Add deepseek/modernbert
Browse files- deepseek/modernbert/p3/sigma3/finetuned/config.json +41 -0
- deepseek/modernbert/p3/sigma3/finetuned/model.safetensors +3 -0
- deepseek/modernbert/p3/sigma3/not_finetuned/config.json +41 -0
- deepseek/modernbert/p3/sigma3/not_finetuned/model.safetensors +3 -0
- deepseek/modernbert/p3/sigma5/finetuned/config.json +41 -0
- deepseek/modernbert/p3/sigma5/finetuned/model.safetensors +3 -0
- deepseek/modernbert/p3/sigma5/not_finetuned/config.json +41 -0
- deepseek/modernbert/p3/sigma5/not_finetuned/model.safetensors +3 -0
- deepseek/modernbert/p5/sigma3/finetuned/config.json +45 -0
- deepseek/modernbert/p5/sigma3/finetuned/model.safetensors +3 -0
- deepseek/modernbert/p5/sigma3/not_finetuned/config.json +45 -0
- deepseek/modernbert/p5/sigma3/not_finetuned/model.safetensors +3 -0
- deepseek/modernbert/p5/sigma5/finetuned/config.json +45 -0
- deepseek/modernbert/p5/sigma5/finetuned/model.safetensors +3 -0
- deepseek/modernbert/p5/sigma5/not_finetuned/config.json +45 -0
- deepseek/modernbert/p5/sigma5/not_finetuned/model.safetensors +3 -0
deepseek/modernbert/p3/sigma3/finetuned/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p3-sigma3",
|
| 4 |
+
"qualified_id": "finetuning/deepseek-modernbert-p3-sigma3",
|
| 5 |
+
"track": "finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p3",
|
| 10 |
+
"sigma": 3,
|
| 11 |
+
"fine_tuning": "finetuned",
|
| 12 |
+
"frozen_backbone": false,
|
| 13 |
+
"num_classes": 3,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"1": "Negative",
|
| 16 |
+
"0": "Neutral",
|
| 17 |
+
"2": "Positive"
|
| 18 |
+
},
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Negative": 1,
|
| 21 |
+
"Neutral": 0,
|
| 22 |
+
"Positive": 2
|
| 23 |
+
},
|
| 24 |
+
"max_len": 512,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"batch_size": 32,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p3_sigma3_finetuned.pt",
|
| 29 |
+
"source_sha256": "4835e810b30c19a6a96a3f0779e6161ccff0b982efe98eb1ca51d8d3fcfba107",
|
| 30 |
+
"tied_weights": {},
|
| 31 |
+
"kfold_f1": [
|
| 32 |
+
0.707071,
|
| 33 |
+
0.677641,
|
| 34 |
+
0.708842,
|
| 35 |
+
0.724982,
|
| 36 |
+
0.721445
|
| 37 |
+
],
|
| 38 |
+
"mean_f1": 0.707996,
|
| 39 |
+
"mean_accuracy": 0.706548,
|
| 40 |
+
"folds": 5
|
| 41 |
+
}
|
deepseek/modernbert/p3/sigma3/finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def6be427be68d8362a25031744910ba369aa019e559edcf28193ee7626fb2b5
|
| 3 |
+
size 791686870
|
deepseek/modernbert/p3/sigma3/not_finetuned/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p3-sigma3",
|
| 4 |
+
"qualified_id": "not-finetuning/deepseek-modernbert-p3-sigma3",
|
| 5 |
+
"track": "not-finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p3",
|
| 10 |
+
"sigma": 3,
|
| 11 |
+
"fine_tuning": "not_finetuned",
|
| 12 |
+
"frozen_backbone": true,
|
| 13 |
+
"num_classes": 3,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"1": "Negative",
|
| 16 |
+
"0": "Neutral",
|
| 17 |
+
"2": "Positive"
|
| 18 |
+
},
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Negative": 1,
|
| 21 |
+
"Neutral": 0,
|
| 22 |
+
"Positive": 2
|
| 23 |
+
},
|
| 24 |
+
"max_len": 512,
|
| 25 |
+
"learning_rate": 0.01,
|
| 26 |
+
"batch_size": 512,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p3_sigma3_not_finetuned.pt",
