Training in progress, step 1000

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "xaviergillard/brabant-xvii-from-scratch",
   "architectures": [
     "BertForMaskedLM"
   ],
@@ -21,5 +20,5 @@
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30000
+  "vocab_size": 24263
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b86a2cc509ac7e2746580c69aa159ff81bed8402b61fe9f61f3342938d6e2a
-size 218249344
+oid sha256:53ca105990abc29101eab3e02b333731e25f4e15617b970881a24a1ae7f3f04e
+size 209425814

pretrained/config.json

@@ -1,6 +1,7 @@
 {
+  "_name_or_path": "xaviergillard/brabant-xvii-from-scratch",
   "architectures": [
-    "BertForPreTraining"
+    "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
@@ -16,7 +17,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,
   "use_cache": true,

pretrained/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

pretrained/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4d2ef66747dc05c596414c3c1e2389b1de3a88a78b298d0285da33617a4baa
-size 438844120
+oid sha256:09b86a2cc509ac7e2746580c69aa159ff81bed8402b61fe9f61f3342938d6e2a
+size 218249344

runs/Mar25_10-15-33_7cb2519f8d33/events.out.tfevents.1711361737.7cb2519f8d33.7223.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd8eea96e8fade053064345d538c31489e424d46bc5ce8724759dfb6b1530a3
-size 5136
+oid sha256:69d0e0d0808d3d433d390d522c40905cb3d9df778b2305f41a32068280429b52
+size 5490

runs/Mar25_15-37-08_21b37dc907a2/events.out.tfevents.1711381032.21b37dc907a2.4143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71565710b00bc6d8a4e478221313dcc5a11d3942f6574b7ad113a8c4417a7325
+size 4995

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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
+  }
 }

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00093e97dcead9ebde093c60dd0a716d6da4343c262cb1c3788a559146599d29
+oid sha256:5fe6a9709ab1107dcdfacad5c96386124ea75443fa03c2f01b6a0846c63ba6ce
 size 4984