End of training

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-  "word_embedding_dimension": 384,
-  "pooling_mode_cls_token": false,
-  "pooling_mode_mean_tokens": true,
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
   "pooling_mode_max_tokens": false,
   "pooling_mode_mean_sqrt_len_tokens": false,
   "pooling_mode_weightedmean_tokens": false,

README.md

@@ -7,51 +7,51 @@ tags:
 - dataset_size:100
 - loss:MatryoshkaLoss
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: BAAI/bge-base-en-v1.5
 widget:
-- source_sentence: <start> TYTGGHJJUUYHTRRGGGRRDREDEERFED <end>
+- source_sentence: <start> FTYGHYHHYHGGTTGRREEEEEEEEDEEEE <end>
   sentences:
-  - published
-  - published
+  - 'on'
+  - later
   - The
-- source_sentence: <start> GTYHYYHHHYYHGFFFTTTRRFERREEDDW <end>
+- source_sentence: <start> YTTHHNNBHJHHGRFRRRFFEEEERRRRED <end>
   sentences:
-  - B.
-  - The
   - Spencers
-- source_sentence: The <start> LLMKIMYVERDWDERFTTTRFRRREEEERR <end> was later published
+  - Richard
+  - The
+- source_sentence: The <start> MLIUYFRRSWEREFRGTTRFTTTFEDWEER <end> was later published
     on Richard B.
   sentences:
   - The
   - Spencers
   - letter
-- source_sentence: The letter <start> WQWEWWWWDSAAWWSSAAZXZSSXXXDDSQ <end> later published
+- source_sentence: The letter was <start> PLJUGRFVAAQAWQSFRFYTTRREEDDEGR <end> published
     on Richard B.
   sentences:
   - The
+  - later
   - The
-  - was
-- source_sentence: The letter was <start> PLJUGRFVAAQAWQSFRFYTTRREEDDEGR <end> published
+- source_sentence: The letter was <start> OLKMUYFDXSSAAZWRGTTTGRRDEDDRRR <end> published
     on Richard B.
   sentences:
-  - later
   - letter
   - The
+  - later
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the generator dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the generator dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
-- **Maximum Sequence Length:** 256 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
     - generator
@@ -68,8 +68,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
   (2): Normalize()
 )
 ```
@@ -92,13 +92,13 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("checkpoints")
 # Run inference
 sentences = [
-    'The letter was <start> PLJUGRFVAAQAWQSFRFYTTRREEDDEGR <end> published on Richard B.',
+    'The letter was <start> OLKMUYFDXSSAAZWRGTTTGRRDEDDRRR <end> published on Richard B.',
     'later',
     'The',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 384]
+# [3, 768]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
@@ -167,10 +167,18 @@ You can finetune this model on your own dataset.
   {
       "loss": "MultipleNegativesRankingLoss",
       "matryoshka_dims": [
+          768,
+          512,
           384,
+          256,
+          128,
           64
       ],
       "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
           1,
           1
       ],
@@ -315,16 +323,16 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | Training Loss |
 |:-----:|:----:|:-------------:|
-| 0.4   | 10   | 5.9732        |
-| 0.8   | 20   | 5.0213        |
-| 1.2   | 30   | 2.5663        |
-| 1.6   | 40   | 2.3414        |
-| 2.0   | 50   | 1.6479        |
-| 2.4   | 60   | 1.4191        |
-| 2.8   | 70   | 1.4435        |
-| 3.2   | 80   | 1.5457        |
-| 3.6   | 90   | 1.3226        |
-| 4.0   | 100  | 1.1394        |
+| 0.4   | 10   | 13.6421       |
+| 0.8   | 20   | 11.8949       |
+| 1.2   | 30   | 7.241         |
+| 1.6   | 40   | 6.3184        |
+| 2.0   | 50   | 4.4524        |
+| 2.4   | 60   | 3.6606        |
+| 2.8   | 70   | 3.4123        |
+| 3.2   | 80   | 2.6028        |
+| 3.6   | 90   | 2.1896        |