|
| 29 |
+
"source_sha256": "05ba699f1ac482d7ab3133483b74bbc563762f32933244aae93a541abba0e23e",
|
| 30 |
+
"tied_weights": {},
|
| 31 |
+
"kfold_f1": [
|
| 32 |
+
0.571645,
|
| 33 |
+
0.56324,
|
| 34 |
+
0.557558,
|
| 35 |
+
0.536981,
|
| 36 |
+
0.655764
|
| 37 |
+
],
|
| 38 |
+
"mean_f1": 0.577037,
|
| 39 |
+
"mean_accuracy": 0.567902,
|
| 40 |
+
"folds": 5
|
| 41 |
+
}
|
deepseek/modernbert/p3/sigma3/not_finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b6eaae92acb3b9d97585d6ffc5d914079897b92619c5ef9ea443e9bbafdebb
|
| 3 |
+
size 789587478
|
deepseek/modernbert/p3/sigma5/finetuned/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p3-sigma5",
|
| 4 |
+
"qualified_id": "finetuning/deepseek-modernbert-p3-sigma5",
|
| 5 |
+
"track": "finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p3",
|
| 10 |
+
"sigma": 5,
|
| 11 |
+
"fine_tuning": "finetuned",
|
| 12 |
+
"frozen_backbone": false,
|
| 13 |
+
"num_classes": 3,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"1": "Negative",
|
| 16 |
+
"0": "Neutral",
|
| 17 |
+
"2": "Positive"
|
| 18 |
+
},
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Negative": 1,
|
| 21 |
+
"Neutral": 0,
|
| 22 |
+
"Positive": 2
|
| 23 |
+
},
|
| 24 |
+
"max_len": 512,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"batch_size": 32,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p3_sigma5_finetuned.pt",
|
| 29 |
+
"source_sha256": "07f0017f199c5adf57b5a739222f7bc8b3f32be0015e8855fe813fa88b9fef3f",
|
| 30 |
+
"tied_weights": {},
|
| 31 |
+
"kfold_f1": [
|
| 32 |
+
0.880894,
|
| 33 |
+
0.915454,
|
| 34 |
+
0.878893,
|
| 35 |
+
0.899512,
|
| 36 |
+
0.899084
|
| 37 |
+
],
|
| 38 |
+
"mean_f1": 0.894767,
|
| 39 |
+
"mean_accuracy": 0.894048,
|
| 40 |
+
"folds": 5
|
| 41 |
+
}
|
deepseek/modernbert/p3/sigma5/finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2773d57d623a8a1730916ab1481c1ca43688234e514682e209c501aafab223c
|
| 3 |
+
size 791686870
|
deepseek/modernbert/p3/sigma5/not_finetuned/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p3-sigma5",
|
| 4 |
+
"qualified_id": "not-finetuning/deepseek-modernbert-p3-sigma5",
|
| 5 |
+
"track": "not-finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p3",
|
| 10 |
+
"sigma": 5,
|
| 11 |
+
"fine_tuning": "not_finetuned",
|
| 12 |
+
"frozen_backbone": true,
|
| 13 |
+
"num_classes": 3,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"1": "Negative",
|
| 16 |
+
"0": "Neutral",
|
| 17 |
+
"2": "Positive"
|
| 18 |
+
},
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Negative": 1,
|
| 21 |
+
"Neutral": 0,
|
| 22 |
+
"Positive": 2
|
| 23 |
+
},
|
| 24 |
+
"max_len": 512,
|
| 25 |
+
"learning_rate": 0.01,
|
| 26 |
+
"batch_size": 512,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p3_sigma5_not_finetuned.pt",
|
| 29 |
+
"source_sha256": "7861798baad9f731996bf0310e3fa66ed95470ac94a3fb4ac6a615f63eadfd5a",
|
| 30 |
+
"tied_weights": {},
|
| 31 |
+
"kfold_f1": [
|
| 32 |
+
0.797441,
|
| 33 |
+
0.831414,
|
| 34 |
+
0.749663,
|
| 35 |
+
0.781371,
|
| 36 |
+
0.798533
|
| 37 |
+
],
|
| 38 |
+
"mean_f1": 0.791684,
|
| 39 |
+
"mean_accuracy": 0.778571,
|
| 40 |
+
"folds": 5
|
| 41 |
+
}
|
deepseek/modernbert/p3/sigma5/not_finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:801349b2d5e7e4e4e3c57455d8ef279757fceb95122d8f645530a0684d9ba9a3
