[2025-03-24 19:26:35,748][__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/2025-03-23/23-16-55 experiments: model: name: microsoft/Phi-3.5-mini-instruct type: phi35_classification_lora num_labels: 6 output_dir: ./results/phi35-balanced/C2 logging_dir: ./logs/phi35-balanced/C2 best_model_dir: ./results/phi35-balanced/C2/best_model lora_r: 8 lora_dropout: 0.05 lora_alpha: 16 lora_target_modules: all-linear dataset: grade_index: 1 training_id: phi35-balanced-C2 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 19:26:35,750][__main__][INFO] - Starting the Fine Tuning training process. [2025-03-24 19:26:41,879][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 19:26:41,879][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 19:26:41,879][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 19:26:41,879][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 19:26:41,879][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 19:26:41,879][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-03-24 19:26:41,954][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 19:26:41,960][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False [2025-03-24 19:26:42,733][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 19:26:42,734][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 19:26:42,735][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 19:26:42,735][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object [2025-03-24 19:26:42,735][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16. [2025-03-24 19:27:09,890][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 19:27:09,891][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 19:27:39,707][__main__][INFO] - None [2025-03-24 19:27:39,709][transformers.training_args][INFO] - PyTorch: setting up devices [2025-03-24 19:27:39,749][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-03-24 19:27:39,758][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 19:27:39,849][transformers.trainer][INFO] - Using auto half precision backend [2025-03-24 19:27:39,850][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 19:27:39,857][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:27:39,868][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:27:39,869][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:27:39,869][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:27:58,784][transformers][INFO] - {'accuracy': 0.24242424242424243, 'RMSE': 66.332495807108, 'QWK': -0.03813155386082001, 'HDIV': 0.20454545454545459, 'Macro_F1': 0.10504184527454583, 'Micro_F1': 0.24242424242424243, 'Weighted_F1': 0.1534017455634112, 'Macro_F1_(ignoring_nan)': np.float64(0.17506974212424306)} [2025-03-24 19:27:58,788][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:27:59,088][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:27:59,114][transformers.trainer][INFO] - ***** Running training ***** [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Num examples = 500 [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Num Epochs = 20 [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Instantaneous batch size per device = 2 [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Gradient Accumulation steps = 8 [2025-03-24 19:27:59,114][transformers.trainer][INFO] - Total optimization steps = 620 [2025-03-24 19:27:59,116][transformers.trainer][INFO] - Number of trainable parameters = 12,601,344 [2025-03-24 19:33:57,142][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:33:57,144][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:33:57,144][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:33:57,144][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:34:15,625][transformers][INFO] - {'accuracy': 0.4621212121212121, 'RMSE': 49.11335065052284, 'QWK': 0.04061358655953251, 'HDIV': 0.007575757575757569, 'Macro_F1': 0.1404692650765949, 'Micro_F1': 0.4621212121212121, 'Weighted_F1': 0.3043671150128393, 'Macro_F1_(ignoring_nan)': np.float64(0.3511731626914873)} [2025-03-24 19:34:15,626][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:34:15,629][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-32 [2025-03-24 19:34:16,447][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 19:34:16,449][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 19:40:22,418][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:40:22,421][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:40:22,421][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:40:22,421][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:40:40,827][transformers][INFO] - {'accuracy': 0.4393939393939394, 'RMSE': 53.143601912576685, 'QWK': 0.2852760736196319, 'HDIV': 0.045454545454545414, 'Macro_F1': 0.2148417214126595, 'Micro_F1': 0.4393939393939394, 'Weighted_F1': 0.3616045380805515, 'Macro_F1_(ignoring_nan)': np.float64(0.26855215176582437)} [2025-03-24 19:40:40,828][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:40:40,830][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-64 [2025-03-24 19:40:41,379][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 19:40:41,381][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 