diff --git "a/run_experiment.log" "b/run_experiment.log" new file mode 100644--- /dev/null +++ "b/run_experiment.log" @@ -0,0 +1,3076 @@ +[2025-03-24 20:42:59,108][__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/2025-03-24/19-26-35 +experiments: + model: + name: microsoft/Phi-3.5-mini-instruct + type: phi35_classification_lora + num_labels: 6 + output_dir: ./results/phi35-balanced/C3 + logging_dir: ./logs/phi35-balanced/C3 + best_model_dir: ./results/phi35-balanced/C3/best_model + lora_r: 8 + lora_dropout: 0.05 + lora_alpha: 16 + lora_target_modules: all-linear + dataset: + grade_index: 2 + training_id: phi35-balanced-C3 + 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 + +[2025-03-24 20:42:59,110][__main__][INFO] - Starting the Fine Tuning training process. +[2025-03-24 20:43:04,743][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 +[2025-03-24 20:43:04,744][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 +[2025-03-24 20:43:04,744][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 +[2025-03-24 20:43:04,744][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 +[2025-03-24 20:43:04,744][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 +[2025-03-24 20:43:04,744][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None +[2025-03-24 20:43:04,821][transformers.tokenization_utils_base][INFO] - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +[2025-03-24 20:43:04,874][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False +[2025-03-24 20:43:06,629][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 +[2025-03-24 20:43:06,630][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 +} + +[2025-03-24 20:43:06,631][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 +[2025-03-24 20:43:06,631][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object +[2025-03-24 20:43:06,631][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16. +[2025-03-24 20:43:33,790][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). +[2025-03-24 20:43:33,790][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. +[2025-03-24 20:44:03,711][__main__][INFO] - None +[2025-03-24 20:44:03,713][transformers.training_args][INFO] - PyTorch: setting up devices +[2025-03-24 20:44:03,736][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 +[2025-03-24 20:44:03,744][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. +[2025-03-24 20:44:03,768][transformers.trainer][INFO] - Using auto half precision backend +[2025-03-24 20:44:03,769][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. +[2025-03-24 20:44:03,777][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 20:44:03,789][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 20:44:03,789][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 20:44:03,789][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 20:44:18,684][transformers][INFO] - {'accuracy': 0.1590909090909091, 'RMSE': 90.45340337332908, 'QWK': -0.11659732317409399, 'HDIV': 0.3712121212121212, 'Macro_F1': 0.06876138433515483, 'Micro_F1': 0.1590909090909091, 'Weighted_F1': 0.09521443947673455, 'Macro_F1_(ignoring_nan)': np.float64(0.13752276867030966)} +[2025-03-24 20:44:18,688][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 20:44:18,951][transformers.trainer][INFO] - The following columns in the training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 20:44:18,978][transformers.trainer][INFO] - ***** Running training ***** +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Num examples = 500 +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Num Epochs = 20 +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Instantaneous batch size per device = 2 +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Gradient Accumulation steps = 8 +[2025-03-24 20:44:18,979][transformers.trainer][INFO] - Total optimization steps = 620 +[2025-03-24 20:44:18,981][transformers.trainer][INFO] - Number of trainable parameters = 12,601,344 +[2025-03-24 20:48:55,260][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 20:48:55,262][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 20:48:55,262][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 20:48:55,262][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 20:49:10,025][transformers][INFO] - {'accuracy': 0.44696969696969696, 'RMSE': 49.60449637488582, 'QWK': 0.27998710232158197, 'HDIV': 0.06818181818181823, 'Macro_F1': 0.2289231932089075, 'Micro_F1': 0.44696969696969696, 'Weighted_F1': 0.40948998091855243, 'Macro_F1_(ignoring_nan)': np.float64(0.34338478981336124)} +[2025-03-24 20:49:10,026][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 20:49:10,028][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-32 +[2025-03-24 20:49:10,566][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 +[2025-03-24 20:49:10,567][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 +} + +[2025-03-24 20:53:54,817][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 