Create README.md

README.md

@@ -0,0 +1,863 @@
+---
+license: mit
+base_model: croissantllm/CroissantCool-v0.2
+datasets: asi/wikitext_fr
+tags:
+- generated_from_trainer
+- mteb
+metrics:
+- accuracy
+model-index:
+- name: final
+  results:
+    - task:
+        type: Clustering
+      dataset:
+        type: lyon-nlp/alloprof
+        name: MTEB AlloProfClusteringP2P (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
+      metrics:
+      - type: v_measure
+        value: 62.345943052433995
+    - task:
+        type: Clustering
+      dataset:
+        type: lyon-nlp/alloprof
+        name: MTEB AlloProfClusteringS2S (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
+      metrics:
+      - type: v_measure
+        value: 25.729454984521148
+    - task:
+        type: Reranking
+      dataset:
+        type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
+        name: MTEB AlloprofReranking (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 65393d0d7a08a10b4e348135e824f385d420b0fd
+      metrics:
+      - type: map
+        value: 26.596323297349183
+      - type: mrr
+        value: 26.091629657044162
+    - task:
+        type: Retrieval
+      dataset:
+        type: lyon-nlp/alloprof
+        name: MTEB AlloprofRetrieval (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: fcf295ea64c750f41fadbaa37b9b861558e1bfbd
+      metrics:
+      - type: map_at_1
+        value: 0.345
+      - type: map_at_10
+        value: 0.9339999999999999
+      - type: map_at_100
+        value: 1.191
+      - type: map_at_1000
+        value: 1.3419999999999999
+      - type: map_at_20
+        value: 1.02
+      - type: map_at_3
+        value: 0.6689999999999999
+      - type: map_at_5
+        value: 0.753
+      - type: mrr_at_1
+        value: 0.345
+      - type: mrr_at_10
+        value: 0.9339999999999999
+      - type: mrr_at_100
+        value: 1.191
+      - type: mrr_at_1000
+        value: 1.3419999999999999
+      - type: mrr_at_20
+        value: 1.02
+      - type: mrr_at_3
+        value: 0.6689999999999999
+      - type: mrr_at_5
+        value: 0.753
+      - type: ndcg_at_1
+        value: 0.345
+      - type: ndcg_at_10
+        value: 1.384
+      - type: ndcg_at_100
+        value: 3.1510000000000002
+      - type: ndcg_at_1000
+        value: 9.014
+      - type: ndcg_at_20
+        value: 1.6920000000000002
+      - type: ndcg_at_3
+        value: 0.7849999999999999
+      - type: ndcg_at_5
+        value: 0.941
+      - type: precision_at_1
+        value: 0.345
+      - type: precision_at_10
+        value: 0.28900000000000003
+      - type: precision_at_100
+        value: 0.124
+      - type: precision_at_1000
+        value: 0.063
+      - type: precision_at_20
+        value: 0.20500000000000002
+      - type: precision_at_3
+        value: 0.374
+      - type: precision_at_5
+        value: 0.302
+      - type: recall_at_1
+        value: 0.345
+      - type: recall_at_10
+        value: 2.8930000000000002
+      - type: recall_at_100
+        value: 12.435
+      - type: recall_at_1000
+        value: 62.867
+      - type: recall_at_20
+        value: 4.102
+      - type: recall_at_3
+        value: 1.123
+      - type: recall_at_5
+        value: 1.5110000000000001
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/amazon_reviews_multi
+        name: MTEB AmazonReviewsClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 1399c76144fd37290681b995c656ef9b2e06e26d
+      metrics:
+      - type: accuracy
+        value: 32.662
+      - type: f1
+        value: 32.443152253731846
+    - task:
+        type: Retrieval
+      dataset:
+        type: maastrichtlawtech/bsard
+        name: MTEB BSARDRetrieval (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
+      metrics:
+      - type: map_at_1
+        value: 0.0
+      - type: map_at_10
+        value: 0.0
+      - type: map_at_100
+        value: 0.062
+      - type: map_at_1000
+        value: 0.077
+      - type: map_at_20
+        value: 0.0
+      - type: map_at_3
+        value: 0.0
+      - type: map_at_5
+        value: 0.0
+      - type: mrr_at_1
+        value: 0.0