|
| 3 |
+
size 789587478
|
deepseek/modernbert/p5/sigma3/finetuned/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p5-sigma3",
|
| 4 |
+
"qualified_id": "finetuning/deepseek-modernbert-p5-sigma3",
|
| 5 |
+
"track": "finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p5",
|
| 10 |
+
"sigma": 3,
|
| 11 |
+
"fine_tuning": "finetuned",
|
| 12 |
+
"frozen_backbone": false,
|
| 13 |
+
"num_classes": 5,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Negative",
|
| 16 |
+
"1": "SlightlyNegative",
|
| 17 |
+
"2": "Neutral",
|
| 18 |
+
"3": "SlightlyPositive",
|
| 19 |
+
"4": "Positive"
|
| 20 |
+
},
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Negative": 0,
|
| 23 |
+
"SlightlyNegative": 1,
|
| 24 |
+
"Neutral": 2,
|
| 25 |
+
"SlightlyPositive": 3,
|
| 26 |
+
"Positive": 4
|
| 27 |
+
},
|
| 28 |
+
"max_len": 512,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"batch_size": 32,
|
| 31 |
+
"torch_dtype": "float16",
|
| 32 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p5_sigma3_finetuned.pt",
|
| 33 |
+
"source_sha256": "45b5852ddf846e11f25c2f5b53bfb6f5ec3a772b6e4f3ca2ce7a69b6313f40ea",
|
| 34 |
+
"tied_weights": {},
|
| 35 |
+
"kfold_f1": [
|
| 36 |
+
0.529728,
|
| 37 |
+
0.503739,
|
| 38 |
+
0.502883,
|
| 39 |
+
0.502152,
|
| 40 |
+
0.485146
|
| 41 |
+
],
|
| 42 |
+
"mean_f1": 0.50473,
|
| 43 |
+
"mean_accuracy": 0.498872,
|
| 44 |
+
"folds": 5
|
| 45 |
+
}
|
deepseek/modernbert/p5/sigma3/finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e154396f993ca5c3aa1fb8d3bb970f443410b06c0e5c719b0aa7ac918e0f7c
|
| 3 |
+
size 791690970
|
deepseek/modernbert/p5/sigma3/not_finetuned/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p5-sigma3",
|
| 4 |
+
"qualified_id": "not-finetuning/deepseek-modernbert-p5-sigma3",
|
| 5 |
+
"track": "not-finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p5",
|
| 10 |
+
"sigma": 3,
|
| 11 |
+
"fine_tuning": "not_finetuned",
|
| 12 |
+
"frozen_backbone": true,
|
| 13 |
+
"num_classes": 5,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Negative",
|
| 16 |
+
"1": "SlightlyNegative",
|
| 17 |
+
"2": "Neutral",
|
| 18 |
+
"3": "SlightlyPositive",
|
| 19 |
+
"4": "Positive"
|
| 20 |
+
},
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Negative": 0,
|
| 23 |
+
"SlightlyNegative": 1,
|
| 24 |
+
"Neutral": 2,
|
| 25 |
+
"SlightlyPositive": 3,
|
| 26 |
+
"Positive": 4
|
| 27 |
+
},
|
| 28 |
+
"max_len": 512,
|
| 29 |
+
"learning_rate": 0.01,
|
| 30 |
+
"batch_size": 512,
|
| 31 |
+
"torch_dtype": "float16",
|
| 32 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p5_sigma3_not_finetuned.pt",
|
| 33 |
+
"source_sha256": "6f77b6ef79aa4f9dbb14dcff7035ea286e396d9a19db0357814f2b8841169490",
|
| 34 |
+
"tied_weights": {},
|
| 35 |
+
"kfold_f1": [
|
| 36 |
+
0.380091,
|
| 37 |
+
0.380405,
|
| 38 |
+
0.383092,
|
| 39 |
+
0.356251,
|
| 40 |
+
0.41019
|
| 41 |
+
],
|
| 42 |
+
"mean_f1": 0.382006,
|
| 43 |
+
"mean_accuracy": 0.404093,
|
| 44 |
+
"folds": 5
|
| 45 |
+
}
|
deepseek/modernbert/p5/sigma3/not_finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0f22e3fbd108c91e2dd5107adf55bce26d029a5ccf098f826c400268daabdf5
|
| 3 |
+
size 789591586
|
deepseek/modernbert/p5/sigma5/finetuned/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p5-sigma5",
