indicators-env / final_eval_metrics.json
bawsi99's picture
Final clean submission
3a7314c
Raw
History Blame Contribute Delete
22.4 kB
{
"160": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-160",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": {
"overall_accuracy": 0.32,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.36,
"Bearish": 0.0,
"Neutral": 0.7
},
"precision": {
"Bullish": 0.5625,
"Bearish": 0.0,
"Neutral": 0.21875
},
"recall": {
"Bullish": 0.36,
"Bearish": 0.0,
"Neutral": 0.7
},
"f1_score": {
"Bullish": 0.43902439024390244,
"Bearish": 0.0,
"Neutral": 0.3333333333333333
},
"macro_f1": 0.25745257452574527,
"weighted_f1": 0.2861788617886179,
"confusion_matrix": [
[
9,
2,
14
],
[
4,
0,
11
],
[
3,
0,
7
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"finetuned_grpo": {
"overall_accuracy": 0.24,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.44,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.36666666666666664,
"Bearish": 0.05263157894736842,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.44,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4,
"Bearish": 0.058823529411764705,
"Neutral": 0.0
},
"macro_f1": 0.15294117647058825,
"weighted_f1": 0.21764705882352942,
"confusion_matrix": [
[
11,
14,
0
],
[
13,
1,
1
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": -0.08000000000000002,
"delta_macro_f1": -0.10451139805515702
},
"180": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-180",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.26,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.44,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.36666666666666664,
"Bearish": 0.1,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.44,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4,
"Bearish": 0.11428571428571428,
"Neutral": 0.0
},
"macro_f1": 0.17142857142857146,
"weighted_f1": 0.23428571428571426,
"confusion_matrix": [
[
11,
14,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"200": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-200",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.26,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.44,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.36666666666666664,
"Bearish": 0.1,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.44,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4,
"Bearish": 0.11428571428571428,
"Neutral": 0.0
},
"macro_f1": 0.17142857142857146,
"weighted_f1": 0.23428571428571426,
"confusion_matrix": [
[
11,
14,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"220": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-220",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.32,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.2,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.41935483870967744,
"Bearish": 0.15789473684210525,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.2,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4642857142857143,
"Bearish": 0.17647058823529413,
"Neutral": 0.0
},
"macro_f1": 0.2135854341736695,
"weighted_f1": 0.2850840336134454,
"confusion_matrix": [
[
13,
12,
0
],
[
12,
3,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"240": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-240",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.32,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.2,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.41935483870967744,
"Bearish": 0.15789473684210525,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.2,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4642857142857143,
"Bearish": 0.17647058823529413,
"Neutral": 0.0
},
"macro_f1": 0.2135854341736695,
"weighted_f1": 0.2850840336134454,
"confusion_matrix": [
[
13,
12,
0
],
[
12,
3,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"260": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-260",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.40625,
"Bearish": 0.1111111111111111,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.45614035087719296,
"Bearish": 0.12121212121212122,
"Neutral": 0.0
},
"macro_f1": 0.1924508240297714,
"weighted_f1": 0.26443381180223285,
"confusion_matrix": [
[
13,
12,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"280": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-280",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.40625,
"Bearish": 0.1111111111111111,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.45614035087719296,
"Bearish": 0.12121212121212122,
"Neutral": 0.0
},
"macro_f1": 0.1924508240297714,
"weighted_f1": 0.26443381180223285,
"confusion_matrix": [
[
13,
12,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"300": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-300",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.4117647058823529,
"Bearish": 0.0625,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4745762711864407,
"Bearish": 0.06451612903225806,
"Neutral": 0.0
},
"macro_f1": 0.17969746673956624,
"weighted_f1": 0.2566429743028978,
"confusion_matrix": [
[
14,
11,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"460": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-460",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.4117647058823529,
"Bearish": 0.0625,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4745762711864407,
"Bearish": 0.06451612903225806,
"Neutral": 0.0
},
"macro_f1": 0.17969746673956624,
"weighted_f1": 0.2566429743028978,
"confusion_matrix": [
[
14,
11,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"480": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-480",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.4117647058823529,
"Bearish": 0.0625,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4745762711864407,
"Bearish": 0.06451612903225806,
"Neutral": 0.0
},
"macro_f1": 0.17969746673956624,
"weighted_f1": 0.2566429743028978,
"confusion_matrix": [
[
14,
11,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"500": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-500",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.28,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.3939393939393939,
"Bearish": 0.058823529411764705,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4482758620689655,
"Bearish": 0.0625,
"Neutral": 0.0
},
"macro_f1": 0.17025862068965517,
"weighted_f1": 0.24288793103448278,
"confusion_matrix": [
[
13,
12,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"520": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-520",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.28,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.3939393939393939,
"Bearish": 0.058823529411764705,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4482758620689655,
"Bearish": 0.0625,
"Neutral": 0.0
},
"macro_f1": 0.17025862068965517,
"weighted_f1": 0.24288793103448278,
"confusion_matrix": [
[
13,
12,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"540": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-540",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.4117647058823529,
"Bearish": 0.0625,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.56,
"Bearish": 0.06666666666666667,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4745762711864407,
"Bearish": 0.06451612903225806,
"Neutral": 0.0
},
"macro_f1": 0.17969746673956624,
"weighted_f1": 0.2566429743028978,
"confusion_matrix": [
[
14,
11,
0
],
[
14,
1,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"560": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-560",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.40625,
"Bearish": 0.1111111111111111,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.45614035087719296,
"Bearish": 0.12121212121212122,
"Neutral": 0.0
},
"macro_f1": 0.1924508240297714,
"weighted_f1": 0.26443381180223285,
"confusion_matrix": [
[
13,
12,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"580": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-580",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.32,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.56,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.42424242424242425,
"Bearish": 0.11764705882352941,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.56,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.4827586206896552,
"Bearish": 0.125,
"Neutral": 0.0
},
"macro_f1": 0.20258620689655174,
"weighted_f1": 0.2788793103448276,
"confusion_matrix": [
[
14,
11,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
},
"600": {
"model_id": "Qwen/Qwen2.5-7B-Instruct",
"adapter_path": "/content/drive/MyDrive/indicators_grpo_v2/checkpoint-600",
"n_eval": 50,
"term": "medium",
"baseline_zeroshot": null,
"finetuned_grpo": {
"overall_accuracy": 0.3,
"n_eval": 50,
"by_class_accuracy": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"precision": {
"Bullish": 0.40625,
"Bearish": 0.1111111111111111,
"Neutral": 0.0
},
"recall": {
"Bullish": 0.52,
"Bearish": 0.13333333333333333,
"Neutral": 0.0
},
"f1_score": {
"Bullish": 0.45614035087719296,
"Bearish": 0.12121212121212122,
"Neutral": 0.0
},
"macro_f1": 0.1924508240297714,
"weighted_f1": 0.26443381180223285,
"confusion_matrix": [
[
13,
12,
0
],
[
13,
2,
0
],
[
6,
4,
0
]
],
"confusion_matrix_labels": [
"Bullish",
"Bearish",
"Neutral"
],
"class_distribution": {
"Bullish": 25,
"Bearish": 15,
"Neutral": 10
}
},
"delta_accuracy": 0,
"delta_macro_f1": 0
}
}