Upload folder using huggingface_hub

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForEncoderDecoder2"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128257
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31da1f3f431d6166f74014ad3b49179e07a0c6a82d07cf26fca00c7afe96ee2
+size 4976707520

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ca2c523e6061e2df25b30aa7135256f632f216f71430172690f757513a7bbd
+size 4999803552

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcf774a75f3296b74f9bc535baf303394f20b6f1e013e7f5cad25c29ef342de
+size 4915916976

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d0ff3a34c721aa39cdf877c71dd5300c3d55a877237eb86912f0ad5bcf16e2
+size 4920065288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77463bbfcae539a0c49993ab5893d9f2723dde7b0148c5c1fe26099e14fff55f
+size 4915916144

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5a0a593ed0a4ed919250ec766655b03172cdcebb8cac75ef1dab701123c08f
+size 4915916176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81481a2430eae6bbb766365898804f989b1e6045f2ade758773c1de0f24f1731
+size 2476822152

model.safetensors.index.json

@@ -0,0 +1,589 @@
+{
+  "metadata": {
+    "total_size": 32121077760
+  },
+  "weight_map": {
+    "encoder.lm_head.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.30.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "encoder.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "encoder.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "encoder.model.norm.weight": "model-00004-of-00007.safetensors",
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1aa1a25170b9a88c638fc6cf25dc66dd66b659d5b6332637be925c355af1402
+size 1064

trainer_state.json

@@ -0,0 +1,1923 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9986146386515817,
+  "eval_steps": 500,
+  "global_step": 1082,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0073885938582313555,
+      "grad_norm": 30.625,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.171,
+      "step": 4
+    },
+    {
+      "epoch": 0.014777187716462711,
+      "grad_norm": 30.625,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 3.1417,
+      "step": 8
+    },
+    {
+      "epoch": 0.022165781574694066,
+      "grad_norm": 26.375,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.9572,
+      "step": 12
+    },
+    {
+      "epoch": 0.029554375432925422,
+      "grad_norm": 19.75,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.4271,
+      "step": 16
+    },
+    {
+      "epoch": 0.03694296929115678,
+      "grad_norm": 16.25,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.9425,
+      "step": 20
+    },
+    {
+      "epoch": 0.04433156314938813,
+      "grad_norm": 10.8125,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.2272,
+      "step": 24
+    },
+    {
+      "epoch": 0.051720157007619484,
+      "grad_norm": 6.21875,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.7596,
+      "step": 28
+    },
+    {
+      "epoch": 0.059108750865850844,
+      "grad_norm": 4.6875,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5928,
+      "step": 32
+    },
+    {
+      "epoch": 0.0664973447240822,
+      "grad_norm": 3.234375,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.5097,
+      "step": 36
+    },
+    {
+      "epoch": 0.07388593858231356,
+      "grad_norm": 2.765625,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4897,
+      "step": 40
+    },
+    {
+      "epoch": 0.0812745324405449,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.8e-06,
+      "loss": 0.4433,
+      "step": 44
+    },
+    {
+      "epoch": 0.08866312629877626,
+      "grad_norm": 2.515625,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.4597,
+      "step": 48
+    },
+    {
+      "epoch": 0.09605172015700762,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.04e-05,
+      "loss": 0.4418,
+      "step": 52
+    },
+    {
+      "epoch": 0.10344031401523897,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.416,
+      "step": 56
+    },
+    {
+      "epoch": 0.11082890787347033,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4305,
+      "step": 60
+    },
+    {
+      "epoch": 0.11821750173170169,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.3997,
+      "step": 64
+    },
+    {
+      "epoch": 0.12560609558993305,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.3958,
+      "step": 68
+    },
+    {
+      "epoch": 0.1329946894481644,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.4051,
+      "step": 72
+    },
+    {
+      "epoch": 0.14038328330639574,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.4058,
+      "step": 76
+    },
+    {
+      "epoch": 0.1477718771646271,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4084,
+      "step": 80
+    },
+    {
+      "epoch": 0.15516047102285846,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.402,
+      "step": 84
+    },
+    {
+      "epoch": 0.1625490648810898,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.76e-05,
+      "loss": 0.3955,
+      "step": 88
+    },
+    {
+      "epoch": 0.16993765873932118,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.395,
+      "step": 92
+    },
+    {
+      "epoch": 0.17732625259755253,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4021,
+      "step": 96
+    },
+    {
+      "epoch": 0.18471484645578387,
+      "grad_norm": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3918,
+      "step": 100
+    },
+    {
+      "epoch": 0.19210344031401524,
+      "grad_norm": 1.75,
+      "learning_rate": 1.9999659601637828e-05,
+      "loss": 0.3943,
+      "step": 104
+    },
+    {
+      "epoch": 0.1994920341722466,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.9998638429725526e-05,
+      "loss": 0.3955,
+      "step": 108
