Training in progress, epoch 1

config.json

@@ -1,36 +1,89 @@
 {
-  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "_name_or_path": "flaubert/flaubert_base_cased",
+  "amp": 1,
   "architectures": [
-    "BertForSequenceClassification"
+    "FlaubertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "asm": false,
+  "attention_dropout": 0.1,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "bptt": 512,
+  "causal": false,
+  "clip_grad_norm": 5,
+  "dropout": 0.1,
+  "emb_dim": 768,
+  "embed_init_std": 0.02209708691207961,
+  "encoder_only": true,
+  "end_n_top": 5,
+  "eos_index": 1,
+  "fp16": true,
+  "gelu_activation": true,
+  "group_by_size": true,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "id2lang": {
+    "0": "fr"
+  },
+  "init_std": 0.02,
+  "is_encoder": true,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
+  "lang2id": {
+    "fr": 0
+  },
+  "lang_id": 0,
+  "langs": [
+    "fr"
+  ],
   "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "lg_sampling_factor": -1,
+  "lgs": "fr",
+  "mask_index": 5,
+  "mask_token_id": 0,
+  "max_batch_size": 0,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "max_vocab": -1,
+  "mlm_steps": [
+    [
+      "fr",
+      null
+    ]
+  ],
+  "model_type": "flaubert",
+  "n_heads": 12,
+  "n_langs": 1,
+  "n_layers": 12,
+  "pad_index": 2,
+  "pad_token_id": 2,
+  "pre_norm": false,
   "problem_type": "single_label_classification",
+  "sample_alpha": 0,
+  "share_inout_emb": true,
+  "sinusoidal_embeddings": false,
+  "start_n_top": 5,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tokens_per_batch": -1,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 31002
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 68729,
+  "word_blank": 0,
+  "word_dropout": 0,
+  "word_keep": 0.1,
+  "word_mask": 0.8,
+  "word_mask_keep_rand": "0.8,0.1,0.1",
+  "word_pred": 0.15,
+  "word_rand": 0.1,
+  "word_shuffle": 0
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c7e06d64fa16ca889125d1b09a887ddb8eb6422bda2e219e202893f8dceded
-size 439433208
+oid sha256:223b5997092b89af197d2bcce7e308bf65e5402208addc74774037291457d4a4
+size 552959120