Training in progress, step 500

generation_config.json

@@ -1,37 +1,12 @@
 {
-  "_from_model_config": false,
-  "assistant_confidence_threshold": 0.4,
-  "assistant_lookbehind": 10,
+  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
-  "diversity_penalty": 0.0,
-  "do_sample": false,
   "early_stopping": true,
-  "encoder_no_repeat_ngram_size": 0,
-  "encoder_repetition_penalty": 1.0,
   "eos_token_id": 2,
-  "epsilon_cutoff": 0.0,
-  "eta_cutoff": 0.0,
   "forced_eos_token_id": 2,
-  "length_penalty": 1.0,
   "max_length": 200,
-  "min_length": 0,
-  "no_repeat_ngram_size": 0,
-  "num_assistant_tokens": 20,
-  "num_assistant_tokens_schedule": "constant",
-  "num_beam_groups": 1,
   "num_beams": 5,
-  "num_return_sequences": 1,
-  "output_scores": false,
   "pad_token_id": 1,
-  "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": "5.2.0",
-  "typical_p": 1.0,
-  "use_cache": true
+  "transformers_version": "5.2.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c353e1685c9edba5741deb56bff7b158acb76a46796a3a1a55ea05e89fbd24b1
+oid sha256:318daefbaf640dd201ce1ef35472ca59838801a632fe3f9656f3bab645004285
 size 5517243408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e500ec972b7c8c6da3d16a184d924bb51ae091daa4078ac7b9f19ecef462de50
+oid sha256:a1ce2ea7bb033c74462d9e4dedc75cd0bf3b4e52f5835b1dedf96eb9887b12ee
 size 5329