Training in progress, step 500

config.json

@@ -8,7 +8,7 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
+  "bos_token_id": null,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 512,
@@ -19,12 +19,12 @@
   "decoder_start_token_id": 59513,
   "decoder_vocab_size": 59514,
   "dropout": 0.1,
+  "dtype": "float32",
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 0,
-  "forced_eos_token_id": 0,
   "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
@@ -32,25 +32,24 @@
     "2": "LABEL_2"
   },
   "init_std": 0.02,
+  "is_decoder": false,
   "is_encoder_decoder": true,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": null,
   "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": null,
   "num_hidden_layers": 6,
   "pad_token_id": 59513,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
-  "use_cache": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
   "vocab_size": 59514
 }

generation_config.json

@@ -0,0 +1,43 @@
+{
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "decoder_start_token_id": 59513,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": [
+    0
+  ],
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_eos_token_id": 0,
+  "length_penalty": 1.0,
+  "max_length": 512,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 4,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 59513,
+  "remove_invalid_values": false,
+  "renormalize_logits": true,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.2.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3b3cf6ed91b0e0eecc40b0cad42cd06552ef43086cc92090f70f9d173fe99c
-size 298705768
+oid sha256:e0265134777bdcecfa031a89d3c89784f92d2669f98cf4eafb44d73f6b50b26a
+size 542475664

tokenizer_config.json

@@ -25,9 +25,9 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "backend": "custom",
   "eos_token": "</s>",
-  "extra_special_tokens": {},
+  "is_local": false,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a21d18ecfedf33e95e840b94fd7c6ae790e1be1d189a747bd49bea59eafa0db
-size 5432
+oid sha256:3a070c3b91298cfcfd5e260b1232d23f02c86834e4db661ffaf1e5d91bd49714
+size 5329