Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "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": 8192,
+  "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": null,
+  "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 sha256:0f8f0ef1463d703471b0bac341a92f55bfb0947cadec4f47bbfb0bd1c2ec61ed
+size 4976707520

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed9086f88edd8261f560f43a277bce27f62cadbd17077d956de76b3426c885b
+size 4999803552

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d645861d1b36c0ad4c62ba0ea2303d52048082aa3f7828af13b35358a7d9a6fb
+size 4915916976

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1d700f58675aa745737ddf985898a584d44dd7cf0720fcaf58e01b81984f80
+size 4920065288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f567a852edbdd9bc2c5f25ce9ce30c4d9885d7db6d98dfec1adf932e0dd4006
+size 4915916144

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8caf8d7cec8dd0a587eedad9d3ddd6e5de0c9390eba75afa154b0aac45aa874
+size 4915916176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5a1ca1d1be85d9741a6ec6508269a449cc93f1baf1f1e20a471d0fb60304f8
+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:b412713f675ae6f44fca626cdc78c952f79e38fc3dc6dfd006f4f29a378bde8b
+size 1064

trainer_state.json

@@ -0,0 +1,2868 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9979219579773724,
+  "eval_steps": 500,
+  "global_step": 1623,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0073885938582313555,
+      "grad_norm": 35.5,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.1173,
+      "step": 4
+    },
+    {
+      "epoch": 0.014777187716462711,
+      "grad_norm": 33.75,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 3.0688,
+      "step": 8
+    },
+    {
+      "epoch": 0.022165781574694066,
+      "grad_norm": 27.25,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.8447,
+      "step": 12
+    },
+    {
+      "epoch": 0.029554375432925422,
+      "grad_norm": 21.125,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.2541,
+      "step": 16
+    },
+    {
+      "epoch": 0.03694296929115678,
+      "grad_norm": 19.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6668,
+      "step": 20
+    },
+    {
+      "epoch": 0.04433156314938813,
+      "grad_norm": 7.625,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.9365,
+      "step": 24
+    },
+    {
+      "epoch": 0.051720157007619484,
+      "grad_norm": 5.34375,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.6331,
+      "step": 28
+    },
+    {
+      "epoch": 0.059108750865850844,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5437,
+      "step": 32
+    },
+    {
+      "epoch": 0.0664973447240822,
+      "grad_norm": 3.109375,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.4885,
+      "step": 36
+    },
+    {
+      "epoch": 0.07388593858231356,
+      "grad_norm": 3.078125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4844,
+      "step": 40
+    },
+    {
+      "epoch": 0.0812745324405449,
+      "grad_norm": 2.9375,
+      "learning_rate": 8.8e-06,
+      "loss": 0.4414,
+      "step": 44
+    },
+    {
+      "epoch": 0.08866312629877626,
+      "grad_norm": 2.6875,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.4578,
+      "step": 48
+    },
+    {
+      "epoch": 0.09605172015700762,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.04e-05,
+      "loss": 0.4403,
+      "step": 52
+    },
+    {
+      "epoch": 0.10344031401523897,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.4154,
+      "step": 56
+    },
+    {
+      "epoch": 0.11082890787347033,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4355,
+      "step": 60
+    },
+    {
+      "epoch": 0.11821750173170169,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.4011,
+      "step": 64
+    },
+    {
+      "epoch": 0.12560609558993305,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.3987,
+      "step": 68
+    },
+    {
+      "epoch": 0.1329946894481644,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.4105,
+      "step": 72
+    },
+    {
+      "epoch": 0.14038328330639574,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.4073,
+      "step": 76
+    },
+    {
+      "epoch": 0.1477718771646271,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4145,
+      "step": 80
+    },
+    {
+      "epoch": 0.15516047102285846,
+      "grad_norm": 2.25,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.4038,
+      "step": 84
+    },
+    {
+      "epoch": 0.1625490648810898,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.76e-05,
+      "loss": 0.4027,
+      "step": 88
+    },
+    {
+      "epoch": 0.16993765873932118,
+      "grad_norm": 2.125,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.3993,
+      "step": 92
+    },
+    {
+      "epoch": 0.17732625259755253,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4072,
+      "step": 96
+    },
+    {
+      "epoch": 0.18471484645578387,
+      "grad_norm": 2.3125,
+      "learning_rate": 2e-05,
+      "loss": 0.3966,
+      "step": 100
+    },
+    {
+      "epoch": 0.19210344031401524,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.9999659601637828e-05,
+      "loss": 0.3952,
+      "step": 104
+    },
+    {
+      "epoch": 0.1994920341722466,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.9998638429725526e-05,
+      "loss": 0.3997,
+      "step": 108
+    },
+    {
+      "epoch": 0.20688062803047794,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.9996936553784137e-05,
+      "loss": 0.4091,
+      "step": 112
+    },
+    {
+      "epoch": 0.2142692218887093,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.999455408967682e-05,
+      "loss": 0.404,
+      "step": 116
+    },
+    {
+      "epoch": 0.22165781574694066,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.999149119960095e-05,
+      "loss": 0.4082,
+      "step": 120
+    },
+    {
+      "epoch": 0.229046409605172,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.9987748092077082e-05,
+      "loss": 0.3819,
+      "step": 124
+    },
+    {
+      "epoch": 0.23643500346340338,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.998332502193475e-05,
+      "loss": 0.3985,
+      "step": 128
+    },
+    {
+      "epoch": 0.24382359732163472,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.9978222290295116e-05,
+      "loss": 0.4103,
+      "step": 132
+    },
+    {
+      "epoch": 0.2512121911798661,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.9972440244550485e-05,
+      "loss": 0.3708,
+      "step": 136
+    },
+    {
+      "epoch": 0.2586007850380974,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.9965979278340638e-05,
+      "loss": 0.4049,
+      "step": 140
+    },
+    {
+      "epoch": 0.2659893788963288,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.995883983152603e-05,
+      "loss": 0.3924,
+      "step": 144
+    },
+    {
+      "epoch": 0.27337797275456016,
+      "grad_norm": 2.0,
+      "learning_rate": 1.995102239015787e-05,
+      "loss": 0.4132,
+      "step": 148
+    },
+    {
+      "epoch": 0.2807665666127915,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.9942527486445e-05,
+      "loss": 0.3873,
+      "step": 152
+    },
+    {