+    },
+    {
+      "epoch": 0.20688062803047794,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.9996936553784137e-05,
+      "loss": 0.4017,
+      "step": 112
+    },
+    {
+      "epoch": 0.2142692218887093,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.999455408967682e-05,
+      "loss": 0.4023,
+      "step": 116
+    },
+    {
+      "epoch": 0.22165781574694066,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.999149119960095e-05,
+      "loss": 0.4046,
+      "step": 120
+    },
+    {
+      "epoch": 0.229046409605172,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.9987748092077082e-05,
+      "loss": 0.3783,
+      "step": 124
+    },
+    {
+      "epoch": 0.23643500346340338,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.998332502193475e-05,
+      "loss": 0.3965,
+      "step": 128
+    },
+    {
+      "epoch": 0.24382359732163472,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9978222290295116e-05,
+      "loss": 0.4031,
+      "step": 132
+    },
+    {
+      "epoch": 0.2512121911798661,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.9972440244550485e-05,
+      "loss": 0.3685,
+      "step": 136
+    },
+    {
+      "epoch": 0.2586007850380974,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.9965979278340638e-05,
+      "loss": 0.4004,
+      "step": 140
+    },
+    {
+      "epoch": 0.2659893788963288,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.995883983152603e-05,
+      "loss": 0.3881,
+      "step": 144
+    },
+    {
+      "epoch": 0.27337797275456016,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.995102239015787e-05,
+      "loss": 0.4091,
+      "step": 148
+    },
+    {
+      "epoch": 0.2807665666127915,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9942527486445e-05,
+      "loss": 0.3785,
+      "step": 152
+    },
+    {
+      "epoch": 0.28815516047102285,
+      "grad_norm": 1.875,
+      "learning_rate": 1.9933355698717683e-05,
+      "loss": 0.3999,
+      "step": 156
+    },
+    {
+      "epoch": 0.2955437543292542,
+      "grad_norm": 1.75,
+      "learning_rate": 1.9923507651388224e-05,
+      "loss": 0.3682,
+      "step": 160
+    },
+    {
+      "epoch": 0.30293234818748555,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.991298401490846e-05,
+      "loss": 0.3975,
+      "step": 164
+    },
+    {
+      "epoch": 0.3103209420457169,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.9901785505724117e-05,
+      "loss": 0.382,
+      "step": 168
+    },
+    {
+      "epoch": 0.3177095359039483,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.988991288622603e-05,
+      "loss": 0.364,
+      "step": 172
+    },
+    {
+      "epoch": 0.3250981297621796,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.9877366964698242e-05,
+      "loss": 0.375,
+      "step": 176
+    },
+    {
+      "epoch": 0.332486723620411,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.9864148595262988e-05,
+      "loss": 0.3637,
+      "step": 180
+    },
+    {
+      "epoch": 0.33987531747864236,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.985025867782252e-05,
+      "loss": 0.3655,
+      "step": 184
+    },
+    {
+      "epoch": 0.3472639113368737,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.9835698157997877e-05,
+      "loss": 0.3498,
+      "step": 188
+    },
+    {
+      "epoch": 0.35465250519510505,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.9820468027064478e-05,
+      "loss": 0.3802,
+      "step": 192
+    },
+    {
+      "epoch": 0.3620410990533364,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.9804569321884638e-05,
+      "loss": 0.3692,
+      "step": 196
+    },
+    {
+      "epoch": 0.36942969291156774,
+      "grad_norm": 1.625,
+      "learning_rate": 1.978800312483701e-05,
+      "loss": 0.3667,
+      "step": 200
+    },
+    {
+      "epoch": 0.3768182867697991,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.9770770563742854e-05,
+      "loss": 0.3677,
+      "step": 204
+    },
+    {
+      "epoch": 0.3842068806280305,
+      "grad_norm": 2.0,
+      "learning_rate": 1.975287281178929e-05,
+      "loss": 0.3802,
+      "step": 208
+    },
+    {
+      "epoch": 0.3915954744862618,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.9734311087449408e-05,
+      "loss": 0.3543,
+      "step": 212
+    },
+    {
+      "epoch": 0.3989840683444932,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.9715086654399317e-05,
+      "loss": 0.3738,
+      "step": 216
+    },
+    {
+      "epoch": 0.40637266220272455,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.9695200821432126e-05,
+      "loss": 0.3568,
+      "step": 220
+    },
+    {
+      "epoch": 0.4137612560609559,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.9674654942368824e-05,
+      "loss": 0.3534,
+      "step": 224
+    },
+    {
+      "epoch": 0.42114984991918725,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.965345041596613e-05,
+      "loss": 0.3793,
+      "step": 228
+    },
+    {
+      "epoch": 0.4285384437774186,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.963158868582126e-05,
+      "loss": 0.3739,
+      "step": 232
+    },
+    {
+      "epoch": 0.43592703763564994,
+      "grad_norm": 1.625,
+      "learning_rate": 1.9609071240273637e-05,
+      "loss": 0.3701,
+      "step": 236
+    },
+    {
+      "epoch": 0.4433156314938813,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.958589961230358e-05,
+      "loss": 0.3648,
+      "step": 240
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.9562075379427926e-05,
+      "loss": 0.3775,
+      "step": 244
+    },
+    {
+      "epoch": 0.458092819210344,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.953760016359265e-05,
+      "loss": 0.3806,
+      "step": 248
+    },
