Training in progress, epoch 1

config.json

@@ -7,6 +7,7 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 512,
@@ -25,31 +26,30 @@
   "eos_token_id": 0,
   "extra_pos_embeddings": 65001,
   "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "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": 65000,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "transformers_version": "4.56.1",
-  "use_cache": true,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
   "vocab_size": 65001
 }

generation_config.json

@@ -1,17 +1,43 @@
 {
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
   "bad_words_ids": [
     [
       65000
     ]
   ],
+  "bos_token_id": 0,
   "decoder_start_token_id": 65000,
-  "eos_token_id": [
-    0
-  ],
+  "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": 65000,
+  "remove_invalid_values": false,
   "renormalize_logits": true,
-  "transformers_version": "4.56.1"
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "tie_word_embeddings": false,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.0.0",
+  "typical_p": 1.0,
+  "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae2085e0eb5438a171b3e3bc1e96bb3cde89be2b55ad80896722f864fb9dd10
-size 309965092
+oid sha256:7a848c9c397ca71b1357c1c0bb1341e2222286f8b948058b7bbee5858c61c4d1
+size 709331876

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aea7fdfdf359d958cf12f4c136d4ae1ffc394ca1292ba3a139274f3a3b13294
-size 6033
+oid sha256:61ed4a160926c52b0d07a1e575e890e1a1e7c53a940827306bd4082bb24a51ec
+size 5393