+      "epoch": 0.28815516047102285,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.9933355698717683e-05,
+      "loss": 0.403,
+      "step": 156
+    },
+    {
+      "epoch": 0.2955437543292542,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.9923507651388224e-05,
+      "loss": 0.3738,
+      "step": 160
+    },
+    {
+      "epoch": 0.30293234818748555,
+      "grad_norm": 1.9765625,
+      "learning_rate": 1.991298401490846e-05,
+      "loss": 0.4014,
+      "step": 164
+    },
+    {
+      "epoch": 0.3103209420457169,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.9901785505724117e-05,
+      "loss": 0.3864,
+      "step": 168
+    },
+    {
+      "epoch": 0.3177095359039483,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.988991288622603e-05,
+      "loss": 0.3689,
+      "step": 172
+    },
+    {
+      "epoch": 0.3250981297621796,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.9877366964698242e-05,
+      "loss": 0.3784,
+      "step": 176
+    },
+    {
+      "epoch": 0.332486723620411,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9864148595262988e-05,
+      "loss": 0.369,
+      "step": 180
+    },
+    {
+      "epoch": 0.33987531747864236,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.985025867782252e-05,
+      "loss": 0.373,
+      "step": 184
+    },
+    {
+      "epoch": 0.3472639113368737,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.9835698157997877e-05,
+      "loss": 0.3568,
+      "step": 188
+    },
+    {
+      "epoch": 0.35465250519510505,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.9820468027064478e-05,
+      "loss": 0.3855,
+      "step": 192
+    },
+    {
+      "epoch": 0.3620410990533364,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9804569321884638e-05,
+      "loss": 0.3731,
+      "step": 196
+    },
+    {
+      "epoch": 0.36942969291156774,
+      "grad_norm": 2.125,
+      "learning_rate": 1.978800312483701e-05,
+      "loss": 0.3738,
+      "step": 200
+    },
+    {
+      "epoch": 0.3768182867697991,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.9770770563742854e-05,
+      "loss": 0.3719,
+      "step": 204
+    },
+    {
+      "epoch": 0.3842068806280305,
+      "grad_norm": 2.125,
+      "learning_rate": 1.975287281178929e-05,
+      "loss": 0.3838,
+      "step": 208
+    },
+    {
+      "epoch": 0.3915954744862618,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.9734311087449408e-05,
+      "loss": 0.3605,
+      "step": 212
+    },
+    {
+      "epoch": 0.3989840683444932,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.9715086654399317e-05,
+      "loss": 0.3785,
+      "step": 216
+    },
+    {
+      "epoch": 0.40637266220272455,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.9695200821432126e-05,
+      "loss": 0.3627,
+      "step": 220
+    },
+    {
+      "epoch": 0.4137612560609559,
+      "grad_norm": 2.125,
+      "learning_rate": 1.9674654942368824e-05,
+      "loss": 0.357,
+      "step": 224
+    },
+    {
+      "epoch": 0.42114984991918725,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.965345041596613e-05,
+      "loss": 0.387,
+      "step": 228
+    },
+    {
+      "epoch": 0.4285384437774186,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.963158868582126e-05,
+      "loss": 0.3789,
+      "step": 232
+    },
+    {
+      "epoch": 0.43592703763564994,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.9609071240273637e-05,
+      "loss": 0.3792,
+      "step": 236
+    },
+    {
+      "epoch": 0.4433156314938813,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.958589961230358e-05,
+      "loss": 0.3735,
+      "step": 240
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9562075379427926e-05,
+      "loss": 0.387,
+      "step": 244
+    },
+    {
+      "epoch": 0.458092819210344,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.953760016359265e-05,
+      "loss": 0.385,
+      "step": 248
+    },
+    {
+      "epoch": 0.4654814130685754,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.951247563106243e-05,
+      "loss": 0.3725,
+      "step": 252
+    },
+    {
+      "epoch": 0.47287000692680675,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.9486703492307207e-05,
+      "loss": 0.3739,
+      "step": 256
+    },
+    {
+      "epoch": 0.48025860078503807,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.9460285501885744e-05,
+      "loss": 0.3721,
+      "step": 260
+    },
+    {
+      "epoch": 0.48764719464326944,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.943322345832618e-05,
+      "loss": 0.3764,
+      "step": 264
+    },
+    {
+      "epoch": 0.4950357885015008,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.9405519204003577e-05,
+      "loss": 0.3491,
+      "step": 268
+    },
+    {
+      "epoch": 0.5024243823597322,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.9377174625014485e-05,
+      "loss": 0.3924,
+      "step": 272
+    },
+    {
+      "epoch": 0.5098129762179635,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.9348191651048565e-05,
+      "loss": 0.3416,
+      "step": 276
+    },
+    {
+      "epoch": 0.5172015700761948,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.9318572255257192e-05,
+      "loss": 0.3718,
+      "step": 280
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9288318454119122e-05,
+      "loss": 0.3684,
+      "step": 284
+    },
+    {
+      "epoch": 0.5319787577926576,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.9257432307303232e-05,
+      "loss": 0.3725,
+      "step": 288
+    },
+    {
+      "epoch": 0.5393673516508889,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.9225915917528277e-05,
+      "loss": 0.3816,
+      "step": 292
+    },
+    {
+      "epoch": 0.5467559455091203,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.919377143041975e-05,
+      "loss": 0.3814,
+      "step": 296
+    },
+    {
+      "epoch": 0.5541445393673516,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.916100103436381e-05,
+      "loss": 0.3533,
+      "step": 300
+    },
+    {
+      "epoch": 0.561533133225583,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.9127606960358274e-05,
+      "loss": 0.3694,
+      "step": 304
+    },
+    {
+      "epoch": 0.5689217270838144,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.9093591481860772e-05,
+      "loss": 0.3755,
+      "step": 308
+    },
+    {
+      "epoch": 0.5763103209420457,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.9058956914633933e-05,
+      "loss": 0.385,
+      "step": 312
+    },
+    {
+      "epoch": 0.583698914800277,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.9023705616587747e-05,
+      "loss": 0.3513,
+      "step": 316
+    },
+    {
+      "epoch": 0.5910875086585085,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.8987839987619042e-05,
+      "loss": 0.3838,
+      "step": 320
+    },
+    {
+      "epoch": 0.5984761025167398,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.895136246944809e-05,
+      "loss": 0.3572,
+      "step": 324
+    },
+    {
+      "epoch": 0.6058646963749711,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.8914275545452377e-05,
+      "loss": 0.3766,
+      "step": 328
+    },
+    {
+      "epoch": 0.6132532902332025,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.887658174049754e-05,