+    {
+      "epoch": 0.4654814130685754,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.951247563106243e-05,
+      "loss": 0.366,
+      "step": 252
+    },
+    {
+      "epoch": 0.47287000692680675,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.9486703492307207e-05,
+      "loss": 0.3682,
+      "step": 256
+    },
+    {
+      "epoch": 0.48025860078503807,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.9460285501885744e-05,
+      "loss": 0.3661,
+      "step": 260
+    },
+    {
+      "epoch": 0.48764719464326944,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.943322345832618e-05,
+      "loss": 0.3713,
+      "step": 264
+    },
+    {
+      "epoch": 0.4950357885015008,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.9405519204003577e-05,
+      "loss": 0.3459,
+      "step": 268
+    },
+    {
+      "epoch": 0.5024243823597322,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.9377174625014485e-05,
+      "loss": 0.3871,
+      "step": 272
+    },
+    {
+      "epoch": 0.5098129762179635,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.9348191651048565e-05,
+      "loss": 0.3369,
+      "step": 276
+    },
+    {
+      "epoch": 0.5172015700761948,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.9318572255257192e-05,
+      "loss": 0.3698,
+      "step": 280
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.9288318454119122e-05,
+      "loss": 0.3649,
+      "step": 284
+    },
+    {
+      "epoch": 0.5319787577926576,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.9257432307303232e-05,
+      "loss": 0.3692,
+      "step": 288
+    },
+    {
+      "epoch": 0.5393673516508889,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.9225915917528277e-05,
+      "loss": 0.3789,
+      "step": 292
+    },
+    {
+      "epoch": 0.5467559455091203,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.919377143041975e-05,
+      "loss": 0.3755,
+      "step": 296
+    },
+    {
+      "epoch": 0.5541445393673516,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.916100103436381e-05,
+      "loss": 0.3482,
+      "step": 300
+    },
+    {
+      "epoch": 0.561533133225583,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9127606960358274e-05,
+      "loss": 0.3644,
+      "step": 304
+    },
+    {
+      "epoch": 0.5689217270838144,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.9093591481860772e-05,
+      "loss": 0.3708,
+      "step": 308
+    },
+    {
+      "epoch": 0.5763103209420457,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.9058956914633933e-05,
+      "loss": 0.3814,
+      "step": 312
+    },
+    {
+      "epoch": 0.583698914800277,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.9023705616587747e-05,
+      "loss": 0.343,
+      "step": 316
+    },
+    {
+      "epoch": 0.5910875086585085,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.8987839987619042e-05,
+      "loss": 0.3793,
+      "step": 320
+    },
+    {
+      "epoch": 0.5984761025167398,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.895136246944809e-05,
+      "loss": 0.3553,
+      "step": 324
+    },
+    {
+      "epoch": 0.6058646963749711,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.8914275545452377e-05,
+      "loss": 0.3714,
+      "step": 328
+    },
+    {
+      "epoch": 0.6132532902332025,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.887658174049754e-05,
+      "loss": 0.3691,
+      "step": 332
+    },
+    {
+      "epoch": 0.6206418840914338,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.8838283620765476e-05,
+      "loss": 0.341,
+      "step": 336
+    },
+    {
+      "epoch": 0.6280304779496652,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.879938379357962e-05,
+      "loss": 0.3559,
+      "step": 340
+    },
+    {
+      "epoch": 0.6354190718078966,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.8759884907227485e-05,
+      "loss": 0.344,
+      "step": 344
+    },
+    {
+      "epoch": 0.6428076656661279,
+      "grad_norm": 1.5,
+      "learning_rate": 1.87197896507803e-05,
+      "loss": 0.3518,
+      "step": 348
+    },
+    {
+      "epoch": 0.6501962595243592,
+      "grad_norm": 1.5,
+      "learning_rate": 1.867910075390999e-05,
+      "loss": 0.3399,
+      "step": 352
+    },
+    {
+      "epoch": 0.6575848533825907,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.8637820986703335e-05,
+      "loss": 0.3468,
+      "step": 356
+    },
+    {
+      "epoch": 0.664973447240822,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.8595953159473357e-05,
+      "loss": 0.3479,
+      "step": 360
+    },
+    {
+      "epoch": 0.6723620410990533,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.8553500122568023e-05,
+      "loss": 0.3497,
+      "step": 364
+    },
+    {
+      "epoch": 0.6797506349572847,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.8510464766176178e-05,
+      "loss": 0.3544,
+      "step": 368
+    },
+    {
+      "epoch": 0.687139228815516,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.8466850020130786e-05,
+      "loss": 0.344,
+      "step": 372
+    },
+    {
+      "epoch": 0.6945278226737474,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.8422658853709475e-05,
+      "loss": 0.3508,
+      "step": 376
+    },
+    {
+      "epoch": 0.7019164165319788,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.8377894275432376e-05,
+      "loss": 0.3452,
+      "step": 380
+    },
+    {
+      "epoch": 0.7093050103902101,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.833255933285732e-05,
+      "loss": 0.3604,
+      "step": 384
+    },
+    {
+      "epoch": 0.7166936042484414,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.8286657112372342e-05,
+      "loss": 0.3719,
+      "step": 388
+    },
+    {