+| 4.0   | 100  | 2.1076        |
 
 
 ### Framework Versions

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[END]": 30523,
+  "[START]": 30522
+}

config.json

@@ -7,19 +7,25 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30524
 }

eval/Information-Retrieval_evaluation_dim_128_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.0,0.1,0.14,0.4,0.0,0.0,0.03333333333333333,0.1,0.027999999999999997,0.14,0.04,0.4,0.08903571428571422,0.15891748166085473,0.1280443398620643
+2.0,50,0.1,0.11,0.13,0.5,0.1,0.1,0.03666666666666666,0.11,0.026000000000000002,0.13,0.05,0.5,0.15130952380952367,0.2269385614063873,0.18373924080735232
+3.0,75,0.1,0.1,0.15,0.47,0.1,0.1,0.03333333333333333,0.1,0.03,0.15,0.04699999999999999,0.47,0.15097619047619035,0.22097689479015556,0.18936047152881524
+None,0,0.0,0.0,0.0,0.44,0.0,0.0,0.0,0.0,0.0,0.0,0.044000000000000004,0.44,0.05490476190476188,0.13850552467454108,0.09346048396048395
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_dim_256_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.06,0.07,0.28,0.37,0.06,0.06,0.02333333333333333,0.07,0.05600000000000001,0.28,0.037000000000000005,0.37,0.1209801587301586,0.17837172608153767,0.15862331467981622
+2.0,50,0.1,0.12,0.19,0.41,0.1,0.1,0.039999999999999994,0.12,0.038000000000000006,0.19,0.040999999999999995,0.41,0.15186507936507923,0.20964629721675362,0.18852671077632382
+3.0,75,0.1,0.11,0.27,0.48,0.1,0.1,0.03666666666666666,0.11,0.054000000000000006,0.27,0.048,0.48,0.16601587301587287,0.23721331849834656,0.19977757596720444
+None,0,0.0,0.0,0.07,0.41,0.0,0.0,0.0,0.0,0.013999999999999999,0.07,0.040999999999999995,0.41,0.05853174603174605,0.13587224773156262,0.10210324805913042
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_dim_384_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.02,0.05,0.22,0.31,0.02,0.02,0.016666666666666666,0.05,0.044000000000000004,0.22,0.031000000000000007,0.31,0.08586904761904764,0.13828730301060527,0.12756731095701682
+2.0,50,0.1,0.12,0.16,0.31,0.1,0.1,0.039999999999999994,0.12,0.032,0.16,0.031,0.31,0.13404761904761897,0.17336238083258182,0.17839009988119894
+3.0,75,0.1,0.12,0.2,0.41,0.1,0.1,0.039999999999999994,0.12,0.04000000000000001,0.2,0.040999999999999995,0.41,0.15067063492063482,0.20877015107584718,0.19038975871909308
+None,0,0.0,0.0,0.07,0.34,0.0,0.0,0.0,0.0,0.014000000000000002,0.07,0.034,0.34,0.049218253968253974,0.11324168536312658,0.09819056841850958
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_dim_512_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.0,0.03,0.2,0.34,0.0,0.0,0.01,0.03,0.04,0.2,0.034,0.34,0.06984920634920636,0.13224375948142458,0.10933917346843042
+2.0,50,0.09,0.13,0.17,0.3,0.09,0.09,0.04333333333333333,0.13,0.034,0.17,0.03,0.3,0.1310238095238095,0.1690811231378314,0.17563488227458815
+3.0,75,0.1,0.13,0.17,0.4,0.1,0.1,0.04333333333333333,0.13,0.034,0.17,0.04,0.4,0.14872619047619037,0.20487994694445105,0.18983214742773566
+None,0,0.0,0.0,0.08,0.4,0.0,0.0,0.0,0.0,0.016,0.08,0.04,0.4,0.05428968253968255,0.129985584157983,0.10074305269893503
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_dim_64_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.08,0.1,0.21,0.32,0.08,0.08,0.03333333333333333,0.1,0.042,0.21,0.032,0.32,0.131797619047619,0.17534726235750558,0.17307788345984942
+2.0,50,0.1,0.18,0.21,0.36,0.1,0.1,0.06,0.18,0.042,0.21,0.036000000000000004,0.36,0.15984523809523804,0.2053888999109833,0.20180102624413773
+3.0,75,0.11,0.19,0.22,0.34,0.11,0.11,0.06333333333333332,0.19,0.044000000000000004,0.22,0.034,0.34,0.16101190476190472,0.20199186992553161,0.20712119291956754
+None,0,0.0,0.0,0.0,0.29,0.0,0.0,0.0,0.0,0.0,0.0,0.029000000000000005,0.29,0.03209523809523811,0.08710139890053481,0.08907092907092908