+      "loss": 0.3733,
+      "step": 332
+    },
+    {
+      "epoch": 0.6206418840914338,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.8838283620765476e-05,
+      "loss": 0.3438,
+      "step": 336
+    },
+    {
+      "epoch": 0.6280304779496652,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.879938379357962e-05,
+      "loss": 0.3589,
+      "step": 340
+    },
+    {
+      "epoch": 0.6354190718078966,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.8759884907227485e-05,
+      "loss": 0.3486,
+      "step": 344
+    },
+    {
+      "epoch": 0.6428076656661279,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.87197896507803e-05,
+      "loss": 0.359,
+      "step": 348
+    },
+    {
+      "epoch": 0.6501962595243592,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.867910075390999e-05,
+      "loss": 0.3461,
+      "step": 352
+    },
+    {
+      "epoch": 0.6575848533825907,
+      "grad_norm": 1.828125,
+      "learning_rate": 1.8637820986703335e-05,
+      "loss": 0.3516,
+      "step": 356
+    },
+    {
+      "epoch": 0.664973447240822,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.8595953159473357e-05,
+      "loss": 0.3521,
+      "step": 360
+    },
+    {
+      "epoch": 0.6723620410990533,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.8553500122568023e-05,
+      "loss": 0.3536,
+      "step": 364
+    },
+    {
+      "epoch": 0.6797506349572847,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.8510464766176178e-05,
+      "loss": 0.3578,
+      "step": 368
+    },
+    {
+      "epoch": 0.687139228815516,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.8466850020130786e-05,
+      "loss": 0.3491,
+      "step": 372
+    },
+    {
+      "epoch": 0.6945278226737474,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8422658853709475e-05,
+      "loss": 0.3551,
+      "step": 376
+    },
+    {
+      "epoch": 0.7019164165319788,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.8377894275432376e-05,
+      "loss": 0.3497,
+      "step": 380
+    },
+    {
+      "epoch": 0.7093050103902101,
+      "grad_norm": 1.96875,
+      "learning_rate": 1.833255933285732e-05,
+      "loss": 0.3664,
+      "step": 384
+    },
+    {
+      "epoch": 0.7166936042484414,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.8286657112372342e-05,
+      "loss": 0.3769,
+      "step": 388
+    },
+    {
+      "epoch": 0.7240821981066728,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.8240190738985578e-05,
+      "loss": 0.3586,
+      "step": 392
+    },
+    {
+      "epoch": 0.7314707919649042,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.819316337611251e-05,
+      "loss": 0.3612,
+      "step": 396
+    },
+    {
+      "epoch": 0.7388593858231355,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.8145578225360594e-05,
+      "loss": 0.3575,
+      "step": 400
+    },
+    {
+      "epoch": 0.7462479796813669,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.809743852631131e-05,
+      "loss": 0.3572,
+      "step": 404
+    },
+    {
+      "epoch": 0.7536365735395982,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.8048747556299595e-05,
+      "loss": 0.375,
+      "step": 408
+    },
+    {
+      "epoch": 0.7610251673978295,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.7999508630190742e-05,
+      "loss": 0.3633,
+      "step": 412
+    },
+    {
+      "epoch": 0.768413761256061,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7949725100154707e-05,
+      "loss": 0.3662,
+      "step": 416
+    },
+    {
+      "epoch": 0.7758023551142923,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.789940035543792e-05,
+      "loss": 0.3508,
+      "step": 420
+    },
+    {
+      "epoch": 0.7831909489725236,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.7848537822132498e-05,
+      "loss": 0.3513,
+      "step": 424
+    },
+    {
+      "epoch": 0.790579542830755,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.7797140962943062e-05,
+      "loss": 0.3558,
+      "step": 428
+    },
+    {
+      "epoch": 0.7979681366889864,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.7745213276950947e-05,
+      "loss": 0.3648,
+      "step": 432
+    },
+    {
+      "epoch": 0.8053567305472177,
+      "grad_norm": 2.0,
+      "learning_rate": 1.7692758299376002e-05,
+      "loss": 0.3584,
+      "step": 436
+    },
+    {
+      "epoch": 0.8127453244054491,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.7639779601335916e-05,
+      "loss": 0.3601,
+      "step": 440
+    },
+    {
+      "epoch": 0.8201339182636804,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.7586280789603104e-05,
+      "loss": 0.3664,
+      "step": 444
+    },
+    {
+      "epoch": 0.8275225121219117,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.753226550635914e-05,
+      "loss": 0.3371,
+      "step": 448
+    },
+    {
+      "epoch": 0.8349111059801432,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7477737428946814e-05,
+      "loss": 0.3533,
+      "step": 452
+    },
+    {
+      "epoch": 0.8422996998383745,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.742270026961978e-05,
+      "loss": 0.3477,
+      "step": 456
+    },
+    {
+      "epoch": 0.8496882936966058,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.736715777528981e-05,
+      "loss": 0.3471,
+      "step": 460
+    },
+    {
+      "epoch": 0.8570768875548372,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7311113727271728e-05,
+      "loss": 0.3361,
+      "step": 464
+    },
+    {
+      "epoch": 0.8644654814130686,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.725457194102596e-05,
+      "loss": 0.3327,
+      "step": 468
+    },
+    {
+      "epoch": 0.8718540752712999,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.71975362658988e-05,
+      "loss": 0.3411,
+      "step": 472
+    },
+    {
+      "epoch": 0.8792426691295313,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.7140010584860322e-05,
+      "loss": 0.3582,
+      "step": 476
+    },
+    {
+      "epoch": 0.8866312629877626,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.708199881424005e-05,
+      "loss": 0.3464,
+      "step": 480
+    },
+    {
+      "epoch": 0.8940198568459939,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.7023504903460325e-05,
+      "loss": 0.3534,
+      "step": 484
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.696453283476743e-05,
+      "loss": 0.3791,
+      "step": 488
+    },
+    {
+      "epoch": 0.9087970445624567,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.6905086622960488e-05,
+      "loss": 0.3647,
+      "step": 492
+    },
+    {
+      "epoch": 0.916185638420688,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.6845170315118124e-05,
+      "loss": 0.3719,
+      "step": 496
+    },
+    {
+      "epoch": 0.9235742322789194,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.678478799032295e-05,
+      "loss": 0.3428,
+      "step": 500
+    },
+    {
+      "epoch": 0.9309628261371508,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.6723943759383857e-05,
+      "loss": 0.3496,
+      "step": 504
+    },
+    {
+      "epoch": 0.9383514199953821,
+      "grad_norm": 1.75,