+      "epoch": 0.7240821981066728,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.8240190738985578e-05,
+      "loss": 0.356,
+      "step": 392
+    },
+    {
+      "epoch": 0.7314707919649042,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.819316337611251e-05,
+      "loss": 0.3592,
+      "step": 396
+    },
+    {
+      "epoch": 0.7388593858231355,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.8145578225360594e-05,
+      "loss": 0.3557,
+      "step": 400
+    },
+    {
+      "epoch": 0.7462479796813669,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.809743852631131e-05,
+      "loss": 0.3532,
+      "step": 404
+    },
+    {
+      "epoch": 0.7536365735395982,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.8048747556299595e-05,
+      "loss": 0.3723,
+      "step": 408
+    },
+    {
+      "epoch": 0.7610251673978295,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7999508630190742e-05,
+      "loss": 0.3604,
+      "step": 412
+    },
+    {
+      "epoch": 0.768413761256061,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.7949725100154707e-05,
+      "loss": 0.36,
+      "step": 416
+    },
+    {
+      "epoch": 0.7758023551142923,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.789940035543792e-05,
+      "loss": 0.3497,
+      "step": 420
+    },
+    {
+      "epoch": 0.7831909489725236,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7848537822132498e-05,
+      "loss": 0.3487,
+      "step": 424
+    },
+    {
+      "epoch": 0.790579542830755,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.7797140962943062e-05,
+      "loss": 0.3491,
+      "step": 428
+    },
+    {
+      "epoch": 0.7979681366889864,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.7745213276950947e-05,
+      "loss": 0.3627,
+      "step": 432
+    },
+    {
+      "epoch": 0.8053567305472177,
+      "grad_norm": 1.75,
+      "learning_rate": 1.7692758299376002e-05,
+      "loss": 0.3534,
+      "step": 436
+    },
+    {
+      "epoch": 0.8127453244054491,
+      "grad_norm": 1.4140625,
+      "learning_rate": 1.7639779601335916e-05,
+      "loss": 0.3565,
+      "step": 440
+    },
+    {
+      "epoch": 0.8201339182636804,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.7586280789603104e-05,
+      "loss": 0.3627,
+      "step": 444
+    },
+    {
+      "epoch": 0.8275225121219117,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.753226550635914e-05,
+      "loss": 0.3352,
+      "step": 448
+    },
+    {
+      "epoch": 0.8349111059801432,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.7477737428946814e-05,
+      "loss": 0.3499,
+      "step": 452
+    },
+    {
+      "epoch": 0.8422996998383745,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.742270026961978e-05,
+      "loss": 0.343,
+      "step": 456
+    },
+    {
+      "epoch": 0.8496882936966058,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.736715777528981e-05,
+      "loss": 0.345,
+      "step": 460
+    },
+    {
+      "epoch": 0.8570768875548372,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.7311113727271728e-05,
+      "loss": 0.3329,
+      "step": 464
+    },
+    {
+      "epoch": 0.8644654814130686,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.725457194102596e-05,
+      "loss": 0.3299,
+      "step": 468
+    },
+    {
+      "epoch": 0.8718540752712999,
+      "grad_norm": 1.375,
+      "learning_rate": 1.71975362658988e-05,
+      "loss": 0.3381,
+      "step": 472
+    },
+    {
+      "epoch": 0.8792426691295313,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.7140010584860322e-05,
+      "loss": 0.3554,
+      "step": 476
+    },
+    {
+      "epoch": 0.8866312629877626,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.708199881424005e-05,
+      "loss": 0.3442,
+      "step": 480
+    },
+    {
+      "epoch": 0.8940198568459939,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.7023504903460325e-05,
+      "loss": 0.3501,
+      "step": 484
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 1.5,
+      "learning_rate": 1.696453283476743e-05,
+      "loss": 0.3751,
+      "step": 488
+    },
+    {
+      "epoch": 0.9087970445624567,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.6905086622960488e-05,
+      "loss": 0.3613,
+      "step": 492
+    },
+    {
+      "epoch": 0.916185638420688,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.6845170315118124e-05,
+      "loss": 0.3655,
+      "step": 496
+    },
+    {
+      "epoch": 0.9235742322789194,
+      "grad_norm": 1.375,
+      "learning_rate": 1.678478799032295e-05,
+      "loss": 0.338,
+      "step": 500
+    },
+    {
+      "epoch": 0.9309628261371508,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.6723943759383857e-05,
+      "loss": 0.3414,
+      "step": 504
+    },
+    {
+      "epoch": 0.9383514199953821,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.666264176455616e-05,
+      "loss": 0.3453,
+      "step": 508
+    },
+    {
+      "epoch": 0.9457400138536135,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.660088617925959e-05,
+      "loss": 0.3275,
+      "step": 512
+    },
+    {
+      "epoch": 0.9531286077118448,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.6538681207794153e-05,
+      "loss": 0.3584,
+      "step": 516
+    },
+    {
+      "epoch": 0.9605172015700761,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.6476031085053937e-05,
+      "loss": 0.3594,
+      "step": 520
+    },
+    {
+      "epoch": 0.9679057954283076,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6412940076238782e-05,
+      "loss": 0.3527,
+      "step": 524
+    },
+    {
+      "epoch": 0.9752943892865389,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.6349412476563893e-05,
+      "loss": 0.3654,
+      "step": 528