20:53:54,819][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 20:53:54,819][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 20:53:54,819][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 20:54:09,579][transformers][INFO] - {'accuracy': 0.42424242424242425, 'RMSE': 50.090826596203314, 'QWK': 0.39994729444834864, 'HDIV': 0.05303030303030298, 'Macro_F1': 0.3048111463876343, 'Micro_F1': 0.42424242424242425, 'Weighted_F1': 0.4200706253158965, 'Macro_F1_(ignoring_nan)': np.float64(0.36577337566516116)} +[2025-03-24 20:54:09,580][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 20:54:09,583][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-64 +[2025-03-24 20:54:10,112][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 +[2025-03-24 20:54:10,113][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 +} + +[2025-03-24 20:54:18,295][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-32] due to args.save_total_limit +[2025-03-24 20:58:54,327][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 20:58:54,329][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 20:58:54,329][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 20:58:54,329][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 20:59:08,976][transformers][INFO] - {'accuracy': 0.48484848484848486, 'RMSE': 47.86344211304794, 'QWK': 0.2894736842105263, 'HDIV': 0.06060606060606055, 'Macro_F1': 0.2556449232585596, 'Micro_F1': 0.48484848484848486, 'Weighted_F1': 0.42275768308826156, 'Macro_F1_(ignoring_nan)': np.float64(0.3834673848878394)} +[2025-03-24 20:59:08,977][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 20:59:08,979][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-96 +[2025-03-24 20:59:09,896][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 +[2025-03-24 20:59:09,898][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 +} + +[2025-03-24 21:03:54,571][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:03:54,573][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:03:54,573][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:03:54,573][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:04:09,095][transformers][INFO] - {'accuracy': 0.4090909090909091, 'RMSE': 50.572480239511265, 'QWK': 0.41413546487168695, 'HDIV': 0.05303030303030298, 'Macro_F1': 0.28829114355430147, 'Micro_F1': 0.4090909090909091, 'Weighted_F1': 0.3784693952158067, 'Macro_F1_(ignoring_nan)': np.float64(0.4324367153314522)} +[2025-03-24 21:04:09,095][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:04:09,098][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-128 +[2025-03-24 21:04:10,039][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 +[2025-03-24 21:04:10,041][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 +} + +[2025-03-24 21:04:18,198][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-64] due to args.save_total_limit +[2025-03-24 21:04:18,216][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-96] due to args.save_total_limit +[2025-03-24 21:08:54,403][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:08:54,406][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:08:54,406][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:08:54,406][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:09:08,977][transformers][INFO] - {'accuracy': 0.4393939393939394, 'RMSE': 52.91502622129181, 'QWK': 0.3044073364358062, 'HDIV': 0.09848484848484851, 'Macro_F1': 0.32087411293848583, 'Micro_F1': 0.4393939393939394, 'Weighted_F1': 0.38613799176305474, 'Macro_F1_(ignoring_nan)': np.float64(0.385048935526183)} +[2025-03-24 21:09:08,978][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:09:08,981][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-160 +[2025-03-24 21:09:09,918][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 +[2025-03-24 21:09:09,919][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 +} + +[2025-03-24 21:13:54,429][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:13:54,432][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:13:54,432][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:13:54,432][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:14:09,300][transformers][INFO] - {'accuracy': 0.4772727272727273, 'RMSE': 48.11602139777888, 'QWK': 0.297872340425532, 'HDIV': 0.0757575757575758, 'Macro_F1': 0.24605757469858466, 'Micro_F1': 0.4772727272727273, 'Weighted_F1': 0.39749065440354975, 'Macro_F1_(ignoring_nan)': np.float64(0.4921151493971693)} +[2025-03-24 21:14:09,300][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:14:09,303][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-192 +[2025-03-24 21:14:10,029][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 +[2025-03-24 21:14:10,030][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 +} + +[2025-03-24 21:14:18,203][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-160] due to