1': 0.5042695866225277, 'Macro_F1_(ignoring_nan)': np.float64(0.3990662931839402)} [2025-03-25 11:28:03,302][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:28:03,304][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-96 [2025-03-25 11:28:03,757][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:28:03,758][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:32:45,176][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:32:45,179][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:32:45,179][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:32:45,179][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:32:58,797][transformers][INFO] - {'accuracy': 0.5833333333333334, 'RMSE': 28.91995221924885, 'QWK': 0.402048319327731, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.2524590163934426, 'Micro_F1': 0.5833333333333334, 'Weighted_F1': 0.5384997516145057, 'Macro_F1_(ignoring_nan)': np.float64(0.6311475409836065)} [2025-03-25 11:32:58,798][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:32:58,800][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-128 [2025-03-25 11:32:59,231][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:32:59,231][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:33:06,038][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-96] due to args.save_total_limit [2025-03-25 11:37:40,393][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:37:40,395][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:37:40,395][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:37:40,395][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:37:54,018][transformers][INFO] - {'accuracy': 0.5757575757575758, 'RMSE': 29.74640288923158, 'QWK': 0.36488267861850776, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.24913793103448273, 'Micro_F1': 0.5757575757575758, 'Weighted_F1': 0.5282131661442006, 'Macro_F1_(ignoring_nan)': np.float64(0.6228448275862069)} [2025-03-25 11:37:54,019][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:37:54,021][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-160 [2025-03-25 11:37:54,455][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:37:54,456][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:38:01,627][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-128] due to args.save_total_limit [2025-03-25 11:42:35,848][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:42:35,851][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:42:35,851][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:42:35,851][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:42:49,389][transformers][INFO] - {'accuracy': 0.5303030303030303, 'RMSE': 30.944720996896347, 'QWK': 0.3408343868520859, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.25017776341305753, 'Micro_F1': 0.5303030303030303, 'Weighted_F1': 0.500048970637206, 'Macro_F1_(ignoring_nan)': np.float64(0.41696293902176257)} [2025-03-25 11:42:49,389][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:42:49,392][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-192 [2025-03-25 11:42:49,850][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:42:49,850][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:42:57,012][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-160] due to args.save_total_limit [2025-03-25 11:47:31,460][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:47:31,462][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:47:31,462][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:47:31,462][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:47:45,109][transformers][INFO] - {'accuracy': 0.5378787878787878, 'RMSE': 31.333978072025612, 'QWK': 0.5219102128420676, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.3209438880967848, 'Micro_F1': 0.5378787878787878, 'Weighted_F1': 0.5375975035810859, 'Macro_F1_(ignoring_nan)': np.float64(0.401179860120981)} [2025-03-25 11:47:45,109][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:47:45,112][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-224 [2025-03-25 11:47:45,576][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:47:45,577][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:47:52,626][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-64] due to args.save_total_limit [2025-03-25 11:47:52,632][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-192] due to args.save_total_limit [2025-03-25 11:52:27,021][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:52:27,023][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:52:27,023][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:52:27,023][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:52:40,710][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 32.47376563543955, 'QWK': 0.41035120147874304, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.2695384450631827, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.49381802605190916, 'Macro_F1_(ignoring_nan)': np.float64(0.3369230563289784)} [2025-03-25 11:52:40,710][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:52:40,713][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-256 [2025-03-25 11:52:41,164][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:52:41,164][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:57:22,807][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 11:57:22,810][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 11:57:22,810][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 11:57:22,810][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 11:57:36,914][transformers][INFO] - {'accuracy': 0.5303030303030303, 'RMSE': 30.944720996896347, 'QWK': 0.49671814671814674, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.3024938574938575, 'Micro_F1': 0.5303030303030303, 'Weighted_F1': 0.5311518129699948, 'Macro_F1_(ignoring_nan)': np.float64(0.5041564291564291)} [2025-03-25 11:57:36,915][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 11:57:36,918][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-288 [2025-03-25 11:57:37,365][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 11:57:37,366][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 11:57:44,625][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-256] due to args.save_total_limit [2025-03-25 12:02:19,292][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 12:02:19,295][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 12:02:19,295][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 12:02:19,295][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 12:02:32,900][transformers][INFO] - {'accuracy': 0.5227272727272727, 'RMSE': 31.71845844395036, 'QWK': 0.3937583001328021, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.2602836879432624, 'Micro_F1': 0.5227272727272727, 'Weighted_F1': 