+    },
+    {
+      "epoch": 0.9826829831447702,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.628545261096745e-05,
+      "loss": 0.3611,
+      "step": 532
+    },
+    {
+      "epoch": 0.9900715770030016,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.622106483381615e-05,
+      "loss": 0.332,
+      "step": 536
+    },
+    {
+      "epoch": 0.997460170861233,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.615625352860877e-05,
+      "loss": 0.329,
+      "step": 540
+    },
+    {
+      "epoch": 1.0048487647194644,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.6091023107677747e-05,
+      "loss": 0.2864,
+      "step": 544
+    },
+    {
+      "epoch": 1.0122373585776956,
+      "grad_norm": 1.3828125,
+      "learning_rate": 1.602537801188876e-05,
+      "loss": 0.2337,
+      "step": 548
+    },
+    {
+      "epoch": 1.019625952435927,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.5959322710338426e-05,
+      "loss": 0.2459,
+      "step": 552
+    },
+    {
+      "epoch": 1.0270145462941584,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.589286170005005e-05,
+      "loss": 0.2397,
+      "step": 556
+    },
+    {
+      "epoch": 1.0344031401523897,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.5825999505667426e-05,
+      "loss": 0.255,
+      "step": 560
+    },
+    {
+      "epoch": 1.041791734010621,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.5758740679146858e-05,
+      "loss": 0.2221,
+      "step": 564
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.569108979944722e-05,
+      "loss": 0.218,
+      "step": 568
+    },
+    {
+      "epoch": 1.0565689217270837,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.562305147221824e-05,
+      "loss": 0.2313,
+      "step": 572
+    },
+    {
+      "epoch": 1.0639575155853152,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.5554630329486954e-05,
+      "loss": 0.2245,
+      "step": 576
+    },
+    {
+      "epoch": 1.0713461094435466,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.548583102934234e-05,
+      "loss": 0.2396,
+      "step": 580
+    },
+    {
+      "epoch": 1.0787347033017778,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.541665825561822e-05,
+      "loss": 0.2248,
+      "step": 584
+    },
+    {
+      "epoch": 1.0861232971600092,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.5347116717574367e-05,
+      "loss": 0.2263,
+      "step": 588
+    },
+    {
+      "epoch": 1.0935118910182406,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.5277211149575915e-05,
+      "loss": 0.2355,
+      "step": 592
+    },
+    {
+      "epoch": 1.1009004848764719,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.5206946310771034e-05,
+      "loss": 0.2197,
+      "step": 596
+    },
+    {
+      "epoch": 1.1082890787347033,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.5136326984766934e-05,
+      "loss": 0.2385,
+      "step": 600
+    },
+    {
+      "epoch": 1.1156776725929347,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.5065357979304191e-05,
+      "loss": 0.2325,
+      "step": 604
+    },
+    {
+      "epoch": 1.123066266451166,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.4994044125929458e-05,
+      "loss": 0.233,
+      "step": 608
+    },
+    {
+      "epoch": 1.1304548603093973,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.492239027966651e-05,
+      "loss": 0.2392,
+      "step": 612
+    },
+    {
+      "epoch": 1.1378434541676288,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.4850401318685728e-05,
+      "loss": 0.2245,
+      "step": 616
+    },
+    {
+      "epoch": 1.14523204802586,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.4778082143971992e-05,
+      "loss": 0.2314,
+      "step": 620
+    },
+    {
+      "epoch": 1.1526206418840914,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.4705437678991034e-05,
+      "loss": 0.2159,
+      "step": 624
+    },
+    {
+      "epoch": 1.1600092357423228,
+      "grad_norm": 1.3828125,
+      "learning_rate": 1.463247286935423e-05,
+      "loss": 0.2289,
+      "step": 628
+    },
+    {
+      "epoch": 1.167397829600554,
+      "grad_norm": 1.3828125,
+      "learning_rate": 1.455919268248192e-05,
+      "loss": 0.2445,
+      "step": 632
+    },
+    {
+      "epoch": 1.1747864234587855,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.4485602107265221e-05,
+      "loss": 0.2343,
+      "step": 636
+    },
+    {
+      "epoch": 1.182175017317017,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.4411706153726391e-05,
+      "loss": 0.2249,
+      "step": 640
+    },
+    {
+      "epoch": 1.1895636111752481,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.4337509852677735e-05,
+      "loss": 0.2241,
+      "step": 644
+    },
+    {
+      "epoch": 1.1969522050334795,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.4263018255379132e-05,
+      "loss": 0.2236,
+      "step": 648
+    },
+    {
+      "epoch": 1.204340798891711,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.4188236433194117e-05,
+      "loss": 0.2215,
+      "step": 652
+    },
+    {
+      "epoch": 1.2117293927499422,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.4113169477244659e-05,
+      "loss": 0.2194,
+      "step": 656
+    },
+    {
+      "epoch": 1.2191179866081736,
+      "grad_norm": 1.5546875,
+      "learning_rate": 1.4037822498064517e-05,
+      "loss": 0.2309,
+      "step": 660
+    },
+    {
+      "epoch": 1.226506580466405,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.3962200625251363e-05,
+      "loss": 0.2195,
+      "step": 664
+    },
+    {
+      "epoch": 1.2338951743246362,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.3886309007117522e-05,
+      "loss": 0.2402,
+      "step": 668