|
| 4 |
+
"qualified_id": "finetuning/deepseek-modernbert-p5-sigma5",
|
| 5 |
+
"track": "finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p5",
|
| 10 |
+
"sigma": 5,
|
| 11 |
+
"fine_tuning": "finetuned",
|
| 12 |
+
"frozen_backbone": false,
|
| 13 |
+
"num_classes": 5,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Negative",
|
| 16 |
+
"1": "SlightlyNegative",
|
| 17 |
+
"2": "Neutral",
|
| 18 |
+
"3": "SlightlyPositive",
|
| 19 |
+
"4": "Positive"
|
| 20 |
+
},
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Negative": 0,
|
| 23 |
+
"SlightlyNegative": 1,
|
| 24 |
+
"Neutral": 2,
|
| 25 |
+
"SlightlyPositive": 3,
|
| 26 |
+
"Positive": 4
|
| 27 |
+
},
|
| 28 |
+
"max_len": 512,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"batch_size": 32,
|
| 31 |
+
"torch_dtype": "float16",
|
| 32 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p5_sigma5_finetuned.pt",
|
| 33 |
+
"source_sha256": "10d84438e8bd2d562a59a52055dc27db8de940e060b3f8d4d8214b8574268985",
|
| 34 |
+
"tied_weights": {},
|
| 35 |
+
"kfold_f1": [
|
| 36 |
+
0.731071,
|
| 37 |
+
0.726649,
|
| 38 |
+
0.649448,
|
| 39 |
+
0.674508,
|
| 40 |
+
0.605856
|
| 41 |
+
],
|
| 42 |
+
"mean_f1": 0.677507,
|
| 43 |
+
"mean_accuracy": 0.688265,
|
| 44 |
+
"folds": 5
|
| 45 |
+
}
|
deepseek/modernbert/p5/sigma5/finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b919a0612f0facd04579f27bd4f7baaab74ae07bba18921bfb6ff6136dbb9a
|
| 3 |
+
size 791690970
|
deepseek/modernbert/p5/sigma5/not_finetuned/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mllmsent_format": 1,
|
| 3 |
+
"spec_id": "deepseek-modernbert-p5-sigma5",
|
| 4 |
+
"qualified_id": "not-finetuning/deepseek-modernbert-p5-sigma5",
|
| 5 |
+
"track": "not-finetuning",
|
| 6 |
+
"base_model": "answerdotai/ModernBERT-large",
|
| 7 |
+
"caption_mllm": "deepseek",
|
| 8 |
+
"text_backbone": "modernbert",
|
| 9 |
+
"problem": "p5",
|
| 10 |
+
"sigma": 5,
|
| 11 |
+
"fine_tuning": "not_finetuned",
|
| 12 |
+
"frozen_backbone": true,
|
| 13 |
+
"num_classes": 5,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Negative",
|
| 16 |
+
"1": "SlightlyNegative",
|
| 17 |
+
"2": "Neutral",
|
| 18 |
+
"3": "SlightlyPositive",
|
| 19 |
+
"4": "Positive"
|
| 20 |
+
},
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Negative": 0,
|
| 23 |
+
"SlightlyNegative": 1,
|
| 24 |
+
"Neutral": 2,
|
| 25 |
+
"SlightlyPositive": 3,
|
| 26 |
+
"Positive": 4
|
| 27 |
+
},
|
| 28 |
+
"max_len": 512,
|
| 29 |
+
"learning_rate": 0.01,
|
| 30 |
+
"batch_size": 512,
|
| 31 |
+
"torch_dtype": "float16",
|
| 32 |
+
"source_checkpoint": "best_checkpoint_deepseek_modernbert_p5_sigma5_not_finetuned.pt",
|
| 33 |
+
"source_sha256": "ca7a70817a01ea56ba356e156ce6edca9e2cf62ffd1e54acf8ba50f37d13d8f3",
|
| 34 |
+
"tied_weights": {},
|
| 35 |
+
"kfold_f1": [
|
| 36 |
+
0.633978,
|
| 37 |
+
0.598136,
|
| 38 |
+
0.596665,
|
| 39 |
+
0.572364,
|
| 40 |
+
0.662752
|
| 41 |
+
],
|
| 42 |
+
"mean_f1": 0.612779,
|
| 43 |
+
"mean_accuracy": 0.605343,
|
| 44 |
+
"folds": 5
|
| 45 |
+
}
|
deepseek/modernbert/p5/sigma5/not_finetuned/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:060ae782d2bcc32d93b9355167b2a07b773e16324914deadde8cc3635a52f398
|
| 3 |
+
size 789591586
|