+      - type: mrr_at_10
+        value: 0.0
+      - type: mrr_at_100
+        value: 0.062
+      - type: mrr_at_1000
+        value: 0.077
+      - type: mrr_at_20
+        value: 0.0
+      - type: mrr_at_3
+        value: 0.0
+      - type: mrr_at_5
+        value: 0.0
+      - type: ndcg_at_1
+        value: 0.0
+      - type: ndcg_at_10
+        value: 0.0
+      - type: ndcg_at_100
+        value: 0.484
+      - type: ndcg_at_1000
+        value: 1.054
+      - type: ndcg_at_20
+        value: 0.0
+      - type: ndcg_at_3
+        value: 0.0
+      - type: ndcg_at_5
+        value: 0.0
+      - type: precision_at_1
+        value: 0.0
+      - type: precision_at_10
+        value: 0.0
+      - type: precision_at_100
+        value: 0.027
+      - type: precision_at_1000
+        value: 0.008
+      - type: precision_at_20
+        value: 0.0
+      - type: precision_at_3
+        value: 0.0
+      - type: precision_at_5
+        value: 0.0
+      - type: recall_at_1
+        value: 0.0
+      - type: recall_at_10
+        value: 0.0
+      - type: recall_at_100
+        value: 2.703
+      - type: recall_at_1000
+        value: 7.6579999999999995
+      - type: recall_at_20
+        value: 0.0
+      - type: recall_at_3
+        value: 0.0
+      - type: recall_at_5
+        value: 0.0
+    - task:
+        type: Clustering
+      dataset:
+        type: lyon-nlp/clustering-hal-s2s
+        name: MTEB HALClusteringS2S (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915
+      metrics:
+      - type: v_measure
+        value: 13.77084465510841
+    - task:
+        type: Clustering
+      dataset:
+        type: mlsum
+        name: MTEB MLSUMClusteringP2P (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
+      metrics:
+      - type: v_measure
+        value: 45.43375637260015
+    - task:
+        type: Clustering
+      dataset:
+        type: mlsum
+        name: MTEB MLSUMClusteringS2S (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
+      metrics:
+      - type: v_measure
+        value: 45.20564648796975
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/mtop_domain
+        name: MTEB MTOPDomainClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
+      metrics:
+      - type: accuracy
+        value: 73.42937676166615
+      - type: f1
+        value: 72.65861284500563
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/mtop_intent
+        name: MTEB MTOPIntentClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
+      metrics:
+      - type: accuracy
+        value: 58.54368932038836
+      - type: f1
+        value: 37.51985447597095
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/masakhanews
+        name: MTEB MasakhaNEWSClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 18193f187b92da67168c655c9973a165ed9593dd
+      metrics:
+      - type: accuracy
+        value: 75.56872037914692
+      - type: f1
+        value: 71.99185345982795
+    - task:
+        type: Clustering
+      dataset:
+        type: masakhane/masakhanews
+        name: MTEB MasakhaNEWSClusteringP2P (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
+      metrics:
+      - type: v_measure
+        value: 38.20382948117535
+    - task:
+        type: Clustering
+      dataset:
+        type: masakhane/masakhanews
+        name: MTEB MasakhaNEWSClusteringS2S (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
+      metrics:
+      - type: v_measure
+        value: 26.943825642352117
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/amazon_massive_intent
+        name: MTEB MassiveIntentClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 4672e20407010da34463acc759c162ca9734bca6
+      metrics:
+      - type: accuracy
+        value: 50.20847343644924
+      - type: f1
+        value: 47.32281768380685
+    - task:
+        type: Classification
+      dataset:
+        type: mteb/amazon_massive_scenario
+        name: MTEB MassiveScenarioClassification (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
+      metrics:
+      - type: accuracy
+        value: 52.57565568258238
+      - type: f1
+        value: 50.95953249242336
