abarbosa's picture
Pushing fine-tuned model to Hugging Face Hub
72d687f verified
Raw History Blame Contribute Delete
57.9 kB
[2025-07-05 07:05:28,066][__main__][INFO] - cache_dir: /tmp/
dataset:
name: kamel-usp/aes_enem_dataset
split: JBCS2025
training_params:
seed: 42
num_train_epochs: 20
logging_steps: 100
metric_for_best_model: QWK
bf16: true
bootstrap:
enabled: true
n_bootstrap: 10000
bootstrap_seed: 42
metrics:
- QWK
- Macro_F1
- Weighted_F1
post_training_results:
model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
experiments:
model:
name: microsoft/Phi-3.5-mini-instruct
type: phi35_classification_lora
num_labels: 6
output_dir: ./results/llama31-8b-balanced/C5
logging_dir: ./logs/llama31-8b-balanced/C5
best_model_dir: ./results/llama31-8b-balanced/C5/best_model
lora_r: 8
lora_dropout: 0.05
lora_alpha: 16
lora_target_modules: all-linear
tokenizer:
name: microsoft/Phi-3.5-mini-instruct
dataset:
grade_index: 4
use_full_context: true
training_params:
weight_decay: 0.01
warmup_ratio: 0.1
learning_rate: 5.0e-05
train_batch_size: 8
eval_batch_size: 4
gradient_accumulation_steps: 2
gradient_checkpointing: true
[2025-07-05 07:05:31,974][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W
[2025-07-05 07:05:31,974][__main__][INFO] - Starting the Fine Tuning training process.
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file tokenizer.model from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.model
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.json
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/added_tokens.json
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/special_tokens_map.json
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer_config.json
[2025-07-05 07:05:36,427][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
[2025-07-05 07:05:36,480][transformers.tokenization_utils_base][INFO] - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[2025-07-05 07:05:36,485][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True
[2025-07-05 07:05:37,958][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:05:37,959][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5"
},
"initializer_range": 0.02,
"intermediate_size": 8192,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:05:37,959][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/model.safetensors.index.json
[2025-07-05 07:05:37,959][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
[2025-07-05 07:05:37,959][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16.
[2025-07-05 07:05:45,465][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).
[2025-07-05 07:05:45,466][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.
[2025-07-05 07:05:46,166][__main__][INFO] - Initialized new PEFT model for ce loss
[2025-07-05 07:05:46,168][__main__][INFO] - None
[2025-07-05 07:05:46,168][transformers.training_args][INFO] - PyTorch: setting up devices
[2025-07-05 07:05:46,223][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
[2025-07-05 07:05:46,227][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
[2025-07-05 07:05:46,250][transformers.trainer][INFO] - Using auto half precision backend
[2025-07-05 07:05:46,251][transformers.trainer][WARNING] - No label_names provided for model class `PeftModelForSequenceClassification`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.
[2025-07-05 07:05:46,252][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:05:46,262][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:05:46,262][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:05:46,262][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:06:05,340][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:06:05,372][transformers.trainer][INFO] - ***** Running training *****
[2025-07-05 07:06:05,372][transformers.trainer][INFO] - Num examples = 500
[2025-07-05 07:06:05,372][transformers.trainer][INFO] - Num Epochs = 20
[2025-07-05 07:06:05,372][transformers.trainer][INFO] - Instantaneous batch size per device = 8
[2025-07-05 07:06:05,372][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16
[2025-07-05 07:06:05,373][transformers.trainer][INFO] - Gradient Accumulation steps = 2
[2025-07-05 07:06:05,373][transformers.trainer][INFO] - Total optimization steps = 640
[2025-07-05 07:06:05,374][transformers.trainer][INFO] - Number of trainable parameters = 12,601,344
[2025-07-05 07:06:05,481][transformers.models.phi3.modeling_phi3][WARNING] - `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
[2025-07-05 07:07:17,935][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:07:17,939][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:07:17,939][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:07:17,939][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:07:36,709][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-32
[2025-07-05 07:07:37,003][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:07:37,003][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:08:49,839][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:08:49,842][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:08:49,842][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:08:49,842][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:09:08,565][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-64
[2025-07-05 07:09:08,856][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:09:08,857][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:09:08,964][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-32] due to args.save_total_limit
[2025-07-05 07:10:21,576][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:10:21,579][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:10:21,579][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:10:21,579][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:10:40,315][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-96
[2025-07-05 07:10:40,624][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:10:40,624][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:10:40,842][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-64] due to args.save_total_limit
[2025-07-05 07:11:53,374][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:11:53,378][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:11:53,378][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:11:53,378][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:12:12,108][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-128
[2025-07-05 07:12:12,576][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:12:12,577][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:13:25,231][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:13:25,235][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:13:25,235][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:13:25,235][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:13:43,973][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-160
[2025-07-05 07:13:44,283][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:13:44,284][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:13:44,358][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-128] due to args.save_total_limit
[2025-07-05 07:14:56,975][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:14:56,978][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:14:56,978][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:14:56,978][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:15:15,709][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-192
[2025-07-05 07:15:16,022][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:15:16,023][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:15:16,154][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-160] due to args.save_total_limit
[2025-07-05 07:16:28,702][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:16:28,705][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:16:28,705][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:16:28,705][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:16:47,428][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-224
[2025-07-05 07:16:47,758][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:16:47,759][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:16:47,857][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-192] due to args.save_total_limit
[2025-07-05 07:18:00,436][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:18:00,439][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:18:00,440][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:18:00,440][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:18:19,168][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-256
[2025-07-05 07:18:19,498][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:18:19,498][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:18:19,556][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-224] due to args.save_total_limit
[2025-07-05 07:18:19,560][transformers.trainer][INFO] -
Training completed. Do not forget to share your model on huggingface.co/models =)
[2025-07-05 07:18:19,560][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-96 (score: 0.31449351143223847).