+      "learning_rate": 1.666264176455616e-05,
+      "loss": 0.347,
+      "step": 508
+    },
+    {
+      "epoch": 0.9457400138536135,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.660088617925959e-05,
+      "loss": 0.3331,
+      "step": 512
+    },
+    {
+      "epoch": 0.9531286077118448,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.6538681207794153e-05,
+      "loss": 0.3611,
+      "step": 516
+    },
+    {
+      "epoch": 0.9605172015700761,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.6476031085053937e-05,
+      "loss": 0.3658,
+      "step": 520
+    },
+    {
+      "epoch": 0.9679057954283076,
+      "grad_norm": 1.875,
+      "learning_rate": 1.6412940076238782e-05,
+      "loss": 0.3569,
+      "step": 524
+    },
+    {
+      "epoch": 0.9752943892865389,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.6349412476563893e-05,
+      "loss": 0.3687,
+      "step": 528
+    },
+    {
+      "epoch": 0.9826829831447702,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.628545261096745e-05,
+      "loss": 0.3644,
+      "step": 532
+    },
+    {
+      "epoch": 0.9900715770030016,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.622106483381615e-05,
+      "loss": 0.3331,
+      "step": 536
+    },
+    {
+      "epoch": 0.997460170861233,
+      "grad_norm": 1.75,
+      "learning_rate": 1.615625352860877e-05,
+      "loss": 0.3317,
+      "step": 540
+    },
+    {
+      "epoch": 1.0048487647194644,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.6091023107677747e-05,
+      "loss": 0.2819,
+      "step": 544
+    },
+    {
+      "epoch": 1.0122373585776956,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.602537801188876e-05,
+      "loss": 0.2252,
+      "step": 548
+    },
+    {
+      "epoch": 1.019625952435927,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.5959322710338426e-05,
+      "loss": 0.2342,
+      "step": 552
+    },
+    {
+      "epoch": 1.0270145462941584,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.589286170005005e-05,
+      "loss": 0.2301,
+      "step": 556
+    },
+    {
+      "epoch": 1.0344031401523897,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.5825999505667426e-05,
+      "loss": 0.2461,
+      "step": 560
+    },
+    {
+      "epoch": 1.041791734010621,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.5758740679146858e-05,
+      "loss": 0.2147,
+      "step": 564
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.569108979944722e-05,
+      "loss": 0.2111,
+      "step": 568
+    },
+    {
+      "epoch": 1.0565689217270837,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.562305147221824e-05,
+      "loss": 0.2223,
+      "step": 572
+    },
+    {
+      "epoch": 1.0639575155853152,
+      "grad_norm": 1.75,
+      "learning_rate": 1.5554630329486954e-05,
+      "loss": 0.2169,
+      "step": 576
+    },
+    {
+      "epoch": 1.0713461094435466,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.548583102934234e-05,
+      "loss": 0.2331,
+      "step": 580
+    },
+    {
+      "epoch": 1.0787347033017778,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.541665825561822e-05,
+      "loss": 0.218,
+      "step": 584
+    },
+    {
+      "epoch": 1.0861232971600092,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.5347116717574367e-05,
+      "loss": 0.2172,
+      "step": 588
+    },
+    {
+      "epoch": 1.0935118910182406,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.5277211149575915e-05,
+      "loss": 0.2283,
+      "step": 592
+    },
+    {
+      "epoch": 1.1009004848764719,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.5206946310771034e-05,
+      "loss": 0.2139,
+      "step": 596
+    },
+    {
+      "epoch": 1.1082890787347033,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.5136326984766934e-05,
+      "loss": 0.229,
+      "step": 600
+    },
+    {
+      "epoch": 1.1156776725929347,
+      "grad_norm": 1.625,
+      "learning_rate": 1.5065357979304191e-05,
+      "loss": 0.2224,
+      "step": 604
+    },
+    {
+      "epoch": 1.123066266451166,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.4994044125929458e-05,
+      "loss": 0.2253,
+      "step": 608
+    },
+    {
+      "epoch": 1.1304548603093973,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.492239027966651e-05,
+      "loss": 0.2319,
+      "step": 612
+    },
+    {
+      "epoch": 1.1378434541676288,
+      "grad_norm": 1.625,
+      "learning_rate": 1.4850401318685728e-05,
+      "loss": 0.2161,
+      "step": 616
+    },
+    {
+      "epoch": 1.14523204802586,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.4778082143971992e-05,
+      "loss": 0.2216,
+      "step": 620
+    },
+    {
+      "epoch": 1.1526206418840914,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.4705437678991034e-05,
+      "loss": 0.2111,
+      "step": 624
+    },
+    {
+      "epoch": 1.1600092357423228,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.463247286935423e-05,
+      "loss": 0.2195,
+      "step": 628
+    },
+    {
+      "epoch": 1.167397829600554,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.455919268248192e-05,
+      "loss": 0.237,
+      "step": 632
+    },
+    {
+      "epoch": 1.1747864234587855,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.4485602107265221e-05,
+      "loss": 0.2263,
+      "step": 636
+    },
+    {
+      "epoch": 1.182175017317017,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.4411706153726391e-05,
+      "loss": 0.2176,
+      "step": 640
+    },
+    {
+      "epoch": 1.1895636111752481,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.4337509852677735e-05,
+      "loss": 0.2179,
+      "step": 644
+    },
+    {
+      "epoch": 1.1969522050334795,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.4263018255379132e-05,
+      "loss": 0.2137,
+      "step": 648
+    },
+    {
+      "epoch": 1.204340798891711,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.4188236433194117e-05,
+      "loss": 0.2141,
+      "step": 652
+    },
+    {
+      "epoch": 1.2117293927499422,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.4113169477244659e-05,
+      "loss": 0.2113,
+      "step": 656
+    },
+    {
+      "epoch": 1.2191179866081736,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.4037822498064517e-05,
+      "loss": 0.2197,
+      "step": 660
+    },
+    {
+      "epoch": 1.226506580466405,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.3962200625251363e-05,
+      "loss": 0.2115,
+      "step": 664
+    },
+    {
+      "epoch": 1.2338951743246362,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.3886309007117522e-05,
+      "loss": 0.2322,
+      "step": 668
+    },
+    {
+      "epoch": 1.2412837681828677,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.3810152810339496e-05,
+      "loss": 0.2331,
+      "step": 672
+    },
+    {
+      "epoch": 1.248672362041099,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.3733737219606222e-05,
+      "loss": 0.2248,
+      "step": 676
+    },
+    {
+      "epoch": 1.2560609558993305,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.3657067437266078e-05,
+      "loss": 0.2007,
+      "step": 680
+    },
+    {
+      "epoch": 1.2634495497575617,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.3580148682972739e-05,