19:40:49,514][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-32] due to args.save_total_limit [2025-03-24 19:46:47,318][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:46:47,320][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:46:47,320][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:46:47,320][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:47:05,629][transformers][INFO] - {'accuracy': 0.4318181818181818, 'RMSE': 52.68545886444927, 'QWK': 0.33076514346439956, 'HDIV': 0.045454545454545414, 'Macro_F1': 0.2661131957473421, 'Micro_F1': 0.4318181818181818, 'Weighted_F1': 0.39607733052855004, 'Macro_F1_(ignoring_nan)': np.float64(0.4435219929122369)} [2025-03-24 19:47:05,630][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:47:05,632][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-96 [2025-03-24 19:47:06,539][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 19:47:06,540][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 19:47:15,012][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-64] due to args.save_total_limit [2025-03-24 19:53:13,045][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:53:13,048][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:53:13,048][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:53:13,048][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:53:31,528][transformers][INFO] - {'accuracy': 0.49242424242424243, 'RMSE': 47.60952285695233, 'QWK': 0.12331297059241364, 'HDIV': 0.022727272727272707, 'Macro_F1': 0.18550724637681157, 'Micro_F1': 0.49242424242424243, 'Weighted_F1': 0.36736934563021517, 'Macro_F1_(ignoring_nan)': np.float64(0.46376811594202894)} [2025-03-24 19:53:31,528][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:53:31,531][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-128 [2025-03-24 19:53:31,974][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 19:53:31,976][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 19:59:37,807][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 19:59:37,809][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 19:59:37,809][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 19:59:37,809][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 19:59:56,127][transformers][INFO] - {'accuracy': 0.38636363636363635, 'RMSE': 58.981250230796896, 'QWK': 0.35724465558194773, 'HDIV': 0.037878787878787845, 'Macro_F1': 0.21283275639401986, 'Micro_F1': 0.38636363636363635, 'Weighted_F1': 0.33311875189695395, 'Macro_F1_(ignoring_nan)': np.float64(0.3547212606566998)} [2025-03-24 19:59:56,128][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 19:59:56,131][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-160 [2025-03-24 19:59:57,072][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 19:59:57,073][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 20:00:05,315][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-96] due to args.save_total_limit [2025-03-24 20:00:05,332][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-128] due to args.save_total_limit [2025-03-24 20:06:02,991][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:06:02,994][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:06:02,994][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:06:02,994][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:06:21,333][transformers][INFO] - {'accuracy': 0.42424242424242425, 'RMSE': 48.36728170358491, 'QWK': 0.2587290502793297, 'HDIV': 0.022727272727272707, 'Macro_F1': 0.1805673137741449, 'Micro_F1': 0.42424242424242425, 'Weighted_F1': 0.36980931781690796, 'Macro_F1_(ignoring_nan)': np.float64(0.2708509706612173)} [2025-03-24 20:06:21,334][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:06:21,337][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-192 [2025-03-24 20:06:21,788][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 20:06:21,789][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 20:12:27,944][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:12:27,946][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:12:27,946][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:12:27,946][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:12:46,237][transformers][INFO] - {'accuracy': 0.3560606060606061, 'RMSE': 51.75700801618925, 'QWK': 0.33579234972677596, 'HDIV': 0.05303030303030298, 'Macro_F1': 0.19786302390851182, 'Micro_F1': 0.3560606060606061, 'Weighted_F1': 0.3335142643286444, 'Macro_F1_(ignoring_nan)': np.float64(0.2967945358627677)} [2025-03-24 20:12:46,237][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:12:46,240][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-224 [2025-03-24 20:12:46,833][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 20:12:46,835][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 20:12:55,009][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-192] due to args.save_total_limit [2025-03-24 20:18:52,733][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:18:52,736][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:18:52,736][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:18:52,736][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:19:11,023][transformers][INFO] - {'accuracy': 