0.5035460992907802, 'Macro_F1_(ignoring_nan)': np.float64(0.325354609929078)} [2025-03-25 12:02:32,901][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 12:02:32,903][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-320 [2025-03-25 12:02:33,339][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 12:02:33,340][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 12:02:39,938][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-288] due to args.save_total_limit [2025-03-25 12:07:14,417][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 12:07:14,419][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 12:07:14,419][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 12:07:14,420][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 12:07:27,903][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 31.333978072025612, 'QWK': 0.46389891696750907, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.31080979284369115, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.4942190264224163, 'Macro_F1_(ignoring_nan)': np.float64(0.3885122410546139)} [2025-03-25 12:07:27,904][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 12:07:27,907][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-352 [2025-03-25 12:07:28,424][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 12:07:28,425][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 12:07:35,137][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-320] due to args.save_total_limit [2025-03-25 12:12:09,972][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 12:12:09,974][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 12:12:09,974][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 12:12:09,974][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 12:12:23,523][transformers][INFO] - {'accuracy': 0.5757575757575758, 'RMSE': 28.4977404739606, 'QWK': 0.43380281690140854, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.2515151515151515, 'Micro_F1': 0.5757575757575758, 'Weighted_F1': 0.5344352617079889, 'Macro_F1_(ignoring_nan)': np.float64(0.41919191919191917)} [2025-03-25 12:12:23,524][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 12:12:23,527][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-384 [2025-03-25 12:12:23,958][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 12:12:23,959][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 12:12:30,528][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-352] due to args.save_total_limit [2025-03-25 12:12:30,535][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-03-25 12:12:30,535][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-224 (score: 0.5219102128420676). [2025-03-25 12:12:48,057][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-25/11-12-15/results/phi35-balanced/C4/checkpoint-384] due to args.save_total_limit [2025-03-25 12:12:48,064][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 12:12:48,067][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 12:12:48,067][transformers.trainer][INFO] - Num examples = 132 [2025-03-25 12:12:48,067][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 12:13:01,694][transformers][INFO] - {'accuracy': 0.5378787878787878, 'RMSE': 31.333978072025612, 'QWK': 0.5219102128420676, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.3209438880967848, 'Micro_F1': 0.5378787878787878, 'Weighted_F1': 0.5375975035810859, 'Macro_F1_(ignoring_nan)': np.float64(0.401179860120981)} [2025-03-25 12:13:01,697][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 12:13:01,698][__main__][INFO] - Training completed successfully. [2025-03-25 12:13:01,698][__main__][INFO] - Running on Test [2025-03-25 12:13:01,699][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt. If essay_text, reference, id, grades, supporting_text, prompt, essay_year, id_prompt are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-25 12:13:01,701][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-25 12:13:01,701][transformers.trainer][INFO] - Num examples = 138 [2025-03-25 12:13:01,701][transformers.trainer][INFO] - Batch size = 16 [2025-03-25 12:13:16,666][transformers][INFO] - {'accuracy': 0.572463768115942, 'RMSE': 29.684329540851266, 'QWK': 0.5590312815338042, 'HDIV': 0.007246376811594235, 'Macro_F1': 0.29486004573723873, 'Micro_F1': 0.572463768115942, 'Weighted_F1': 0.593693390260896, 'Macro_F1_(ignoring_nan)': np.float64(0.44229006860585807)} [2025-03-25 12:13:16,666][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-25 12:13:16,669][transformers.trainer][INFO] - Saving model checkpoint to ./results/phi35-balanced/C4/best_model [2025-03-25 12:13:17,103][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json [2025-03-25 12:13:17,103][transformers.configuration_utils][INFO] - Model config Phi3Config { "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "model_type": "phi3", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0800000429153442, 1.1100000143051147, 1.1399999856948853, 1.340000033378601, 1.5899999141693115, 1.600000023841858, 1.6200000047683716, 2.620000123977661, 3.2300000190734863, 3.2300000190734863, 4.789999961853027, 7.400000095367432, 7.700000286102295, 9.09000015258789, 12.199999809265137, 17.670000076293945, 24.46000099182129, 28.57000160217285, 30.420001983642578, 30.840002059936523, 32.590003967285156, 32.93000411987305, 42.320003509521484, 44.96000289916992, 50.340003967285156, 50.45000457763672, 57.55000305175781, 57.93000411987305, 58.21000289916992, 60.1400032043457, 62.61000442504883, 62.62000274658203, 62.71000289916992, 63.1400032043457, 63.1400032043457, 63.77000427246094, 63.93000411987305, 63.96000289916992, 63.970001220703125, 64.02999877929688, 64.06999969482422, 64.08000183105469, 64.12000274658203, 64.41000366210938, 64.4800033569336, 64.51000213623047, 64.52999877929688, 64.83999633789062 ], "short_factor": [ 1.0, 1.0199999809265137, 1.0299999713897705, 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0499999523162842, 1.0699999332427979, 1.0999999046325684, 1.1099998950958252, 1.1599998474121094, 1.1599998474121094, 1.1699998378753662, 1.2899998426437378, 1.339999794960022, 1.679999828338623, 1.7899998426437378, 1.8199998140335083, 1.8499997854232788, 1.8799997568130493, 1.9099997282028198, 1.9399996995925903, 1.9899996519088745, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0199997425079346, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0299997329711914, 2.0799996852874756, 2.0899996757507324, 2.189999580383301, 2.2199995517730713, 2.5899994373321533, 2.729999542236328, 2.749999523162842, 2.8399994373321533 ], "type": "longrope" }, "rope_theta": 10000.0, "sliding_window": 262144, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0", "use_cache": true, "vocab_size": 32064 } [2025-03-25 12:13:23,549][__main__][INFO] - Fine Tuning Finished.