+      "loss": 0.2224,
+      "step": 684
+    },
+    {
+      "epoch": 1.2708381436157932,
+      "grad_norm": 1.625,
+      "learning_rate": 1.3502986193329793e-05,
+      "loss": 0.2188,
+      "step": 688
+    },
+    {
+      "epoch": 1.2782267374740246,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.3425585221534266e-05,
+      "loss": 0.2263,
+      "step": 692
+    },
+    {
+      "epoch": 1.2856153313322558,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.3347951037018961e-05,
+      "loss": 0.2156,
+      "step": 696
+    },
+    {
+      "epoch": 1.2930039251904872,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.3270088925093726e-05,
+      "loss": 0.2142,
+      "step": 700
+    },
+    {
+      "epoch": 1.3003925190487187,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.3192004186585643e-05,
+      "loss": 0.2182,
+      "step": 704
+    },
+    {
+      "epoch": 1.3077811129069499,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.311370213747813e-05,
+      "loss": 0.2293,
+      "step": 708
+    },
+    {
+      "epoch": 1.3151697067651813,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.3035188108549035e-05,
+      "loss": 0.2297,
+      "step": 712
+    },
+    {
+      "epoch": 1.3225583006234127,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.2956467445007736e-05,
+      "loss": 0.2289,
+      "step": 716
+    },
+    {
+      "epoch": 1.329946894481644,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.2877545506131219e-05,
+      "loss": 0.2201,
+      "step": 720
+    },
+    {
+      "epoch": 1.3373354883398754,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.2798427664899232e-05,
+      "loss": 0.2181,
+      "step": 724
+    },
+    {
+      "epoch": 1.3447240821981068,
+      "grad_norm": 1.75,
+      "learning_rate": 1.271911930762848e-05,
+      "loss": 0.2161,
+      "step": 728
+    },
+    {
+      "epoch": 1.352112676056338,
+      "grad_norm": 1.75,
+      "learning_rate": 1.2639625833605959e-05,
+      "loss": 0.2186,
+      "step": 732
+    },
+    {
+      "epoch": 1.3595012699145694,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.255995265472134e-05,
+      "loss": 0.2219,
+      "step": 736
+    },
+    {
+      "epoch": 1.3668898637728009,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.2480105195098537e-05,
+      "loss": 0.229,
+      "step": 740
+    },
+    {
+      "epoch": 1.374278457631032,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.2400088890726451e-05,
+      "loss": 0.2207,
+      "step": 744
+    },
+    {
+      "epoch": 1.3816670514892635,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.231990918908887e-05,
+      "loss": 0.2163,
+      "step": 748
+    },
+    {
+      "epoch": 1.389055645347495,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.2239571548793618e-05,
+      "loss": 0.2081,
+      "step": 752
+    },
+    {
+      "epoch": 1.3964442392057261,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.2159081439200933e-05,
+      "loss": 0.2352,
+      "step": 756
+    },
+    {
+      "epoch": 1.4038328330639576,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.2078444340051107e-05,
+      "loss": 0.2258,
+      "step": 760
+    },
+    {
+      "epoch": 1.411221426922189,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.199766574109144e-05,
+      "loss": 0.2215,
+      "step": 764
+    },
+    {
+      "epoch": 1.4186100207804202,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.1916751141702485e-05,
+      "loss": 0.2344,
+      "step": 768
+    },
+    {
+      "epoch": 1.4259986146386516,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.1835706050523663e-05,
+      "loss": 0.2186,
+      "step": 772
+    },
+    {
+      "epoch": 1.433387208496883,
+      "grad_norm": 1.75,
+      "learning_rate": 1.1754535985078236e-05,
+      "loss": 0.2076,
+      "step": 776
+    },
+    {
+      "epoch": 1.4407758023551143,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.1673246471397672e-05,
+      "loss": 0.2107,
+      "step": 780
+    },
+    {
+      "epoch": 1.4481643962133457,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.1591843043645432e-05,
+      "loss": 0.2208,
+      "step": 784
+    },
+    {
+      "epoch": 1.4555529900715771,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.1510331243740214e-05,
+      "loss": 0.2204,
+      "step": 788
+    },
+    {
+      "epoch": 1.4629415839298083,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.1428716620978654e-05,
+      "loss": 0.2225,
+      "step": 792
+    },
+    {
+      "epoch": 1.4703301777880398,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.134700473165754e-05,
+      "loss": 0.2298,
+      "step": 796
+    },
+    {
+      "epoch": 1.4777187716462712,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.1265201138695526e-05,
+      "loss": 0.2202,
+      "step": 800
+    },
+    {
+      "epoch": 1.4851073655045024,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.1183311411254425e-05,
+      "loss": 0.1972,
+      "step": 804
+    },
+    {
+      "epoch": 1.4924959593627338,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.1101341124360056e-05,
+      "loss": 0.2101,
+      "step": 808
+    },
+    {
+      "epoch": 1.4998845532209653,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.1019295858522708e-05,
+      "loss": 0.2186,
+      "step": 812
+    },
+    {
+      "epoch": 1.5072731470791965,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.0937181199357192e-05,
+      "loss": 0.2173,
+      "step": 816
+    },
+    {
+      "epoch": 1.514661740937428,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.0855002737202617e-05,
+      "loss": 0.222,
+      "step": 820
+    },
+    {
+      "epoch": 1.5220503347956593,
+      "grad_norm": 1.875,
+      "learning_rate": 1.0772766066741763e-05,
+      "loss": 0.2236,
+      "step": 824
+    },
+    {
+      "epoch": 1.5294389286538905,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.0690476786620214e-05,
+      "loss": 0.2268,
+      "step": 828
+    },
+    {
+      "epoch": 1.536827522512122,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.060814049906521e-05,
+      "loss": 0.2054,
+      "step": 832
+    },
+    {
+      "epoch": 1.5442161163703534,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.0525762809504234e-05,
+      "loss": 0.2262,
+      "step": 836
+    },
+    {
+      "epoch": 1.5516047102285846,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.0443349326183409e-05,
+      "loss": 0.219,
+      "step": 840
+    },
+    {
+      "epoch": 1.558993304086816,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.0360905659785682e-05,
+      "loss": 0.2319,
+      "step": 844
+    },
+    {
+      "epoch": 1.5663818979450475,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.0278437423048862e-05,
+      "loss": 0.2041,
+      "step": 848
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 1.9765625,
+      "learning_rate": 1.0195950230383482e-05,
+      "loss": 0.2128,
+      "step": 852
+    },
+    {
+      "epoch": 1.58115908566151,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.011344969749061e-05,
+      "loss": 0.2207,
+      "step": 856
+    },
+    {
