Upload 13 files

1_Pooling/config.json

@@ -1,9 +1,5 @@
 {
   "word_embedding_dimension": 1024,
-  "pooling_mode_cls_token": false,
-  "pooling_mode_mean_tokens": false,
-  "pooling_mode_max_tokens": false,
-  "pooling_mode_mean_sqrt_len_tokens": false,
-  "pooling_mode_weightedmean_tokens": true,
-  "pooling_mode_lasttoken": false
+  "position_start": 0,
+  "num_positions": 512
 }

1_Pooling/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b5b722c730d9037743f6cbc1222e6c304f9659ae02911530578368a513e65c
+size 2877

README.md

@@ -8,7 +8,7 @@ tags:
 
 # {MODEL_NAME}
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a None dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -45,29 +45,31 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1100 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 30617 with parameters:
 ```
-{'batch_size': 512}
+{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
 **Loss**:
 
-`sentence_transformers.losses.MultipleNegativesRankingLoss.MNRLGradCache` 
+`sentence_transformers.losses.MSELoss.MSELoss` 
 
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 1,
-    "evaluation_steps": 110,
-    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "epochs": 3,
+    "evaluation_steps": 1000,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'transformers.optimization.AdamW'>",
     "optimizer_params": {
-        "lr": 0.00032
+        "correct_bias": false,
+        "eps": 1e-06,
+        "lr": 2e-05
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 110,
+    "warmup_steps": 10000,
     "weight_decay": 0.01
 }
 ```
@@ -76,8 +78,8 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: BloomModel 
-  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BloomModel 
+  (1): WeightedMeanPooling()
 )
 ```
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bigscience/bloom-560m",
+  "_name_or_path": "Mayhem50/sgpt-bloom-560M-nli",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomModel"

eval/mse_evaluation_TED2020-en-fr-dev.tsv.gz_results.csv

@@ -0,0 +1,55 @@
+epoch,steps,MSE
+0,1000,1272.7741241455078
+0,2000,1239.7001266479492
+0,3000,1244.563388824463
+0,4000,1255.099868774414
+0,5000,1284.8063468933105
+0,6000,1265.7715797424316
+0,7000,1308.1769943237305
+0,8000,1277.3436546325684
+0,9000,1263.1890296936035
+0,10000,1308.1955909729004
+0,11000,1283.3735466003418
+0,12000,1262.7530097961426
+0,13000,1260.5589866638184
+0,14000,1253.4588813781738
+0,15000,1239.389419555664
+0,16000,1284.862232208252
+0,17000,1215.8602714538574
+0,18000,1208.6514472961426
+0,19000,1207.7702522277832
+0,20000,1203.3350944519043
+0,21000,1202.7355194091797
+0,22000,1193.0546760559082
+0,23000,1168.9787864685059
+0,24000,1169.53125
+0,25000,1167.289161682129
+0,26000,1183.1158638000488
+0,27000,1167.3190116882324
+0,28000,1135.9935760498047
+0,29000,1140.6807899475098
+0,30000,1136.8371963500977
+0,-1,1127.4292945861816
+1,31000,1103.3071517944336
+1,32000,1101.201057434082
+1,33000,1093.484878540039
+1,34000,1085.3593826293945
+1,35000,1087.46919631958
+1,36000,1088.6981964111328
+1,37000,1085.8448028564453
+1,38000,1079.0802955627441
+1,39000,1078.3958435058594
+1,40000,1067.711067199707
+1,41000,1070.4686164855957
+1,42000,1062.2697830200195
+1,43000,1062.1541023254395
+1,44000,1061.3683700561523
+1,45000,1068.0513381958008
+1,46000,1060.914134979248
+1,47000,1047.8565216064453
+1,48000,1049.0880012512207
+1,49000,1041.7594909667969
+1,50000,1047.9501724243164
+1,51000,1041.0179138183594
+1,52000,1047.9998588562012
+1,53000,1035.096263885498

eval/translation_evaluation_TED2020-en-fr-dev.tsv.gz_results.csv

@@ -0,0 +1,55 @@
+epoch,steps,src2trg,trg2src
+0,1000,0.963,0.96
+0,2000,0.965,0.964
+0,3000,0.963,0.962
+0,4000,0.967,0.963
+0,5000,0.966,0.959
+0,6000,0.97,0.963
+0,7000,0.966,0.962
+0,8000,0.968,0.966
+0,9000,0.974,0.964
+0,10000,0.969,0.96
+0,11000,0.972,0.965
+0,12000,0.969,0.956
+0,13000,0.962,0.957
+0,14000,0.97,0.963
+0,15000,0.969,0.967
+0,16000,0.967,0.959
+0,17000,0.971,0.962
+0,18000,0.97,0.964
+0,19000,0.965,0.962
+0,20000,0.968,0.965
+0,21000,0.972,0.967
+0,22000,0.968,0.965
+0,23000,0.972,0.966
+0,24000,0.967,0.957
+0,25000,0.972,0.961
+0,26000,0.97,0.959
+0,27000,0.969,0.962
+0,28000,0.967,0.968
+0,29000,0.968,0.963
+0,30000,0.969,0.965
+0,-1,0.968,0.961
+1,31000,0.968,0.964
+1,32000,0.969,0.967
+1,33000,0.971,0.966
+1,34000,0.972,0.965
+1,35000,0.973,0.968
+1,36000,0.973,0.97
+1,37000,0.973,0.966
+1,38000,0.971,0.967
+1,39000,0.972,0.969
+1,40000,0.973,0.967
+1,41000,0.972,0.967
+1,42000,0.97,0.967
+1,43000,0.968,0.967
+1,44000,0.97,0.96
+1,45000,0.969,0.965
+1,46000,0.972,0.964
+1,47000,0.97,0.967
+1,48000,0.972,0.965
+1,49000,0.971,0.969
+1,50000,0.973,0.969
+1,51000,0.971,0.969
+1,52000,0.973,0.967
+1,53000,0.972,0.967

modules.json

@@ -8,7 +8,7 @@
   {
     "idx": 1,
     "name": "1",
-    "path": "1_Pooling",
-    "type": "sentence_transformers.models.Pooling"
+    "path": "1_WeightedMeanPooling",
+    "type": "sentence_transformers.models.WeightedMeanPooling"
   }
 ]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315daacf1871ff28875d33e477925ed63831ef9a6db45fd01d44ae3feed61e33
+oid sha256:1085ad4f1f628a9ff63ec9b12a5a0b6258f11c982ebbbcc6fe16f5ea7c49c4ed
 size 2236953889

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 75,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796518d81847a3370a556a1c4bc940286069aec6dbbc8cb61deb5f696dac82f7
-size 14500694
+oid sha256:872aa95025502051626b31ba2ddf6709b05318c68e3cfd501dd0ee688f166724
+size 14500695

tokenizer_config.json

@@ -3,7 +3,7 @@
   "bos_token": "<s>",
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "bigscience/bloom-560m",
+  "name_or_path": "Mayhem50/sgpt-bloom-560M-nli",
   "pad_token": "<pad>",
   "padding_side": "left",
   "special_tokens_map_file": null,