Training in progress, step 500

config.json

@@ -1,25 +1,32 @@
 {
-  "_name_or_path": "distilbert-base-cased-distilled-squad",
-  "activation": "gelu",
+  "_name_or_path": "salti/bert-base-multilingual-cased-finetuned-squad",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
-  "tie_weights_": true,
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
-  "vocab_size": 28996
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc40b576e96e28aef8dcd002bc3c6e094d8ec1b16be5dae5f5b25639e306628
-size 260804645
+oid sha256:5e399aa031ab9bde49e6d53cbdf46d673bd74247e44db11d2135af0febeee632
+size 709129709

runs/Mar08_15-38-10_04752a836637/1678289959.5507143/events.out.tfevents.1678289959.04752a836637.161.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15a71f87819cc5d4da0010e0e163d48a9a302e95c936001893e7e1f15e28bda
+size 5667

runs/Mar08_15-38-10_04752a836637/events.out.tfevents.1678289959.04752a836637.161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a326296ff7d6bdd5d4c7815ed8384a5b95bbc775b40c0c69efe17c9c422198d
+size 6604

tokenizer_config.json

@@ -1,14 +1,16 @@
 {
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-cased-distilled-squad",
+  "name_or_path": "salti/bert-base-multilingual-cased-finetuned-squad",
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--salti--bert-base-multilingual-cased-finetuned-squad/snapshots/0368c75d052222a1188f1fd5c5b97f4064e58567/special_tokens_map.json",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d1ab3c03d3fb81122976ba1b81c9425cb189446736e0dfa821305994d552ac
+oid sha256:aa6d2a92d2e95b05e6b6ef068a21fffe5293db305478c65dd69c35587cd68f62
 size 3515