+    - task:
+        type: Retrieval
+      dataset:
+        type: jinaai/mintakaqa
+        name: MTEB MintakaRetrieval (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e
+      metrics:
+      - type: map_at_1
+        value: 0.164
+      - type: map_at_10
+        value: 0.584
+      - type: map_at_100
+        value: 0.8240000000000001
+      - type: map_at_1000
+        value: 0.9769999999999999
+      - type: map_at_20
+        value: 0.6669999999999999
+      - type: map_at_3
+        value: 0.40299999999999997
+      - type: map_at_5
+        value: 0.47600000000000003
+      - type: mrr_at_1
+        value: 0.164
+      - type: mrr_at_10
+        value: 0.584
+      - type: mrr_at_100
+        value: 0.8240000000000001
+      - type: mrr_at_1000
+        value: 0.9769999999999999
+      - type: mrr_at_20
+        value: 0.6669999999999999
+      - type: mrr_at_3
+        value: 0.40299999999999997
+      - type: mrr_at_5
+        value: 0.47600000000000003
+      - type: ndcg_at_1
+        value: 0.164
+      - type: ndcg_at_10
+        value: 0.8670000000000001
+      - type: ndcg_at_100
+        value: 2.443
+      - type: ndcg_at_1000
+        value: 8.671
+      - type: ndcg_at_20
+        value: 1.176
+      - type: ndcg_at_3
+        value: 0.47800000000000004
+      - type: ndcg_at_5
+        value: 0.612
+      - type: precision_at_1
+        value: 0.164
+      - type: precision_at_10
+        value: 0.18
+      - type: precision_at_100
+        value: 0.10200000000000001
+      - type: precision_at_1000
+        value: 0.064
+      - type: precision_at_20
+        value: 0.152
+      - type: precision_at_3
+        value: 0.232
+      - type: precision_at_5
+        value: 0.20500000000000002
+      - type: recall_at_1
+        value: 0.164
+      - type: recall_at_10
+        value: 1.802
+      - type: recall_at_100
+        value: 10.156
+      - type: recall_at_1000
+        value: 64.21
+      - type: recall_at_20
+        value: 3.0300000000000002
+      - type: recall_at_3
+        value: 0.696
+      - type: recall_at_5
+        value: 1.024
+    - task:
+        type: PairClassification
+      dataset:
+        type: GEM/opusparcus
+        name: MTEB OpusparcusPC (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a
+      metrics:
+      - type: cos_sim_accuracy
+        value: 73.433242506812
+      - type: cos_sim_ap
+        value: 86.03577758642086
+      - type: cos_sim_f1
+        value: 82.1602478972997
+      - type: cos_sim_precision
+        value: 74.12140575079871
+      - type: cos_sim_recall
+        value: 92.15491559086395
+      - type: dot_accuracy
+        value: 68.8692098092643
+      - type: dot_ap
+        value: 75.51070462676913
+      - type: dot_f1
+        value: 81.47547628698824
+      - type: dot_precision
+        value: 68.83561643835617
+      - type: dot_recall
+        value: 99.80139026812313
+      - type: euclidean_accuracy
+        value: 73.84196185286103
+      - type: euclidean_ap
+        value: 86.27910998502644
+      - type: euclidean_f1
+        value: 82.5531914893617
+      - type: euclidean_precision
+        value: 72.22635889798957
+      - type: euclidean_recall
+        value: 96.32571996027805
+      - type: manhattan_accuracy
+        value: 73.9100817438692
+      - type: manhattan_ap
+        value: 86.43527306280204
+      - type: manhattan_f1
+        value: 82.57349808265872
+      - type: manhattan_precision
+        value: 72.31343283582089
+      - type: manhattan_recall
+        value: 96.22641509433963
+      - type: max_accuracy
+        value: 73.9100817438692
+      - type: max_ap
+        value: 86.43527306280204
+      - type: max_f1
+        value: 82.57349808265872
+    - task:
+        type: PairClassification
+      dataset:
+        type: paws-x
+        name: MTEB PawsX (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 8a04d940a42cd40658986fdd8e3da561533a3646
+      metrics:
+      - type: cos_sim_accuracy
+        value: 61.550000000000004
+      - type: cos_sim_ap
+        value: 60.30864957174996
+      - type: cos_sim_f1