+      "epoch": 1.5885476795197415,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.0030941440979489e-05,
+      "loss": 0.2145,
+      "step": 860
+    },
+    {
+      "epoch": 1.5959362733779727,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.948431077985203e-06,
+      "loss": 0.2155,
+      "step": 864
+    },
+    {
+      "epoch": 1.6033248672362042,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.865924225786241e-06,
+      "loss": 0.2193,
+      "step": 868
+    },
+    {
+      "epoch": 1.6107134610944356,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.783426501422063e-06,
+      "loss": 0.2201,
+      "step": 872
+    },
+    {
+      "epoch": 1.6181020549526668,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.700943521310727e-06,
+      "loss": 0.2103,
+      "step": 876
+    },
+    {
+      "epoch": 1.6254906488108982,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.618480900866502e-06,
+      "loss": 0.211,
+      "step": 880
+    },
+    {
+      "epoch": 1.6328792426691296,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.536044254117572e-06,
+      "loss": 0.2072,
+      "step": 884
+    },
+    {
+      "epoch": 1.6402678365273609,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.453639193323844e-06,
+      "loss": 0.2159,
+      "step": 888
+    },
+    {
+      "epoch": 1.6476564303855923,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.371271328594867e-06,
+      "loss": 0.1998,
+      "step": 892
+    },
+    {
+      "epoch": 1.6550450242438237,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.28894626750789e-06,
+      "loss": 0.2095,
+      "step": 896
+    },
+    {
+      "epoch": 1.662433618102055,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.2066696147261e-06,
+      "loss": 0.2213,
+      "step": 900
+    },
+    {
+      "epoch": 1.6698222119602864,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.124446971617078e-06,
+      "loss": 0.2209,
+      "step": 904
+    },
+    {
+      "epoch": 1.6772108058185178,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.042283935871425e-06,
+      "loss": 0.2143,
+      "step": 908
+    },
+    {
+      "epoch": 1.684599399676749,
+      "grad_norm": 1.8984375,
+      "learning_rate": 8.9601861011217e-06,
+      "loss": 0.2341,
+      "step": 912
+    },
+    {
+      "epoch": 1.6919879935349804,
+      "grad_norm": 1.828125,
+      "learning_rate": 8.878159056561605e-06,
+      "loss": 0.2203,
+      "step": 916
+    },
+    {
+      "epoch": 1.6993765873932118,
+      "grad_norm": 1.640625,
+      "learning_rate": 8.796208386565465e-06,
+      "loss": 0.2105,
+      "step": 920
+    },
+    {
+      "epoch": 1.706765181251443,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.714339670308045e-06,
+      "loss": 0.2024,
+      "step": 924
+    },
+    {
+      "epoch": 1.7141537751096745,
+      "grad_norm": 1.609375,
+      "learning_rate": 8.632558481384729e-06,
+      "loss": 0.2105,
+      "step": 928
+    },
+    {
+      "epoch": 1.721542368967906,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.550870387432075e-06,
+      "loss": 0.2123,
+      "step": 932
+    },
+    {
+      "epoch": 1.7289309628261371,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.469280949748764e-06,
+      "loss": 0.2204,
+      "step": 936
+    },
+    {
+      "epoch": 1.7363195566843685,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.38779572291698e-06,
+      "loss": 0.2111,
+      "step": 940
+    },
+    {
+      "epoch": 1.7437081505426,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.306420254424274e-06,
+      "loss": 0.2155,
+      "step": 944
+    },
+    {
+      "epoch": 1.7510967444008312,
+      "grad_norm": 1.609375,
+      "learning_rate": 8.225160084285893e-06,
+      "loss": 0.203,
+      "step": 948
+    },
+    {
+      "epoch": 1.7584853382590626,
+      "grad_norm": 1.75,
+      "learning_rate": 8.144020744667596e-06,
+      "loss": 0.2153,
+      "step": 952
+    },
+    {
+      "epoch": 1.765873932117294,
+      "grad_norm": 1.796875,
+      "learning_rate": 8.063007759509044e-06,
+      "loss": 0.2201,
+      "step": 956
+    },
+    {
+      "epoch": 1.7732625259755253,
+      "grad_norm": 1.6640625,
+      "learning_rate": 7.982126644147733e-06,
+      "loss": 0.2226,
+      "step": 960
+    },
+    {
+      "epoch": 1.7806511198337567,
+      "grad_norm": 1.6875,
+      "learning_rate": 7.901382904943505e-06,
+      "loss": 0.2119,
+      "step": 964
+    },
+    {
+      "epoch": 1.788039713691988,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.82078203890367e-06,
+      "loss": 0.2215,
+      "step": 968
+    },
+    {
+      "epoch": 1.7954283075502193,
+      "grad_norm": 1.6875,
+      "learning_rate": 7.740329533308793e-06,
+      "loss": 0.2103,
+      "step": 972
+    },
+    {
+      "epoch": 1.8028169014084507,
+      "grad_norm": 1.71875,
+      "learning_rate": 7.660030865339096e-06,
+      "loss": 0.2124,
+      "step": 976
+    },
+    {
+      "epoch": 1.8102054952666822,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.57989150170159e-06,
+      "loss": 0.2277,
+      "step": 980
+    },
+    {
+      "epoch": 1.8175940891249134,
+      "grad_norm": 1.734375,
+      "learning_rate": 7.499916898257906e-06,
+      "loss": 0.2174,
+      "step": 984
+    },
+    {
+      "epoch": 1.8249826829831448,
+      "grad_norm": 1.78125,
+      "learning_rate": 7.420112499652851e-06,
+      "loss": 0.2065,
+      "step": 988
+    },
+    {
+      "epoch": 1.8323712768413762,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.3404837389437314e-06,
+      "loss": 0.2143,
+      "step": 992
+    },
+    {
+      "epoch": 1.8397598706996074,
+      "grad_norm": 1.78125,
+      "learning_rate": 7.261036037230499e-06,
+      "loss": 0.222,
+      "step": 996
+    },
+    {
+      "epoch": 1.8471484645578389,
+      "grad_norm": 1.75,
+      "learning_rate": 7.181774803286661e-06,
+      "loss": 0.2348,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8545370584160703,
+      "grad_norm": 1.6328125,
+      "learning_rate": 7.102705433191066e-06,
+      "loss": 0.209,
+      "step": 1004
+    },
+    {
+      "epoch": 1.8619256522743015,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.02383330996052e-06,
+      "loss": 0.2192,
+      "step": 1008
+    },
+    {
+      "epoch": 1.869314246132533,
+      "grad_norm": 1.6953125,
+      "learning_rate": 6.945163803183345e-06,
+      "loss": 0.2146,
+      "step": 1012
+    },
+    {
+      "epoch": 1.8767028399907644,
+      "grad_norm": 1.7265625,
+      "learning_rate": 6.866702268653787e-06,
+      "loss": 0.2244,
+      "step": 1016
+    },
+    {
+      "epoch": 1.8840914338489956,
+      "grad_norm": 1.71875,
+      "learning_rate": 6.788454048007418e-06,
+      "loss": 0.2312,
+      "step": 1020
+    },
+    {
+      "epoch": 1.891480027707227,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.710424468357471e-06,
+      "loss": 0.2219,
+      "step": 1024
+    },
+    {
+      "epoch": 1.8988686215654584,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.632618841932164e-06,
+      "loss": 0.2022,
+      "step": 1028
+    },
+    {
+      "epoch": 1.9062572154236896,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.555042465713059e-06,
