Training complete

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: camembert-base
+base_model: camembert/camembert-large
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # relatives_psr_seq-cbert_finetuned
 
-This model is a fine-tuned version of [camembert-base](https://huggingface.co/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: 0.8671
-- Precision: 0.9512
-- Recall: 0.2004
-- F1: 0.1730
-- Accuracy: 0.7559
+- Loss: 0.6317
+- Precision: 0.7005
+- Recall: 0.2671
+- F1: 0.2695
+- Accuracy: 0.7798
 
 ## Model description
 
@@ -55,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 49   | 1.0447          | 0.9511    | 0.2    | 0.1722 | 0.7557   |
-| No log        | 2.0   | 98   | 0.9864          | 0.9511    | 0.2    | 0.1722 | 0.7557   |
-| No log        | 3.0   | 147  | 0.9540          | 0.9511    | 0.2    | 0.1722 | 0.7557   |
-| No log        | 4.0   | 196  | 0.8967          | 0.9511    | 0.2    | 0.1722 | 0.7557   |
-| No log        | 5.0   | 245  | 0.8671          | 0.9512    | 0.2004 | 0.1730 | 0.7559   |
+| No log        | 1.0   | 49   | 0.7987          | 0.9511    | 0.2    | 0.1722 | 0.7557   |
+| No log        | 2.0   | 98   | 0.7748          | 0.8306    | 0.2107 | 0.1935 | 0.7590   |
+| No log        | 3.0   | 147  | 0.6992          | 0.8346    | 0.2178 | 0.2051 | 0.7617   |
+| No log        | 4.0   | 196  | 0.6507          | 0.6659    | 0.2580 | 0.2513 | 0.7742   |
+| No log        | 5.0   | 245  | 0.6317          | 0.7005    | 0.2671 | 0.2695 | 0.7798   |
 
 
 ### Framework versions

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "camembert-base",
+  "_name_or_path": "camembert/camembert-large",
   "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,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -20,7 +20,7 @@
     "6": "LABEL_6"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -33,8 +33,8 @@
   "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": 1,
   "position_embedding_type": "absolute",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9eea458012bd54cc3896b7f1849ac99c397db7cd917b2305fe15338d5afcbed
-size 440170892
+oid sha256:088bef76544e9affdbf114cb35b5b2b95e0312a9d5b3a4a4f3f2d080f85d9673
+size 1342524276

runs/Jun04_21-58-41_8aee68de80dd/events.out.tfevents.1717538330.8aee68de80dd.2906.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d7d82d1323ad2262487d07d14f718d1d65b4668486d40bc137f6a696fdc3aa
+size 5149

runs/Jun04_21-59-56_8aee68de80dd/events.out.tfevents.1717538404.8aee68de80dd.2906.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fb4d9de76754d6a6a96266c9c815caff0dc9e6417ed9241b2aa42bcedd1964
+size 7845

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea76f9ec60c8bb9e1ed9d3a523d5748d0be8529e18bed07258aa8be3f61e513
+oid sha256:24899b86068cbd3a8de60c82fd114ba4ff49f6365c8aa96729b840ffe2ae6325
 size 5112