+        value: 62.891311994372145
+      - type: cos_sim_precision
+        value: 46.08247422680412
+      - type: cos_sim_recall
+        value: 99.00332225913621
+      - type: dot_accuracy
+        value: 55.35
+      - type: dot_ap
+        value: 47.540176633815165
+      - type: dot_f1
+        value: 62.20227821884707
+      - type: dot_precision
+        value: 45.18555667001003
+      - type: dot_recall
+        value: 99.77851605758582
+      - type: euclidean_accuracy
+        value: 61.95
+      - type: euclidean_ap
+        value: 60.44070441806914
+      - type: euclidean_f1
+        value: 62.89978678038379
+      - type: euclidean_precision
+        value: 46.31083202511774
+      - type: euclidean_recall
+        value: 98.00664451827242
+      - type: manhattan_accuracy
+        value: 61.9
+      - type: manhattan_ap
+        value: 60.52939878134297
+      - type: manhattan_f1
+        value: 63.034188034188034
+      - type: manhattan_precision
+        value: 46.45669291338583
+      - type: manhattan_recall
+        value: 98.00664451827242
+      - type: max_accuracy
+        value: 61.95
+      - type: max_ap
+        value: 60.52939878134297
+      - type: max_f1
+        value: 63.034188034188034
+    - task:
+        type: STS
+      dataset:
+        type: Lajavaness/SICK-fr
+        name: MTEB SICKFr (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a
+      metrics:
+      - type: cos_sim_pearson
+        value: 55.697943925847646
+      - type: cos_sim_spearman
+        value: 53.33151992866752
+      - type: euclidean_pearson
+        value: 54.32882764397367
+      - type: euclidean_spearman
+        value: 53.54968438609837
+      - type: manhattan_pearson
+        value: 54.56634524641888
+      - type: manhattan_spearman
+        value: 53.81344727168701
+    - task:
+        type: STS
+      dataset:
+        type: mteb/sts22-crosslingual-sts
+        name: MTEB STS22 (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
+      metrics:
+      - type: cos_sim_pearson
+        value: 22.771197036286605
+      - type: cos_sim_spearman
+        value: 60.29016180301653
+      - type: euclidean_pearson
+        value: 35.31319988418939
+      - type: euclidean_spearman
+        value: 59.61398871828641
+      - type: manhattan_pearson
+        value: 36.10315029818106
+      - type: manhattan_spearman
+        value: 60.5122301133988
+    - task:
+        type: STS
+      dataset:
+        type: mteb/stsb_multi_mt
+        name: MTEB STSBenchmarkMultilingualSTS (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 29afa2569dcedaaa2fe6a3dcfebab33d28b82e8c
+      metrics:
+      - type: cos_sim_pearson
+        value: 47.730796921644384
+      - type: cos_sim_spearman
+        value: 49.54059034135741
+      - type: euclidean_pearson
+        value: 49.48474815018905
+      - type: euclidean_spearman
+        value: 50.71533884079761
+      - type: manhattan_pearson
+        value: 50.10488858533032
+      - type: manhattan_spearman
+        value: 51.1375710610132
+    - task:
+        type: Summarization
+      dataset:
+        type: lyon-nlp/summarization-summeval-fr-p2p
+        name: MTEB SummEvalFr (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: b385812de6a9577b6f4d0f88c6a6e35395a94054
+      metrics:
+      - type: cos_sim_pearson
+        value: 29.102661066592816
+      - type: cos_sim_spearman
+        value: 29.615000554218955
+      - type: dot_pearson
+        value: 19.77690299595119
+      - type: dot_spearman
+        value: 19.112834848310158
+    - task:
+        type: Reranking
+      dataset:
+        type: lyon-nlp/mteb-fr-reranking-syntec-s2p
+        name: MTEB SyntecReranking (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: daf0863838cd9e3ba50544cdce3ac2b338a1b0ad
+      metrics:
+      - type: map
+        value: 37.372655122655125
+      - type: mrr
+        value: 37.28174603174604
+    - task:
+        type: Retrieval
+      dataset:
+        type: lyon-nlp/mteb-fr-retrieval-syntec-s2p
+        name: MTEB SyntecRetrieval (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: 19661ccdca4dfc2d15122d776b61685f48c68ca9
