Training in progress, epoch 1

config.json

@@ -5,31 +5,33 @@
     "MBartForConditionalGeneration"
   ],
   "attention_dropout": 0.1,
-  "bos_token_id": 64000,
+  "bos_token_id": 2,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
+  "decoder_start_token_id": null,
   "dropout": 0.1,
+  "dtype": "float32",
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
-  "eos_token_id": 64001,
+  "eos_token_id": 3,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "init_std": 0.02,
+  "is_decoder": false,
   "is_encoder_decoder": true,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
-  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "scale_embedding": false,
+  "tie_word_embeddings": true,
   "tokenizer_class": "AlbertTokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.54.1",
-  "use_cache": true,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
   "vocab_size": 64014
 }

generation_config.json

@@ -1,7 +1,38 @@
 {
-  "bos_token_id": 64000,
-  "eos_token_id": 64001,
-  "forced_eos_token_id": 2,
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "bos_token_id": 2,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": [
+    3,
+    64001
+  ],
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
   "pad_token_id": 0,
-  "transformers_version": "4.52.4"
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.13.1",
+  "typical_p": 1.0,
+  "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c639ae8f0c15176fa3171b708339ac61d68acfd5992b32e957d29f73bf602312
+oid sha256:5d6524fab2076643537a00d3bf5c6567e9e56cd4af3aa04e3e3db504d9fa3d8d
 size 976355336

tokenizer_config.json

@@ -1,188 +1,27 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "3": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64000": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64001": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64002": {
-      "content": "<2as>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64003": {
-      "content": "<2bn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64004": {
-      "content": "<2en>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64005": {
-      "content": "<2gu>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64006": {
-      "content": "<2hi>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64007": {
-      "content": "<2kn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64008": {
-      "content": "<2ml>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64009": {
-      "content": "<2mr>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64010": {
-      "content": "<2or>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64011": {
-      "content": "<2pa>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64012": {
-      "content": "<2ta>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64013": {
-      "content": "<2te>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<s>",
-    "</s>",
-    "<2as>",
-    "<2bn>",
-    "<2en>",
-    "<2gu>",
-    "<2hi>",
-    "<2kn>",
-    "<2ml>",
-    "<2mr>",
-    "<2or>",
-    "<2pa>",
-    "<2ta>",
-    "<2te>"
-  ],
+  "add_prefix_space": true,
+  "backend": "tokenizers",
   "bos_token": "[CLS]",
-  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
-  "extra_special_tokens": {},
+  "extra_special_tokens": [
+    "<pad>",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "is_local": false,
   "keep_accents": true,
+  "local_files_only": false,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "remove_space": true,
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
   "tokenizer_class": "AlbertTokenizer",
+  "trim_offsets": true,
+  "unk_id": 1,
   "unk_token": "<unk>",
   "use_fast": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406514327bea94c3c685e0fce08a17eb29f743a36edd427991065d1728554603
-size 5560
+oid sha256:3cb8e5cf40c6c77b282837190a4878d79321bfda9d3063df7f6a230aec12a1f2
+size 5329