args.save_total_limit +[2025-03-24 21:18:54,633][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:18:54,636][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:18:54,636][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:18:54,636][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:19:09,381][transformers][INFO] - {'accuracy': 0.4318181818181818, 'RMSE': 53.37119867948301, 'QWK': 0.3880691233330702, 'HDIV': 0.08333333333333337, 'Macro_F1': 0.3240266713102027, 'Micro_F1': 0.4318181818181818, 'Weighted_F1': 0.42270168051152773, 'Macro_F1_(ignoring_nan)': np.float64(0.38883200557224323)} +[2025-03-24 21:19:09,381][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:19:09,384][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-224 +[2025-03-24 21:19:09,883][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 +[2025-03-24 21:19:09,884][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 +} + +[2025-03-24 21:19:18,224][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-192] due to args.save_total_limit +[2025-03-24 21:23:54,422][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:23:54,425][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:23:54,425][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:23:54,425][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:24:09,094][transformers][INFO] - {'accuracy': 0.4696969696969697, 'RMSE': 50.572480239511265, 'QWK': 0.42535281010151027, 'HDIV': 0.09090909090909094, 'Macro_F1': 0.28053948161543096, 'Micro_F1': 0.4696969696969697, 'Weighted_F1': 0.4352282316839279, 'Macro_F1_(ignoring_nan)': np.float64(0.42080922242314645)} +[2025-03-24 21:24:09,094][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:24:09,097][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-256 +[2025-03-24 21:24:09,594][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 +[2025-03-24 21:24:09,595][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 +} + +[2025-03-24 21:24:17,819][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-128] due to args.save_total_limit +[2025-03-24 21:24:17,837][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-224] due to args.save_total_limit +[2025-03-24 21:28:54,045][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:28:54,048][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:28:54,048][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:28:54,048][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:29:08,798][transformers][INFO] - {'accuracy': 0.4696969696969697, 'RMSE': 49.848254581765296, 'QWK': 0.3706976744186047, 'HDIV': 0.09090909090909094, 'Macro_F1': 0.34991564807741277, 'Micro_F1': 0.4696969696969697, 'Weighted_F1': 0.4365355233002292, 'Macro_F1_(ignoring_nan)': np.float64(0.4198987776928953)} +[2025-03-24 21:29:08,799][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:29:08,801][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-288 +[2025-03-24 21:29:09,303][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 +[2025-03-24 21:29:09,304][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 +} + +[2025-03-24 21:33:53,782][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:33:53,784][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:33:53,784][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:33:53,785][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:34:08,502][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 48.865926655275736, 'QWK': 0.4835557673975215, 'HDIV': 0.08333333333333337, 'Macro_F1': 0.38035734552588485, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.4966709263951347, 'Macro_F1_(ignoring_nan)': np.float64(0.45642881463106183)} +[2025-03-24 21:34:08,503][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:34:08,506][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-320 +[2025-03-24 21:34:09,050][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 +[2025-03-24 21:34:09,051][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 +} + +[2025-03-24 21:34:17,728][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-256] due to args.save_total_limit +[2025-03-24 21:34:17,745][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-288] due to args.save_total_limit +[2025-03-24 21:38:53,917][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:38:53,919][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:38:53,919][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:38:53,919][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:39:08,333][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 51.99067515459193, 'QWK': 0.44178108169612385, 'HDIV': 0.08333333333333337, 'Macro_F1': 0.3436145788491893, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.49456423903259894, 'Macro_F1_(ignoring_nan)': np.float64(0.41233749461902713)} +[2025-03-24 21:39:08,334][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:39:08,337][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-352 +[2025-03-24 21:39:08,852][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 +[2025-03-24 21:39:08,853][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 +} + +[2025-03-24 21:43:53,337][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:43:53,339][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:43:53,340][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:43:53,340][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:44:08,075][transformers][INFO] - {'accuracy': 0.5075757575757576, 'RMSE': 48.36728170358491, 'QWK': 0.4449673202614379, 'HDIV': 0.06818181818181823, 'Macro_F1': 0.3666403678419461, 'Micro_F1': 0.5075757575757576, 'Weighted_F1': 0.5011660844336598, 'Macro_F1_(ignoring_nan)': np.float64(0.4399684414103353)} +[2025-03-24 21:44:08,075][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:44:08,078][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-384 +[2025-03-24 21:44:08,928][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 +[2025-03-24 21:44:08,929][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 +} + +[2025-03-24 21:44:17,206][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-352] due to args.save_total_limit +[2025-03-24 21:48:53,616][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:48:53,619][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:48:53,619][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:48:53,619][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:49:08,293][transformers][INFO] - {'accuracy': 0.5075757575757576, 'RMSE': 47.60952285695233, 'QWK': 0.4913032726073696, 'HDIV': 0.0757575757575758, 'Macro_F1': 0.38534530771372877, 'Micro_F1': 0.5075757575757576, 'Weighted_F1': 0.5082073871547556, 'Macro_F1_(ignoring_nan)': np.float64(0.4624143692564745)} +[2025-03-24 21:49:08,294][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:49:08,297][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-416 +[2025-03-24 21:49:08,795][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 +[2025-03-24 21:49:08,796][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 +} + +[2025-03-24 21:49:17,214][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-320] due to args.save_total_limit +[2025-03-24 21:49:17,232][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-384] due to args.save_total_limit +[2025-03-24 21:53:53,501][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:53:53,504][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:53:53,504][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:53:53,504][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:54:08,103][transformers][INFO] - {'accuracy': 0.4621212121212121, 'RMSE': 51.286479995248555, 'QWK': 0.33373650911797526, 'HDIV': 0.09848484848484851, 'Macro_F1': 0.2843933843933844, 'Micro_F1': 0.4621212121212121, 'Weighted_F1': 0.43266329629965994, 'Macro_F1_(ignoring_nan)': np.float64(0.3412720612720613)} +[2025-03-24 21:54:08,103][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:54:08,106][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-448 +[2025-03-24 21:54:08,612][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 +[2025-03-24 21:54:08,613][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 +} + +[2025-03-24 21:58:53,309][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 21:58:53,311][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 21:58:53,311][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 21:58:53,311][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 21:59:07,872][transformers][INFO] - {'accuracy': 0.5303030303030303, 'RMSE': 48.617243480439775, 'QWK': 0.4149999999999999, 'HDIV': 0.06818181818181823, 'Macro_F1': 0.29559447503836783, 'Micro_F1': 0.5303030303030303, 'Weighted_F1': 0.49783307481240124, 'Macro_F1_(ignoring_nan)': np.float64(0.4433917125575517)} +[2025-03-24 21:59:07,873][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 21:59:07,876][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-480 +[2025-03-24 21:59:08,399][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 +[2025-03-24 21:59:08,400][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 +} + +[2025-03-24 21:59:16,525][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-448] due to args.save_total_limit +[2025-03-24 22:03:52,815][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 22:03:52,817][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 22:03:52,817][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 22:03:52,817][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 22:04:07,290][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 50.33222956847167, 'QWK': 0.34668940039784035, 'HDIV': 0.09090909090909094, 'Macro_F1': 0.34605040021706684, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.4617462784129451, 'Macro_F1_(ignoring_nan)': np.float64(0.41526048026048024)} +[2025-03-24 22:04:07,290][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 