Training in progress, epoch 3

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "camembert-base",
+  "_name_or_path": "cmarkea/distilcamembert-base-ner",
   "architectures": [
     "CamembertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 5,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 6,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -62,8 +63,7 @@
   "max_position_embeddings": 514,
   "model_type": "camembert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702ac52ca5ff1dfda89b9a656c18e649bccbc90d6c8b371a7f80fbc64e6d50e1
-size 440213956
+oid sha256:6faaaf83cdd3d7dbf5527857d4bb47fdf97e5205f3e5ce980165bd931ef5697e
+size 270093412

runs/Jul04_08-40-36_a6439592a7b2/events.out.tfevents.1720082437.a6439592a7b2.453.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf3eb87754d3b3c175523f17aad55bfb6d94e465efbd6600d83009fc6dfd7bf
+size 7496

special_tokens_map.json

@@ -1,8 +1,7 @@
 {
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
+    "</s>NOTUSED"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer_config.json

@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "3": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -55,20 +55,11 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32005": {
-      "content": "<unk>NOTUSED",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
+    "</s>NOTUSED"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
@@ -78,6 +69,7 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5c5b45a5fde37427e19cc375234ddb51ef80678768201fd4690f8a333fbc99
+oid sha256:4e9eca8af6fabf3747197e99304bd66ffd349c5b83b295bfa5f82e87c2e34e79
 size 5112