+    },
+    {
+      "epoch": 1.2412837681828677,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.3810152810339496e-05,
+      "loss": 0.2419,
+      "step": 672
+    },
+    {
+      "epoch": 1.248672362041099,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.3733737219606222e-05,
+      "loss": 0.2321,
+      "step": 676
+    },
+    {
+      "epoch": 1.2560609558993305,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.3657067437266078e-05,
+      "loss": 0.2086,
+      "step": 680
+    },
+    {
+      "epoch": 1.2634495497575617,
+      "grad_norm": 1.5,
+      "learning_rate": 1.3580148682972739e-05,
+      "loss": 0.2302,
+      "step": 684
+    },
+    {
+      "epoch": 1.2708381436157932,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.3502986193329793e-05,
+      "loss": 0.2251,
+      "step": 688
+    },
+    {
+      "epoch": 1.2782267374740246,
+      "grad_norm": 1.3515625,
+      "learning_rate": 1.3425585221534266e-05,
+      "loss": 0.2315,
+      "step": 692
+    },
+    {
+      "epoch": 1.2856153313322558,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.3347951037018961e-05,
+      "loss": 0.2234,
+      "step": 696
+    },
+    {
+      "epoch": 1.2930039251904872,
+      "grad_norm": 1.4140625,
+      "learning_rate": 1.3270088925093726e-05,
+      "loss": 0.2236,
+      "step": 700
+    },
+    {
+      "epoch": 1.3003925190487187,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.3192004186585643e-05,
+      "loss": 0.2263,
+      "step": 704
+    },
+    {
+      "epoch": 1.3077811129069499,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.311370213747813e-05,
+      "loss": 0.2368,
+      "step": 708
+    },
+    {
+      "epoch": 1.3151697067651813,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.3035188108549035e-05,
+      "loss": 0.2393,
+      "step": 712
+    },
+    {
+      "epoch": 1.3225583006234127,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.2956467445007736e-05,
+      "loss": 0.2355,
+      "step": 716
+    },
+    {
+      "epoch": 1.329946894481644,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.2877545506131219e-05,
+      "loss": 0.2286,
+      "step": 720
+    },
+    {
+      "epoch": 1.3373354883398754,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.2798427664899232e-05,
+      "loss": 0.2264,
+      "step": 724
+    },
+    {
+      "epoch": 1.3447240821981068,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.271911930762848e-05,
+      "loss": 0.2223,
+      "step": 728
+    },
+    {
+      "epoch": 1.352112676056338,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.2639625833605959e-05,
+      "loss": 0.2247,
+      "step": 732
+    },
+    {
+      "epoch": 1.3595012699145694,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.255995265472134e-05,
+      "loss": 0.2314,
+      "step": 736
+    },
+    {
+      "epoch": 1.3668898637728009,
+      "grad_norm": 1.5546875,
+      "learning_rate": 1.2480105195098537e-05,
+      "loss": 0.2381,
+      "step": 740
+    },
+    {
+      "epoch": 1.374278457631032,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.2400088890726451e-05,
+      "loss": 0.2292,
+      "step": 744
+    },
+    {
+      "epoch": 1.3816670514892635,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.231990918908887e-05,
+      "loss": 0.2222,
+      "step": 748
+    },
+    {
+      "epoch": 1.389055645347495,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.2239571548793618e-05,
+      "loss": 0.2149,
+      "step": 752
+    },
+    {
+      "epoch": 1.3964442392057261,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.2159081439200933e-05,
+      "loss": 0.2465,
+      "step": 756
+    },
+    {
+      "epoch": 1.4038328330639576,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.2078444340051107e-05,
+      "loss": 0.2329,
+      "step": 760
+    },
+    {
+      "epoch": 1.411221426922189,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.199766574109144e-05,
+      "loss": 0.2284,
+      "step": 764
+    },
+    {
+      "epoch": 1.4186100207804202,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.1916751141702485e-05,
+      "loss": 0.2453,
+      "step": 768
+    },
+    {
+      "epoch": 1.4259986146386516,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.1835706050523663e-05,
+      "loss": 0.2267,
+      "step": 772
+    },
+    {
+      "epoch": 1.433387208496883,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.1754535985078236e-05,
+      "loss": 0.2178,
+      "step": 776
+    },
+    {
+      "epoch": 1.4407758023551143,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.1673246471397672e-05,
+      "loss": 0.2171,
+      "step": 780
+    },
+    {
+      "epoch": 1.4481643962133457,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.1591843043645432e-05,
+      "loss": 0.2279,
+      "step": 784
+    },
+    {
+      "epoch": 1.4555529900715771,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.1510331243740214e-05,
+      "loss": 0.2298,
+      "step": 788
+    },
+    {
+      "epoch": 1.4629415839298083,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.1428716620978654e-05,
+      "loss": 0.2319,
+      "step": 792
+    },
+    {
+      "epoch": 1.4703301777880398,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.134700473165754e-05,
+      "loss": 0.2392,
+      "step": 796
+    },
+    {
+      "epoch": 1.4777187716462712,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.1265201138695526e-05,
+      "loss": 0.2313,
+      "step": 800
+    },
+    {
+      "epoch": 1.4851073655045024,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.1183311411254425e-05,
+      "loss": 0.2021,
+      "step": 804
+    },
+    {
+      "epoch": 1.4924959593627338,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.1101341124360056e-05,
