Training in progress, epoch 1

config.json

@@ -1,31 +1,34 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "camembert-base",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "CamembertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "problem_type": "regression",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8b524806969cf05dde71b6d0db01a2ab84dd1be332eee9e4d3624508b22319
-size 267829484
+oid sha256:7eaf4cd5f23cc03d470a1152dbce9553067cf615b4bebcc446bb821541a0c89c
+size 442515028

runs/May06_20-38-17_2962dfe42553/events.out.tfevents.1715027898.2962dfe42553.242.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8196d1b82e2f7a2a067f295548d684efe09dac39026b0bd92f030959754b769
+size 4184

runs/May06_20-40-48_2962dfe42553/events.out.tfevents.1715028049.2962dfe42553.1784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac228cdcf05ac6cb75fa49ab2560025dbbe86bbb5d89f751cf55e63220bae1a
+size 4799

runs/May06_20-40-48_2962dfe42553/events.out.tfevents.1715028088.2962dfe42553.1784.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceea351049620e6aa6fc9a368d534399bcfdbbb989fcb5e3c11df7210a68ea90
+size 4799

runs/May06_20-45-27_2962dfe42553/events.out.tfevents.1715028334.2962dfe42553.1784.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2717b3128a6e67d932162887f259bfe5513d90f1f3ee4e4928aa78c247ed1dc
+size 11581

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0694ddc68a68a07096e31ba9bb5c4471fc58739bcfe27fc18855f06f761b6cc
+oid sha256:b01f74db84eb9c0d8d76d115e677672c4eddc1ee85f74ce504d1306d4ff6930f
 size 4984