Training in progress, step 1000

config.json

@@ -12,12 +12,13 @@
   "initializer_range": 0.041666666666666664,
   "intermediate_size": 1536,
   "is_llama_config": true,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
+  "pad_token_id": 128001,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_interleaved": false,
@@ -25,7 +26,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.52.4",
   "use_cache": true,
   "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2401cd24257d203d8b2dec1890bae07845e5551a744a8f01bdef5ee00b1326bb
+oid sha256:f17d5619a7378f35482ad7d5053f050d5b14eae6f958e2319116bf9ecfc347c9
 size 720346024

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25fb4691a1a754fc20a14c94605e92c90427fa489b3144013ed9532a2d2f0141
-size 5368
+oid sha256:f8877c8f6054fb7e4e14bb35368b7bb0ff88a9ebca9cd9310fb591d80d6a0cd9
+size 5713