Training in progress, step 1000

generation_config.json

@@ -1,9 +1,37 @@
 {
-  "_from_model_config": true,
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
   "decoder_start_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": [
     1
   ],
+  "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": "5.3.0"
+  "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": "5.3.0",
+  "typical_p": 1.0,
+  "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04092b9c0c8751ce7b9998595170714a7dee1a4c00ea0f98dfe72c4204ad789
+oid sha256:5875ca2ec8f51d687cbea7158e2407f0a132d239a9e7262b600ffb18379886e7
 size 307867048