Training in progress, epoch 1

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "0_not_relevant",
     "1": "1_not_happening",
@@ -20,7 +19,6 @@
     "7": "7_fossil_fuels_needed"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
   "label2id": {
     "0_not_relevant": 0,
     "1_not_happening": 1,
@@ -31,17 +29,17 @@
     "6_proponents_biased": 6,
     "7_fossil_fuels_needed": 7
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5b2f97dfce3cd869b7b8a4270d829c15f793872d0369e42c61a10b4f9dfe000
-size 90877192
+oid sha256:3e5c90d0d1b4bd9827645cf2c4444e8c26772f88aba7b1144a5ead7008b8e38f
+size 267851024

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -2,20 +2,11 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -43,23 +43,14 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_length": 128,
   "model_max_length": 512,
-  "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa5435a043f29b39276a10041cc8a2cbe0420f8cd406bd76406ab90adf82563
+oid sha256:8e86370459d3d79a889ef96465ca2a67d6a8a2d5810cc7180dcec78c89f4208e
 size 5304