22:04:07,293][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-512 +[2025-03-24 22:04:07,897][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 +[2025-03-24 22:04:07,898][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 +} + +[2025-03-24 22:04:16,111][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-480] due to args.save_total_limit +[2025-03-24 22:08:52,265][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 22:08:52,267][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 22:08:52,267][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 22:08:52,267][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 22:09:06,893][transformers][INFO] - {'accuracy': 0.44696969696969696, 'RMSE': 50.33222956847167, 'QWK': 0.435135135135135, 'HDIV': 0.0757575757575758, 'Macro_F1': 0.33657152409447394, 'Micro_F1': 0.44696969696969696, 'Weighted_F1': 0.4453170011003548, 'Macro_F1_(ignoring_nan)': np.float64(0.4038858289133687)} +[2025-03-24 22:09:06,894][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 22:09:06,896][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-544 +[2025-03-24 22:09:07,386][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 +[2025-03-24 22:09:07,387][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 +} + +[2025-03-24 22:09:15,703][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-512] due to args.save_total_limit +[2025-03-24 22:13:52,069][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 22:13:52,072][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 22:13:52,072][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 22:13:52,072][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 22:14:06,774][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 50.33222956847167, 'QWK': 0.3815459110473458, 'HDIV': 0.09090909090909094, 'Macro_F1': 0.36160714285714285, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.47104978354978355, 'Macro_F1_(ignoring_nan)': np.float64(0.43392857142857144)} +[2025-03-24 22:14:06,775][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 22:14:06,778][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-576 +[2025-03-24 22:14:07,646][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 +[2025-03-24 22:14:07,647][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 +} + +[2025-03-24 22:14:15,989][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-544] due to args.save_total_limit +[2025-03-24 22:14:16,005][transformers.trainer][INFO] - + +Training completed. Do not forget to share your model on huggingface.co/models =) + + +[2025-03-24 22:14:16,005][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-416 (score: 0.4913032726073696). +[2025-03-24 22:14:37,691][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/20-42-59/results/phi35-balanced/C3/checkpoint-576] due to args.save_total_limit +[2025-03-24 22:14:37,709][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 22:14:37,712][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 22:14:37,712][transformers.trainer][INFO] - Num examples = 132 +[2025-03-24 22:14:37,712][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 22:14:52,669][transformers][INFO] - {'accuracy': 0.5075757575757576, 'RMSE': 47.60952285695233, 'QWK': 0.4913032726073696, 'HDIV': 0.0757575757575758, 'Macro_F1': 0.38534530771372877, 'Micro_F1': 0.5075757575757576, 'Weighted_F1': 0.5082073871547556, 'Macro_F1_(ignoring_nan)': np.float64(0.4624143692564745)} +[2025-03-24 22:14:52,672][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 22:14:52,673][__main__][INFO] - Training completed successfully. +[2025-03-24 22:14:52,673][__main__][INFO] - Running on Test +[2025-03-24 22:14:52,674][transformers.trainer][INFO] - The following columns in the evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year. If id_prompt, reference, grades, supporting_text, prompt, id, essay_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. +[2025-03-24 22:14:52,676][transformers.trainer][INFO] - +***** Running Evaluation ***** +[2025-03-24 22:14:52,676][transformers.trainer][INFO] - Num examples = 138 +[2025-03-24 22:14:52,676][transformers.trainer][INFO] - Batch size = 16 +[2025-03-24 22:15:08,409][transformers][INFO] - {'accuracy': 0.3333333333333333, 'RMSE': 60.43321862224019, 'QWK': 0.23535620052770445, 'HDIV': 0.1159420289855072, 'Macro_F1': 0.26255872656551776, 'Micro_F1': 0.3333333333333333, 'Weighted_F1': 0.3336611749101599, 'Macro_F1_(ignoring_nan)': np.float64(0.3150704718786213)} +[2025-03-24 22:15:08,410][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. +[2025-03-24 22:15:08,412][transformers.trainer][INFO] - Saving model checkpoint to ./results/phi35-balanced/C3/best_model +[2025-03-24 22:15:09,301][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 +[2025-03-24 22:15:09,302][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 +} + +[2025-03-24 22:15:17,688][__main__][INFO] - Fine Tuning Finished.