Training complete

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: camembert/camembert-base
+base_model: camembert/camembert-large
 tags:
 - generated_from_trainer
 metrics:
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # relatives_psr-cbert_finetuned
 
-This model is a fine-tuned version of [camembert/camembert-base](https://huggingface.co/camembert/camembert-base) on an unknown dataset.
+This model is a fine-tuned version of [camembert/camembert-large](https://huggingface.co/camembert/camembert-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2415
-- Precision: 0.9906
-- Recall: 0.3333
-- F1: 0.3286
-- Accuracy: 0.9718
+- Loss: 0.0532
+- Precision: 0.6127
+- Recall: 0.5628
+- F1: 0.5835
+- Accuracy: 0.9789
 
 ## Model description
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 49   | 0.3068          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
-| No log        | 2.0   | 98   | 0.2658          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
-| No log        | 3.0   | 147  | 0.2512          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
-| No log        | 4.0   | 196  | 0.2439          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
-| No log        | 5.0   | 245  | 0.2415          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
+| No log        | 1.0   | 49   | 0.1420          | 0.9906    | 0.3333 | 0.3286 | 0.9718   |
+| No log        | 2.0   | 98   | 0.0846          | 0.7921    | 0.6010 | 0.5037 | 0.9733   |
+| No log        | 3.0   | 147  | 0.0590          | 0.6117    | 0.5888 | 0.5891 | 0.9782   |
+| No log        | 4.0   | 196  | 0.0555          | 0.6077    | 0.6158 | 0.5861 | 0.9794   |
+| No log        | 5.0   | 245  | 0.0532          | 0.6127    | 0.5628 | 0.5835 | 0.9789   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "camembert/camembert-base",
+  "_name_or_path": "camembert/camembert-large",
   "architectures": [
     "CamembertForTokenClassification"
   ],
@@ -7,10 +7,9 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "eos_token_ids": 0,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "DET",
@@ -18,7 +17,7 @@
     "3": "AMBIGUE"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "AMBIGUE": 3,
     "APPO": 2,
@@ -28,14 +27,14 @@
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "camembert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 32005
+  "vocab_size": 100000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b71e4c5d625ff39e27ef3251a03ec2d5c7de546f5f7b66a68f0b4e649eaae42
-size 440161664
+oid sha256:be2a36d6f4db76b657b6d145cd7fc40e9289789b017ffa945fef7c78a80e811a
+size 1621019680

runs/Jun04_22-42-32_dd4455f1defd/events.out.tfevents.1717540964.dd4455f1defd.1891.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91997c716a859e7a2eece1818afcf758e6958fdade7c9508fcf50e7b00434be2
+size 7694

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637fa905c788e3b9757b85a29d87bb11527bddeacb478dacde15ec27363df3be
+oid sha256:1bb43257ef2c6ef3f820ebe04c3bdfa572be0b6a428055080fbcaaa588f00480
 size 5112