Training in progress, step 500

README.md

@@ -1,37 +1,60 @@
 ---
-language: en
+library_name: transformers
 license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
 tags:
-- question-answering
-- squad
-pipeline_tag: question-answering  # Clé pour activer le widget QA
-datasets:
-- squad
-widget:
-- question: "Who supervises the 2017 film Baby Driver?"
-  context: "Baby Driver is a 2017 American action film written and directed by Edgar Wright. The film stars Ansel Elgort, Lily James, Jamie Foxx, Jon Hamm, Eiza González and Kevin Spacey. The plot follows a young getaway driver who must complete a final job for a crime boss. Baby Driver was released in the United States by TriStar Pictures on June 28, 2017, and received praise from critics."
+- generated_from_trainer
 model-index:
-- name: distilbert-base-uncased-finetuned-squad
-  results:
-  - task:
-      type: question-answering
-    dataset:
-      name: squad
-      type: squad
-    metrics:
-      - name: f1
-        type: f1
-        value: 85.5  # Remplace par ton score F1 (ex. de trainer.evaluate())
-      - name: exact_match
-        type: exact_match
-        value: 78.2  # Remplace par ton score Exact Match
+- name: my_awesome_qa_model
+  results: []
 ---
 
-# Ton modèle QA
-Ce modèle est DistilBERT fine-tuné sur SQuAD pour extraire des réponses à des questions dans un contexte.
+<!-- 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. -->
 
-## Utilisation
-```python
-from transformers import pipeline
-qa = pipeline("question-answering", model="Titemaybe/my_awesome_qa_model")
-print(qa(question="Who supervises the 2017 film Baby Driver?", context="..."))
+# my_awesome_qa_model
+
+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: 1.7431
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 250  | 2.6253          |
+| 2.9024        | 2.0   | 500  | 1.8672          |
+| 2.9024        | 3.0   | 750  | 1.7431          |
+
+
+### Framework versions
+
+- Transformers 4.56.2
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efdb2ccb7349fcb80d08a92e11b53ae58afe062536e96ef4a9fc07439c847ad
+oid sha256:4b5f645a0a034fa2dd3c9556a0d425a45ca7af82ae8bd82a4e8389deb67baf16
 size 265470032

runs/Oct08_12-48-45_6eabe5bb0e9c/events.out.tfevents.1759927727.6eabe5bb0e9c.540.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77e5f1fd6225feefb469043a769e996cb7ceb0630efc1be98e038e4ef53ef17
+size 5351

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -46,18 +46,11 @@
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_length": 384,
   "model_max_length": 512,
-  "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": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d7b40c4bcc1318944a85bcd3d3ca00b430c9fc6a650cf5b974580a8b94d634
+oid sha256:8fe53714ed432c4a6c43abbeb6a4b85f03b7527af50e3f6adbf8f7ab698cb2d6
 size 5777