+      "loss": 0.2178,
+      "step": 808
+    },
+    {
+      "epoch": 1.4998845532209653,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.1019295858522708e-05,
+      "loss": 0.2268,
+      "step": 812
+    },
+    {
+      "epoch": 1.5072731470791965,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.0937181199357192e-05,
+      "loss": 0.2244,
+      "step": 816
+    },
+    {
+      "epoch": 1.514661740937428,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.0855002737202617e-05,
+      "loss": 0.2311,
+      "step": 820
+    },
+    {
+      "epoch": 1.5220503347956593,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.0772766066741763e-05,
+      "loss": 0.2314,
+      "step": 824
+    },
+    {
+      "epoch": 1.5294389286538905,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.0690476786620214e-05,
+      "loss": 0.2357,
+      "step": 828
+    },
+    {
+      "epoch": 1.536827522512122,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.060814049906521e-05,
+      "loss": 0.2126,
+      "step": 832
+    },
+    {
+      "epoch": 1.5442161163703534,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.0525762809504234e-05,
+      "loss": 0.235,
+      "step": 836
+    },
+    {
+      "epoch": 1.5516047102285846,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.0443349326183409e-05,
+      "loss": 0.2274,
+      "step": 840
+    },
+    {
+      "epoch": 1.558993304086816,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.0360905659785682e-05,
+      "loss": 0.2404,
+      "step": 844
+    },
+    {
+      "epoch": 1.5663818979450475,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.0278437423048862e-05,
+      "loss": 0.2124,
+      "step": 848
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.0195950230383482e-05,
+      "loss": 0.2218,
+      "step": 852
+    },
+    {
+      "epoch": 1.58115908566151,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.011344969749061e-05,
+      "loss": 0.2298,
+      "step": 856
+    },
+    {
+      "epoch": 1.5885476795197415,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.0030941440979489e-05,
+      "loss": 0.2238,
+      "step": 860
+    },
+    {
+      "epoch": 1.5959362733779727,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.948431077985203e-06,
+      "loss": 0.2225,
+      "step": 864
+    },
+    {
+      "epoch": 1.6033248672362042,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.865924225786241e-06,
+      "loss": 0.227,
+      "step": 868
+    },
+    {
+      "epoch": 1.6107134610944356,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.783426501422063e-06,
+      "loss": 0.2291,
+      "step": 872
+    },
+    {
+      "epoch": 1.6181020549526668,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.700943521310727e-06,
+      "loss": 0.2179,
+      "step": 876
+    },
+    {
+      "epoch": 1.6254906488108982,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.618480900866502e-06,
+      "loss": 0.2161,
+      "step": 880
+    },
+    {
+      "epoch": 1.6328792426691296,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.536044254117572e-06,
+      "loss": 0.2139,
+      "step": 884
+    },
+    {
+      "epoch": 1.6402678365273609,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.453639193323844e-06,
+      "loss": 0.226,
+      "step": 888
+    },
+    {
+      "epoch": 1.6476564303855923,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.371271328594867e-06,
+      "loss": 0.2072,
+      "step": 892
+    },
+    {
+      "epoch": 1.6550450242438237,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.28894626750789e-06,
+      "loss": 0.2195,
+      "step": 896
+    },
+    {
+      "epoch": 1.662433618102055,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.2066696147261e-06,
+      "loss": 0.2293,
+      "step": 900
+    },
+    {
+      "epoch": 1.6698222119602864,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.124446971617078e-06,
+      "loss": 0.2313,
+      "step": 904
+    },
+    {
+      "epoch": 1.6772108058185178,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.042283935871425e-06,
+      "loss": 0.2237,
+      "step": 908
+    },
+    {
+      "epoch": 1.684599399676749,
+      "grad_norm": 1.671875,
+      "learning_rate": 8.9601861011217e-06,
+      "loss": 0.2418,
+      "step": 912
+    },
+    {
+      "epoch": 1.6919879935349804,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.878159056561605e-06,
+      "loss": 0.2304,
+      "step": 916
+    },
+    {
+      "epoch": 1.6993765873932118,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.796208386565465e-06,
+      "loss": 0.2202,
+      "step": 920
+    },
+    {
+      "epoch": 1.706765181251443,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.714339670308045e-06,
+      "loss": 0.2104,
+      "step": 924
+    },
+    {
+      "epoch": 1.7141537751096745,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.632558481384729e-06,
+      "loss": 0.2206,
+      "step": 928
+    },
+    {
+      "epoch": 1.721542368967906,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.550870387432075e-06,
+      "loss": 0.2187,
+      "step": 932
+    },
+    {
+      "epoch": 1.7289309628261371,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.469280949748764e-06,
+      "loss": 0.2283,
+      "step": 936
+    },
+    {
+      "epoch": 1.7363195566843685,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.38779572291698e-06,
+      "loss": 0.2195,
+      "step": 940
+    },
+    {
+      "epoch": 1.7437081505426,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.306420254424274e-06,
+      "loss": 0.2237,
+      "step": 944
+    },
+    {
+      "epoch": 1.7510967444008312,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.225160084285893e-06,
+      "loss": 0.2109,