+      "loss": 0.2089,
+      "step": 1032
+    },
+    {
+      "epoch": 1.913645809281921,
+      "grad_norm": 1.7734375,
+      "learning_rate": 6.4777006210744375e-06,
+      "loss": 0.207,
+      "step": 1036
+    },
+    {
+      "epoch": 1.9210344031401525,
+      "grad_norm": 1.703125,
+      "learning_rate": 6.400598573423753e-06,
+      "loss": 0.214,
+      "step": 1040
+    },
+    {
+      "epoch": 1.9284229969983837,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.323741571843145e-06,
+      "loss": 0.2001,
+      "step": 1044
+    },
+    {
+      "epoch": 1.9358115908566151,
+      "grad_norm": 1.765625,
+      "learning_rate": 6.24713484873211e-06,
+      "loss": 0.2099,
+      "step": 1048
+    },
+    {
+      "epoch": 1.9432001847148466,
+      "grad_norm": 1.71875,
+      "learning_rate": 6.170783619451264e-06,
+      "loss": 0.2069,
+      "step": 1052
+    },
+    {
+      "epoch": 1.9505887785730778,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.094693081967289e-06,
+      "loss": 0.22,
+      "step": 1056
+    },
+    {
+      "epoch": 1.9579773724313092,
+      "grad_norm": 1.7578125,
+      "learning_rate": 6.018868416499046e-06,
+      "loss": 0.2097,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9653659662895406,
+      "grad_norm": 1.625,
+      "learning_rate": 5.943314785164924e-06,
+      "loss": 0.2285,
+      "step": 1064
+    },
+    {
+      "epoch": 1.9727545601477718,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.8680373316314e-06,
+      "loss": 0.2183,
+      "step": 1068
+    },
+    {
+      "epoch": 1.9801431540060033,
+      "grad_norm": 1.6953125,
+      "learning_rate": 5.793041180762845e-06,
+      "loss": 0.2173,
+      "step": 1072
+    },
+    {
+      "epoch": 1.9875317478642347,
+      "grad_norm": 1.5625,
+      "learning_rate": 5.7183314382726555e-06,
+      "loss": 0.2186,
+      "step": 1076
+    },
+    {
+      "epoch": 1.994920341722466,
+      "grad_norm": 1.6796875,
+      "learning_rate": 5.643913190375614e-06,
+      "loss": 0.2079,
+      "step": 1080
+    },
+    {
+      "epoch": 2.002308935580697,
+      "grad_norm": 1.1875,
+      "learning_rate": 5.569791503441669e-06,
+      "loss": 0.1967,
+      "step": 1084
+    },
+    {
+      "epoch": 2.0096975294389288,
+      "grad_norm": 1.15625,
+      "learning_rate": 5.4959714236509835e-06,
+      "loss": 0.1402,
+      "step": 1088
+    },
+    {
+      "epoch": 2.01708612329716,
+      "grad_norm": 1.296875,
+      "learning_rate": 5.422457976650416e-06,
+      "loss": 0.127,
+      "step": 1092
+    },
+    {
+      "epoch": 2.024474717155391,
+      "grad_norm": 1.7109375,
+      "learning_rate": 5.349256167211345e-06,
+      "loss": 0.1282,
+      "step": 1096
+    },
+    {
+      "epoch": 2.031863311013623,
+      "grad_norm": 1.84375,
+      "learning_rate": 5.276370978888992e-06,
+      "loss": 0.1247,
+      "step": 1100
+    },
+    {
+      "epoch": 2.039251904871854,
+      "grad_norm": 2.15625,
+      "learning_rate": 5.203807373683094e-06,
+      "loss": 0.1226,
+      "step": 1104
+    },
+    {
+      "epoch": 2.0466404987300852,
+      "grad_norm": 1.7109375,
+      "learning_rate": 5.1315702917001295e-06,
+      "loss": 0.126,
+      "step": 1108
+    },
+    {
+      "epoch": 2.054029092588317,
+      "grad_norm": 1.6484375,
+      "learning_rate": 5.0596646508169755e-06,
+      "loss": 0.1186,
+      "step": 1112
+    },
+    {
+      "epoch": 2.061417686446548,
+      "grad_norm": 1.6640625,
+      "learning_rate": 4.988095346346105e-06,
+      "loss": 0.1227,
+      "step": 1116
+    },
+    {
+      "epoch": 2.0688062803047793,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.91686725070233e-06,
+      "loss": 0.1317,
+      "step": 1120
+    },
+    {
+      "epoch": 2.076194874163011,
+      "grad_norm": 1.4765625,
+      "learning_rate": 4.845985213071067e-06,
+      "loss": 0.1233,
+      "step": 1124
+    },
+    {
+      "epoch": 2.083583468021242,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.775454059078221e-06,
+      "loss": 0.1314,
+      "step": 1128
+    },
+    {
+      "epoch": 2.0909720618794734,
+      "grad_norm": 1.859375,
+      "learning_rate": 4.705278590461646e-06,
+      "loss": 0.1318,
+      "step": 1132
+    },
+    {
+      "epoch": 2.098360655737705,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.6354635847442675e-06,
+      "loss": 0.1249,
+      "step": 1136
+    },
+    {
+      "epoch": 2.1057492495959362,
+      "grad_norm": 1.5703125,
+      "learning_rate": 4.566013794908798e-06,
+      "loss": 0.1262,
+      "step": 1140
+    },
+    {
+      "epoch": 2.1131378434541674,
+      "grad_norm": 1.8828125,
+      "learning_rate": 4.496933949074189e-06,
+      "loss": 0.127,
+      "step": 1144
+    },
+    {
+      "epoch": 2.120526437312399,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.428228750173705e-06,
+      "loss": 0.1178,
+      "step": 1148
+    },
+    {
+      "epoch": 2.1279150311706303,
+      "grad_norm": 1.8359375,
+      "learning_rate": 4.359902875634793e-06,
+      "loss": 0.125,
+      "step": 1152
+    },
+    {
+      "epoch": 2.1353036250288615,
+      "grad_norm": 1.7109375,
+      "learning_rate": 4.2919609770606e-06,
+      "loss": 0.1247,
+      "step": 1156
+    },
+    {
+      "epoch": 2.142692218887093,
+      "grad_norm": 1.5234375,
+      "learning_rate": 4.224407679913338e-06,
+      "loss": 0.1238,
+      "step": 1160
+    },
+    {
+      "epoch": 2.1500808127453244,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.157247583199334e-06,
+      "loss": 0.1169,
+      "step": 1164
+    },
+    {
+      "epoch": 2.1574694066035556,
+      "grad_norm": 1.703125,
+      "learning_rate": 4.090485259155985e-06,
+      "loss": 0.1238,
+      "step": 1168
+    },
+    {
+      "epoch": 2.1648580004617872,
+      "grad_norm": 1.75,
+      "learning_rate": 4.024125252940438e-06,
+      "loss": 0.134,
+      "step": 1172
+    },
+    {
+      "epoch": 2.1722465943200184,
+      "grad_norm": 1.875,
+      "learning_rate": 3.958172082320178e-06,
+      "loss": 0.1233,
+      "step": 1176
+    },
+    {
+      "epoch": 2.1796351881782496,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.892630237365459e-06,
+      "loss": 0.1315,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1870237820364813,
+      "grad_norm": 1.5078125,
+      "learning_rate": 3.827504180143611e-06,
+      "loss": 0.1257,
+      "step": 1184
+    },
+    {
+      "epoch": 2.1944123758947125,
+      "grad_norm": 1.625,
+      "learning_rate": 3.7627983444152847e-06,
+      "loss": 0.1266,
+      "step": 1188
+    },
+    {
+      "epoch": 2.2018009697529437,
+      "grad_norm": 1.7265625,
+      "learning_rate": 3.6985171353325733e-06,
+      "loss": 0.1247,
+      "step": 1192
+    },
+    {
+      "epoch": 2.2091895636111754,
+      "grad_norm": 1.734375,
+      "learning_rate": 3.6346649291391458e-06,
+      "loss": 0.1187,
+      "step": 1196
+    },
+    {
+      "epoch": 2.2165781574694066,
+      "grad_norm": 1.53125,
+      "learning_rate": 3.57124607287227e-06,
+      "loss": 0.1254,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2239667513276378,
+      "grad_norm": 1.578125,
+      "learning_rate": 3.5082648840669165e-06,