+      metrics:
+      - type: map_at_1
+        value: 2.0
+      - type: map_at_10
+        value: 6.816999999999999
+      - type: map_at_100
+        value: 9.522
+      - type: map_at_1000
+        value: 9.522
+      - type: map_at_20
+        value: 8.402
+      - type: map_at_3
+        value: 4.167
+      - type: map_at_5
+        value: 4.867
+      - type: mrr_at_1
+        value: 2.0
+      - type: mrr_at_10
+        value: 6.816999999999999
+      - type: mrr_at_100
+        value: 9.522
+      - type: mrr_at_1000
+        value: 9.522
+      - type: mrr_at_20
+        value: 8.402
+      - type: mrr_at_3
+        value: 4.167
+      - type: mrr_at_5
+        value: 4.867
+      - type: ndcg_at_1
+        value: 2.0
+      - type: ndcg_at_10
+        value: 10.940999999999999
+      - type: ndcg_at_100
+        value: 25.96
+      - type: ndcg_at_1000
+        value: 25.96
+      - type: ndcg_at_20
+        value: 16.742
+      - type: ndcg_at_3
+        value: 4.893
+      - type: ndcg_at_5
+        value: 6.141
+      - type: precision_at_1
+        value: 2.0
+      - type: precision_at_10
+        value: 2.5
+      - type: precision_at_100
+        value: 1.0
+      - type: precision_at_1000
+        value: 0.1
+      - type: precision_at_20
+        value: 2.4
+      - type: precision_at_3
+        value: 2.333
+      - type: precision_at_5
+        value: 2.0
+      - type: recall_at_1
+        value: 2.0
+      - type: recall_at_10
+        value: 25.0
+      - type: recall_at_100
+        value: 100.0
+      - type: recall_at_1000
+        value: 100.0
+      - type: recall_at_20
+        value: 48.0
+      - type: recall_at_3
+        value: 7.000000000000001
+      - type: recall_at_5
+        value: 10.0
+    - task:
+        type: Retrieval
+      dataset:
+        type: jinaai/xpqa
+        name: MTEB XPQARetrieval (fra-Latn)
+        config: fra-Latn
+        split: test
+        revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f
+      metrics:
+      - type: map_at_1
+        value: 9.437
+      - type: map_at_10
+        value: 13.574
+      - type: map_at_100
+        value: 14.265
+      - type: map_at_1000
+        value: 14.527999999999999
+      - type: map_at_20
+        value: 13.834
+      - type: map_at_3
+        value: 12.277000000000001
+      - type: map_at_5
+        value: 12.936
+      - type: mrr_at_1
+        value: 14.285999999999998
+      - type: mrr_at_10
+        value: 18.269
+      - type: mrr_at_100
+        value: 18.991
+      - type: mrr_at_1000
+        value: 19.15
+      - type: mrr_at_20
+        value: 18.598
+      - type: mrr_at_3
+        value: 17.0
+      - type: mrr_at_5
+        value: 17.681
+      - type: ndcg_at_1
+        value: 14.285999999999998
+      - type: ndcg_at_10
+        value: 16.447
+      - type: ndcg_at_100
+        value: 20.617
+      - type: ndcg_at_1000
+        value: 27.589000000000002
+      - type: ndcg_at_20
+        value: 17.455000000000002
+      - type: ndcg_at_3
+        value: 14.540000000000001
+      - type: ndcg_at_5
+        value: 15.084
+      - type: precision_at_1
+        value: 14.285999999999998
+      - type: precision_at_10
+        value: 3.698
+      - type: precision_at_100
+        value: 0.734
+      - type: precision_at_1000
+        value: 0.18
+      - type: precision_at_20
+        value: 2.163
+      - type: precision_at_3
+        value: 8.366999999999999
+      - type: precision_at_5
+        value: 5.928
+      - type: recall_at_1
+        value: 9.437
+      - type: recall_at_10
+        value: 20.16
+      - type: recall_at_100
+        value: 38.527
+      - type: recall_at_1000
+        value: 85.102
+      - type: recall_at_20
+        value: 23.632
+      - type: recall_at_3
+        value: 14.562
+      - type: recall_at_5
+        value: 16.8
+
+language:
+- fr
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llm2vec-croissant-mntp
+
+This model is a fine-tuned version of [croissantllm/CroissantCool-v0.2](https://huggingface.co/croissantllm/CroissantCool-v0.2) on [asi/wikitext_fr](asi/wikitext_fr).
