added final checkpoint

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/rgroup/dsig/llm-team/experiments/mlm-fine-tuning/tmp/models/timestamp_20250304_15-54-56/nasa-impact/nasa-smd-ibm-v0.1/checkpoint-41059",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": 1026,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286a86f7f004b067bbc3a927cecc331fd8a3605a0af35ea182a80a8daddad878
+size 500386812

model_architecture.txt

@@ -0,0 +1,44 @@
+RobertaForMaskedLM(
+  (roberta): RobertaModel(
+    (embeddings): RobertaEmbeddings(
+      (word_embeddings): Embedding(50265, 768, padding_idx=1)
+      (position_embeddings): Embedding(1026, 768, padding_idx=1)
+      (token_type_embeddings): Embedding(1, 768)
+      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.1, inplace=False)
+    )
+    (encoder): RobertaEncoder(
+      (layer): ModuleList(
+        (0-11): 12 x RobertaLayer(
+          (attention): RobertaAttention(
+            (self): RobertaSdpaSelfAttention(
+              (query): Linear(in_features=768, out_features=768, bias=True)
+              (key): Linear(in_features=768, out_features=768, bias=True)
+              (value): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+            (output): RobertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (intermediate): RobertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): RobertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            (dropout): Dropout(p=0.1, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (lm_head): RobertaLMHead(
+    (dense): Linear(in_features=768, out_features=768, bias=True)
+    (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+    (decoder): Linear(in_features=768, out_features=50265, bias=True)
+  )
+)

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "nasa_eb_tokenizer",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1e44d2ad0904cb73142d06890d88099e3f9a9859761602d65745016c9e9e2e
+size 5432