Training in progress, step 30000

config.json

@@ -1,54 +1,27 @@
 {
   "_name_or_path": "nsi319/legal-led-base-16384",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
   "architectures": [
-    "LEDForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "attention_window": [
-    1024,
-    1024,
-    1024,
-    1024,
-    1024,
-    1024
+    "RobertaForMaskedLM"
   ],
+  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_decoder_position_embeddings": 1024,
-  "max_encoder_position_embeddings": 16384,
-  "model_type": "led",
-  "num_hidden_layers": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c009195220d834ce2b852160b340d9a7ad5dcd67d5b9df5ebd2e49613b6d4850
-size 647614116
+oid sha256:a29a2cb4d2465ba8be47488a6e9718c95cf388fc15bcdd68bda793e56cd484e8
+size 498813948

runs/Feb23_17-02-08_gitspot/events.out.tfevents.1740310344.gitspot.2125547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8298f5837c6fc1ea9dc180847efdfd7c90318be05656a54be3c61ebddb8952d
+size 4136

runs/Feb23_17-04-22_gitspot/events.out.tfevents.1740310476.gitspot.2126098.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6836fd5f31149586b880afd14eae4d873cadb30f7ead72960e715dcf535ef6
+size 17757

special_tokens_map.json

@@ -1,51 +1,15 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -4,7 +4,7 @@
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,15 +28,15 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "4": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -49,10 +49,10 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 16384,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "LEDTokenizer",
+  "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a535f375d4fe718d49ea5a49d9afaa22bc4fb7983eeb4d415cbc783e2eb758
-size 4987
+oid sha256:e5c748b6e59a2d002b1762397a2882a55d9f39dca98acc840e4f873c35795645
+size 4859