+      "step": 948
+    },
+    {
+      "epoch": 1.7584853382590626,
+      "grad_norm": 1.75,
+      "learning_rate": 8.144020744667596e-06,
+      "loss": 0.2244,
+      "step": 952
+    },
+    {
+      "epoch": 1.765873932117294,
+      "grad_norm": 1.640625,
+      "learning_rate": 8.063007759509044e-06,
+      "loss": 0.2318,
+      "step": 956
+    },
+    {
+      "epoch": 1.7732625259755253,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.982126644147733e-06,
+      "loss": 0.2318,
+      "step": 960
+    },
+    {
+      "epoch": 1.7806511198337567,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.901382904943505e-06,
+      "loss": 0.2226,
+      "step": 964
+    },
+    {
+      "epoch": 1.788039713691988,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.82078203890367e-06,
+      "loss": 0.2323,
+      "step": 968
+    },
+    {
+      "epoch": 1.7954283075502193,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.740329533308793e-06,
+      "loss": 0.2209,
+      "step": 972
+    },
+    {
+      "epoch": 1.8028169014084507,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.660030865339096e-06,
+      "loss": 0.2228,
+      "step": 976
+    },
+    {
+      "epoch": 1.8102054952666822,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.57989150170159e-06,
+      "loss": 0.2378,
+      "step": 980
+    },
+    {
+      "epoch": 1.8175940891249134,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.499916898257906e-06,
+      "loss": 0.2257,
+      "step": 984
+    },
+    {
+      "epoch": 1.8249826829831448,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.420112499652851e-06,
+      "loss": 0.2138,
+      "step": 988
+    },
+    {
+      "epoch": 1.8323712768413762,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.3404837389437314e-06,
+      "loss": 0.2219,
+      "step": 992
+    },
+    {
+      "epoch": 1.8397598706996074,
+      "grad_norm": 1.625,
+      "learning_rate": 7.261036037230499e-06,
+      "loss": 0.2291,
+      "step": 996
+    },
+    {
+      "epoch": 1.8471484645578389,
+      "grad_norm": 1.6015625,
+      "learning_rate": 7.181774803286661e-06,
+      "loss": 0.2437,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8545370584160703,
+      "grad_norm": 1.5,
+      "learning_rate": 7.102705433191066e-06,
+      "loss": 0.2206,
+      "step": 1004
+    },
+    {
+      "epoch": 1.8619256522743015,
+      "grad_norm": 1.5,
+      "learning_rate": 7.02383330996052e-06,
+      "loss": 0.228,
+      "step": 1008
+    },
+    {
+      "epoch": 1.869314246132533,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.945163803183345e-06,
+      "loss": 0.2234,
+      "step": 1012
+    },
+    {
+      "epoch": 1.8767028399907644,
+      "grad_norm": 1.65625,
+      "learning_rate": 6.866702268653787e-06,
+      "loss": 0.2359,
+      "step": 1016
+    },
+    {
+      "epoch": 1.8840914338489956,
+      "grad_norm": 1.625,
+      "learning_rate": 6.788454048007418e-06,
+      "loss": 0.2411,
+      "step": 1020
+    },
+    {
+      "epoch": 1.891480027707227,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.710424468357471e-06,
+      "loss": 0.2315,
+      "step": 1024
+    },
+    {
+      "epoch": 1.8988686215654584,
+      "grad_norm": 1.4375,
+      "learning_rate": 6.632618841932164e-06,
+      "loss": 0.2092,
+      "step": 1028
+    },
+    {
+      "epoch": 1.9062572154236896,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.555042465713059e-06,
+      "loss": 0.2192,
+      "step": 1032
+    },
+    {
+      "epoch": 1.913645809281921,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.4777006210744375e-06,
+      "loss": 0.2158,
+      "step": 1036
+    },
+    {
+      "epoch": 1.9210344031401525,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.400598573423753e-06,
+      "loss": 0.2213,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9284229969983837,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.323741571843145e-06,
+      "loss": 0.2106,
+      "step": 1044
+    },
+    {
+      "epoch": 1.9358115908566151,
+      "grad_norm": 1.609375,
+      "learning_rate": 6.24713484873211e-06,
+      "loss": 0.2225,
+      "step": 1048
+    },
+    {
+      "epoch": 1.9432001847148466,
+      "grad_norm": 1.5625,
+      "learning_rate": 6.170783619451264e-06,
+      "loss": 0.2151,
+      "step": 1052
+    },
+    {
+      "epoch": 1.9505887785730778,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.094693081967289e-06,
+      "loss": 0.2305,
+      "step": 1056
+    },
+    {
+      "epoch": 1.9579773724313092,
+      "grad_norm": 1.609375,
+      "learning_rate": 6.018868416499046e-06,
+      "loss": 0.2196,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9653659662895406,
+      "grad_norm": 1.625,
+      "learning_rate": 5.943314785164924e-06,
+      "loss": 0.2395,
+      "step": 1064
+    },
+    {
+      "epoch": 1.9727545601477718,
+      "grad_norm": 1.546875,
+      "learning_rate": 5.8680373316314e-06,
+      "loss": 0.2275,
+      "step": 1068
+    },
+    {
+      "epoch": 1.9801431540060033,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.793041180762845e-06,
+      "loss": 0.2246,
+      "step": 1072
+    },
+    {
+      "epoch": 1.9875317478642347,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.7183314382726555e-06,
+      "loss": 0.2268,
+      "step": 1076
+    },
+    {
+      "epoch": 1.994920341722466,
+      "grad_norm": 1.65625,
+      "learning_rate": 5.643913190375614e-06,
+      "loss": 0.2132,
+      "step": 1080
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 1623,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3964435361415823e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8470b43419937f5bdaf5acf1baa0c879d6d60399d1cf8b2e76cbb2b4cb0ffe8e
+size 5432