[2025-07-05 07:18:19,661][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/07-05-28/results/llama31-8b-balanced/C5/checkpoint-256] due to args.save_total_limit
[2025-07-05 07:18:19,665][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:18:19,668][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:18:19,668][transformers.trainer][INFO] - Num examples = 132
[2025-07-05 07:18:19,668][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:18:38,382][__main__][INFO] - Training completed successfully.
[2025-07-05 07:18:38,382][__main__][INFO] - Running on Test
[2025-07-05 07:18:38,382][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference. If id, grades, essay_year, supporting_text, prompt, essay_text, id_prompt, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-05 07:18:38,385][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-05 07:18:38,385][transformers.trainer][INFO] - Num examples = 138
[2025-07-05 07:18:38,385][transformers.trainer][INFO] - Batch size = 4
[2025-07-05 07:18:58,113][__main__][INFO] - Test metrics: {'eval_loss': 1.7179045677185059, 'eval_model_preparation_time': 0.0074, 'eval_accuracy': 0.21014492753623187, 'eval_RMSE': 76.7453912131782, 'eval_QWK': 0.2313832119989475, 'eval_HDIV': 0.21014492753623193, 'eval_Macro_F1': 0.22240047534165183, 'eval_Micro_F1': 0.21014492753623187, 'eval_Weighted_F1': 0.202111358377343, 'eval_TP_0': 5, 'eval_TN_0': 83, 'eval_FP_0': 33, 'eval_FN_0': 17, 'eval_TP_1': 9, 'eval_TN_1': 79, 'eval_FP_1': 27, 'eval_FN_1': 23, 'eval_TP_2': 3, 'eval_TN_2': 99, 'eval_FP_2': 15, 'eval_FN_2': 21, 'eval_TP_3': 1, 'eval_TN_3': 104, 'eval_FP_3': 9, 'eval_FN_3': 24, 'eval_TP_4': 10, 'eval_TN_4': 82, 'eval_FP_4': 24, 'eval_FN_4': 22, 'eval_TP_5': 1, 'eval_TN_5': 134, 'eval_FP_5': 1, 'eval_FN_5': 2, 'eval_runtime': 19.7202, 'eval_samples_per_second': 6.998, 'eval_steps_per_second': 1.775, 'epoch': 8.0}
[2025-07-05 07:18:58,113][transformers.trainer][INFO] - Saving model checkpoint to ./results/llama31-8b-balanced/C5/best_model
[2025-07-05 07:18:58,457][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
[2025-07-05 07:18:58,458][transformers.configuration_utils][INFO] - Model config Phi3Config {
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "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": "4.53.0",
"use_cache": true,
"vocab_size": 32064
}
[2025-07-05 07:18:58,553][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/llama31-8b-balanced/C5/best_model/chat_template.jinja
[2025-07-05 07:18:58,554][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/llama31-8b-balanced/C5/best_model/tokenizer_config.json
[2025-07-05 07:18:58,554][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/llama31-8b-balanced/C5/best_model/special_tokens_map.json
[2025-07-05 07:18:58,576][__main__][INFO] - Model and tokenizer saved to ./results/llama31-8b-balanced/C5/best_model
[2025-07-05 07:18:58,580][__main__][INFO] - Fine Tuning Finished.
[2025-07-05 07:18:59,091][__main__][INFO] - Total emissions: 0.0100 kg CO2eq