Training in progress, step 2000

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "docketanalyzer/llama-encoder-1b-base",
+  "architectures": [
+    "LlamaEncoderForMaskedLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "docketanalyzer/llama-encoder-1b-base--configuration_llama.LlamaEncoderConfig",
+    "AutoModel": "docketanalyzer/llama-encoder-1b-base--modeling_llama.LlamaEncoderModel",
+    "AutoModelForMaskedLM": "docketanalyzer/llama-encoder-1b-base--modeling_llama.LlamaEncoderForMaskedLM"
+  },
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama_encoder",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128259
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32685cf19cba7651bb76dc8d1e77d51007bbd799b1576536a400fab13f22c662
+size 2997015224

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788da3930b11a77a6ce8658dea0422068339964a534ac71946d85d120448e212
+size 5240