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_dim_768_results.csv

@@ -0,0 +1,8 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,25,0.0,0.03,0.16,0.33,0.0,0.0,0.01,0.03,0.032,0.16,0.033,0.33,0.06391269841269842,0.12438013321411066,0.10620924478857914
+2.0,50,0.08,0.12,0.14,0.26,0.08,0.08,0.039999999999999994,0.12,0.027999999999999997,0.14,0.026000000000000002,0.26,0.11834523809523803,0.15041653152432066,0.16498134545193366
+3.0,75,0.1,0.1,0.14,0.35,0.1,0.1,0.03333333333333333,0.1,0.027999999999999997,0.14,0.035,0.35,0.13278968253968246,0.17998457242588123,0.17666418630389225
+None,0,0.0,0.0,0.0,0.32,0.0,0.0,0.0,0.0,0.0,0.0,0.032,0.32,0.04357142857142856,0.10436767336990385,0.09584999559264264
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0
+None,0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333334,1.0,0.19999999999999996,1.0,0.09999999999999998,1.0,1.0,1.0,1.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed75f08e8a83a2c17feca9a3abe70195524eed243f665523939aa37a9457e041
-size 90864192
+oid sha256:4ca6eeae92e6efc831bf6a82a7584f012f0a9004a86fd9fcaa7ec41dd8f5295e
+size 437957472

runs/Jun11_16-40-59_snark.fritz.box/events.out.tfevents.1749652861.snark.fritz.box.78994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d20cbdd31ecf28535f8e1fdba0dc5865b20964cee54914b3573f91dcbc6672e
+size 24753

runs/Jun15_14-10-20_snark.fritz.box/events.out.tfevents.1749989436.snark.fritz.box.43343.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31120162a4fa69f4372a0b6b16533cd21cf55b317dc3eb5e6f30bc84314c1d5
+size 6276

runs/Jun15_14-15-02_snark.fritz.box/events.out.tfevents.1749989715.snark.fritz.box.44429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e337f62989e0c5ad50317044f2fb27564fe352849cd5a9b94f2bdfa89dddf04
+size 6276

runs/Jun15_14-23-07_snark.fritz.box/events.out.tfevents.1749990244.snark.fritz.box.45770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80b66cb641b86b526d9a3dba132db2f2da5d9752a215abc115caae86b0b0b10
+size 6276

runs/Jun15_14-26-47_snark.fritz.box/events.out.tfevents.1749990420.snark.fritz.box.46430.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812ace3a559ad2568a8992f9927b616887b70bf76c210c8763fd0795228d55a4
+size 6276

runs/Jun17_12-04-38_snark.fritz.box/events.out.tfevents.1750154680.snark.fritz.box.67555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21cef39306279df407d5385a47792ca4384c3e0ba8868908c1e896a3527f10c
+size 6772

runs/Jun17_12-09-44_snark.fritz.box/events.out.tfevents.1750155010.snark.fritz.box.68692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d951afc89aca83d46a61ce5651768b4b66024e6bb5f019cef975671092af6924
+size 6772

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
-  "do_lower_case": false
+  "max_seq_length": 512,
+  "do_lower_case": true
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -59,6 +59,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 30522,
+      "content": "[START]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
+    },
+    {
+      "id": 30523,
+      "content": "[END]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -39,27 +39,36 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30522": {
+      "content": "[START]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30523": {
+      "content": "[END]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_length": 128,
-  "model_max_length": 256,
+  "model_max_length": 512,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b704fd35f9d2b6ae30dc7809d90d313db8787a073f0da45f0731caea409816e
+oid sha256:1762c950240851dbfbe4aa34848965ecfc1203552f84ba62d02df00ba0c5f815
 size 5969