0.3333333333333333, 'RMSE': 61.00173867368143, 'QWK': 0.3459651387992253, 'HDIV': 0.06060606060606055, 'Macro_F1': 0.26468434343434344, 'Micro_F1': 0.3333333333333333, 'Weighted_F1': 0.33276419498010407, 'Macro_F1_(ignoring_nan)': np.float64(0.33085542929292927)} [2025-03-24 20:19:11,024][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:19:11,026][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-256 [2025-03-24 20:19:11,512][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 20:19:11,513][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 20:19:19,615][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-224] due to args.save_total_limit [2025-03-24 20:25:17,239][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:25:17,242][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:25:17,242][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:25:17,242][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:25:35,922][transformers][INFO] - {'accuracy': 0.4166666666666667, 'RMSE': 55.37749241945383, 'QWK': 0.3101710319755432, 'HDIV': 0.045454545454545414, 'Macro_F1': 0.23327141209785254, 'Micro_F1': 0.4166666666666667, 'Weighted_F1': 0.3928450028485377, 'Macro_F1_(ignoring_nan)': np.float64(0.34990711814677883)} [2025-03-24 20:25:35,923][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:25:35,926][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-288 [2025-03-24 20:25:36,379][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 20:25:36,381][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 20:25:44,605][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-256] due to args.save_total_limit [2025-03-24 20:31:42,515][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:31:42,518][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:31:42,518][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:31:42,518][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:32:01,004][transformers][INFO] - {'accuracy': 0.45454545454545453, 'RMSE': 53.143601912576685, 'QWK': 0.24462127910403786, 'HDIV': 0.045454545454545414, 'Macro_F1': 0.27681543857724816, 'Micro_F1': 0.45454545454545453, 'Weighted_F1': 0.42073346116794536, 'Macro_F1_(ignoring_nan)': np.float64(0.3460192982215602)} [2025-03-24 20:32:01,005][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:32:01,008][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-320 [2025-03-24 20:32:01,457][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 20:32:01,458][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 20:32:09,598][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-288] due to args.save_total_limit [2025-03-24 20:32:09,615][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-03-24 20:32:09,616][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-160 (score: 0.35724465558194773). [2025-03-24 20:32:31,185][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-03-24/19-26-35/results/phi35-balanced/C2/checkpoint-320] due to args.save_total_limit [2025-03-24 20:32:31,204][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:32:31,207][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:32:31,207][transformers.trainer][INFO] - Num examples = 132 [2025-03-24 20:32:31,207][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:32:49,532][transformers][INFO] - {'accuracy': 0.38636363636363635, 'RMSE': 58.981250230796896, 'QWK': 0.35724465558194773, 'HDIV': 0.037878787878787845, 'Macro_F1': 0.21283275639401986, 'Micro_F1': 0.38636363636363635, 'Weighted_F1': 0.33311875189695395, 'Macro_F1_(ignoring_nan)': np.float64(0.3547212606566998)} [2025-03-24 20:32:49,535][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:32:49,536][__main__][INFO] - Training completed successfully. [2025-03-24 20:32:49,537][__main__][INFO] - Running on Test [2025-03-24 20:32:49,537][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, essay_text, id, reference, prompt, essay_year, supporting_text, grades. If id_prompt, essay_text, id, reference, prompt, essay_year, supporting_text, grades are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. [2025-03-24 20:32:49,539][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-03-24 20:32:49,539][transformers.trainer][INFO] - Num examples = 138 [2025-03-24 20:32:49,539][transformers.trainer][INFO] - Batch size = 16 [2025-03-24 20:33:09,361][transformers][INFO] - {'accuracy': 0.36231884057971014, 'RMSE': 65.31972647421809, 'QWK': 0.3441810010847668, 'HDIV': 0.07246376811594202, 'Macro_F1': 0.24235405087851392, 'Micro_F1': 0.36231884057971014, 'Weighted_F1': 0.32848489320136964, 'Macro_F1_(ignoring_nan)': np.float64(0.3635310763177709)} [2025-03-24 20:33:09,362][tensorboardX.summary][INFO] - Summary name eval/Macro_F1_(ignoring_nan) is illegal; using eval/Macro_F1__ignoring_nan_ instead. [2025-03-24 20:33:09,364][transformers.trainer][INFO] - Saving model checkpoint to ./results/phi35-balanced/C2/best_model [2025-03-24 20:33:09,802][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 20:33:09,803][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 20:33:17,890][__main__][INFO] - Fine Tuning Finished.