+It achieves the following results on the evaluation set:
+- Loss: 1.8867
+- Accuracy: 0.6078
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.0884 | 100  | 4.7866          | 0.1990   |
+| No log        | 0.1768 | 200  | 4.0496          | 0.3309   |
+| No log        | 0.2653 | 300  | 3.6525          | 0.3779   |
+| No log        | 0.3537 | 400  | 3.2410          | 0.4258   |
+| 3.9116        | 0.4421 | 500  | 3.6305          | 0.3912   |
+| 3.9116        | 0.5305 | 600  | 3.1770          | 0.4406   |
+| 3.9116        | 0.6189 | 700  | 2.4478          | 0.5199   |
+| 3.9116        | 0.7073 | 800  | 2.2383          | 0.5508   |
+| 3.9116        | 0.7958 | 900  | 2.1547          | 0.5635   |
+| 2.4568        | 0.8842 | 1000 | 2.0868          | 0.5759   |
+| 2.4568        | 0.9726 | 1100 | 2.0399          | 0.5820   |
+| 2.4568        | 1.0610 | 1200 | 2.0102          | 0.5873   |
+| 2.4568        | 1.1494 | 1300 | 1.9805          | 0.5897   |
+| 2.4568        | 1.2378 | 1400 | 1.9590          | 0.5955   |
+| 1.9305        | 1.3263 | 1500 | 1.9381          | 0.5982   |
+| 1.9305        | 1.4147 | 1600 | 1.9249          | 0.5995   |
+| 1.9305        | 1.5031 | 1700 | 1.9223          | 0.6017   |
+| 1.9305        | 1.5915 | 1800 | 1.9091          | 0.6037   |
+| 1.9305        | 1.6799 | 1900 | 1.9038          | 0.6042   |
+| 1.8511        | 1.7683 | 2000 | 1.8982          | 0.6045   |
+| 1.8511        | 1.8568 | 2100 | 1.8924          | 0.6060   |
+| 1.8511        | 1.9452 | 2200 | 1.8844          | 0.6072   |
+| 1.8511        | 2.0336 | 2300 | 1.8873          | 0.6087   |
+| 1.8511        | 2.1220 | 2400 | 1.8889          | 0.6068   |
+| 1.8197        | 2.2104 | 2500 | 1.8848          | 0.6080   |
+| 1.8197        | 2.2989 | 2600 | 1.8736          | 0.6091   |
+| 1.8197        | 2.3873 | 2700 | 1.8858          | 0.6072   |
+| 1.8197        | 2.4757 | 2800 | 1.8814          | 0.6088   |
+| 1.8197        | 2.5641 | 2900 | 1.8649          | 0.6103   |
+| 1.8116        | 2.6525 | 3000 | 1.8647          | 0.6091   |
+| 1.8116        | 2.7409 | 3100 | 1.8755          | 0.6101   |
+| 1.8116        | 2.8294 | 3200 | 1.8755          | 0.6099   |
+| 1.8116        | 2.9178 | 3300 | 1.8867          | 0.6078   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1