End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google-bert/bert-base-multilingual-cased
+base_model: distilbert/distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # dzoQA_ml
 
-This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.5072
+- Loss: 5.2318
 
 ## Model description
 
@@ -40,15 +40,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 9
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 17   | 7.1536          |
-| No log        | 2.0   | 34   | 7.5442          |
-| No log        | 3.0   | 51   | 7.5072          |
+| No log        | 1.0   | 17   | 5.5030          |
+| No log        | 2.0   | 34   | 5.4155          |
+| No log        | 3.0   | 51   | 5.3362          |
+| No log        | 4.0   | 68   | 5.3240          |
+| No log        | 5.0   | 85   | 5.2659          |
+| No log        | 6.0   | 102  | 5.2410          |
+| No log        | 7.0   | 119  | 5.2223          |
+| No log        | 8.0   | 136  | 5.2406          |
+| No log        | 9.0   | 153  | 5.2318          |
 
 
 ### Framework versions

config.json

@@ -1,31 +1,24 @@
 {
-  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForQuestionAnswering"
+    "DistilBertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748206fd3b8529f4927b2c408cc8149a327a949d0504d8fa9ebb574faf1a4c35
-size 709080904
+oid sha256:4a0cf06565271ac16eebe172709b89bba1f5b7f8a1dadb92f865d9b05a895525
+size 265470032

runs/May12_11-56-27_01050a5ad463/events.out.tfevents.1715514991.01050a5ad463.3537.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa646ed9f3f296f7d128fd7ba8c22e66f61ec807aa7d4d4531fe177fab2f273
+size 7297

tokenizer_config.json

@@ -43,13 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6b6eedf6d775923837c3e3479be2e2067d244544e87b41241343c0a307ad58
+oid sha256:187097fc6101f836fcc5dd3c5eb82cd40da080eec328859f1b4c17afa3cfcea4
 size 4984