+      "loss": 0.1179,
+      "step": 1204
+    },
+    {
+      "epoch": 2.2313553451858694,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.4457256504617833e-06,
+      "loss": 0.1169,
+      "step": 1208
+    },
+    {
+      "epoch": 2.2387439390441006,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.3836326297074175e-06,
+      "loss": 0.1242,
+      "step": 1212
+    },
+    {
+      "epoch": 2.246132532902332,
+      "grad_norm": 1.65625,
+      "learning_rate": 3.321990049076319e-06,
+      "loss": 0.1263,
+      "step": 1216
+    },
+    {
+      "epoch": 2.2535211267605635,
+      "grad_norm": 1.6171875,
+      "learning_rate": 3.260802105175195e-06,
+      "loss": 0.119,
+      "step": 1220
+    },
+    {
+      "epoch": 2.2609097206187947,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.200072963659221e-06,
+      "loss": 0.1244,
+      "step": 1224
+    },
+    {
+      "epoch": 2.268298314477026,
+      "grad_norm": 1.671875,
+      "learning_rate": 3.139806758948458e-06,
+      "loss": 0.1193,
+      "step": 1228
+    },
+    {
+      "epoch": 2.2756869083352576,
+      "grad_norm": 1.765625,
+      "learning_rate": 3.080007593946379e-06,
+      "loss": 0.1316,
+      "step": 1232
+    },
+    {
+      "epoch": 2.2830755021934888,
+      "grad_norm": 1.4921875,
+      "learning_rate": 3.020679539760555e-06,
+      "loss": 0.1216,
+      "step": 1236
+    },
+    {
+      "epoch": 2.29046409605172,
+      "grad_norm": 1.7265625,
+      "learning_rate": 2.9618266354254777e-06,
+      "loss": 0.1205,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2978526899099516,
+      "grad_norm": 1.46875,
+      "learning_rate": 2.9034528876275927e-06,
+      "loss": 0.1311,
+      "step": 1244
+    },
+    {
+      "epoch": 2.305241283768183,
+      "grad_norm": 1.7265625,
+      "learning_rate": 2.8455622704325383e-06,
+      "loss": 0.1276,
+      "step": 1248
+    },
+    {
+      "epoch": 2.312629877626414,
+      "grad_norm": 1.8046875,
+      "learning_rate": 2.788158725014559e-06,
+      "loss": 0.1258,
+      "step": 1252
+    },
+    {
+      "epoch": 2.3200184714846457,
+      "grad_norm": 1.53125,
+      "learning_rate": 2.7312461593882312e-06,
+      "loss": 0.1184,
+      "step": 1256
+    },
+    {
+      "epoch": 2.327407065342877,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.674828448142375e-06,
+      "loss": 0.124,
+      "step": 1260
+    },
+    {
+      "epoch": 2.334795659201108,
+      "grad_norm": 1.828125,
+      "learning_rate": 2.6189094321762997e-06,
+      "loss": 0.1186,
+      "step": 1264
+    },
+    {
+      "epoch": 2.3421842530593397,
+      "grad_norm": 1.6796875,
+      "learning_rate": 2.563492918438284e-06,
+      "loss": 0.116,
+      "step": 1268
+    },
+    {
+      "epoch": 2.349572846917571,
+      "grad_norm": 1.671875,
+      "learning_rate": 2.508582679666439e-06,
+      "loss": 0.1182,
+      "step": 1272
+    },
+    {
+      "epoch": 2.356961440775802,
+      "grad_norm": 1.734375,
+      "learning_rate": 2.4541824541318282e-06,
+      "loss": 0.1166,
+      "step": 1276
+    },
+    {
+      "epoch": 2.364350034634034,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.4002959453839936e-06,
+      "loss": 0.1211,
+      "step": 1280
+    },
+    {
+      "epoch": 2.371738628492265,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.3469268219987896e-06,
+      "loss": 0.1227,
+      "step": 1284
+    },
+    {
+      "epoch": 2.3791272223504962,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.2940787173286627e-06,
+      "loss": 0.128,
+      "step": 1288
+    },
+    {
+      "epoch": 2.386515816208728,
+      "grad_norm": 1.5390625,
+      "learning_rate": 2.2417552292552635e-06,
+      "loss": 0.1291,
+      "step": 1292
+    },
+    {
+      "epoch": 2.393904410066959,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.18995991994452e-06,
+      "loss": 0.1189,
+      "step": 1296
+    },
+    {
+      "epoch": 2.4012930039251903,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.1386963156041274e-06,
+      "loss": 0.1219,
+      "step": 1300
+    },
+    {
+      "epoch": 2.408681597783422,
+      "grad_norm": 1.75,
+      "learning_rate": 2.0879679062434745e-06,
+      "loss": 0.1255,
+      "step": 1304
+    },
+    {
+      "epoch": 2.416070191641653,
+      "grad_norm": 1.8671875,
+      "learning_rate": 2.0377781454360534e-06,
+      "loss": 0.1283,
+      "step": 1308
+    },
+    {
+      "epoch": 2.4234587854998844,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.988130450084339e-06,
+      "loss": 0.1238,
+      "step": 1312
+    },
+    {
+      "epoch": 2.430847379358116,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.939028200187173e-06,
+      "loss": 0.1201,
+      "step": 1316
+    },
+    {
+      "epoch": 2.438235973216347,
+      "grad_norm": 1.625,
+      "learning_rate": 1.8904747386096357e-06,
+      "loss": 0.1294,
+      "step": 1320
+    },
+    {
+      "epoch": 2.4456245670745784,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.8424733708554932e-06,
+      "loss": 0.1233,
+      "step": 1324
+    },
+    {
+      "epoch": 2.45301316093281,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.7950273648421347e-06,
+      "loss": 0.1229,
+      "step": 1328
+    },
+    {
+      "epoch": 2.4604017547910413,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.748139950678115e-06,
+      "loss": 0.1196,
+      "step": 1332
+    },
+    {
+      "epoch": 2.4677903486492725,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.7018143204432214e-06,
+      "loss": 0.1166,
+      "step": 1336
+    },
+    {
+      "epoch": 2.475178942507504,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.6560536279711937e-06,
+      "loss": 0.1262,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4825675363657354,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.6108609886349802e-06,
+      "loss": 0.1126,
+      "step": 1344
+    },
+    {
+      "epoch": 2.4899561302239666,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.5662394791346703e-06,
+      "loss": 0.1199,
+      "step": 1348
+    },
+    {
+      "epoch": 2.497344724082198,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.5221921372880056e-06,
+      "loss": 0.1308,
+      "step": 1352
+    },
+    {
+      "epoch": 2.5047333179404294,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.4787219618235982e-06,
+      "loss": 0.1263,
+      "step": 1356
+    },
+    {
+      "epoch": 2.512121911798661,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4358319121767495e-06,
+      "loss": 0.1295,
+      "step": 1360
+    },
+    {
+      "epoch": 2.5195105056568923,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.393524908287991e-06,
+      "loss": 0.1249,
+      "step": 1364
+    },
+    {
+      "epoch": 2.5268990995151235,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.3518038304042946e-06,
+      "loss": 0.1212,
+      "step": 1368
+    },
+    {
+      "epoch": 2.534287693373355,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.3106715188829666e-06,
+      "loss": 0.1163,
+      "step": 1372
+    },
+    {
+      "epoch": 2.5416762872315863,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.2701307739983093e-06,
+      "loss": 0.1145,
+      "step": 1376
+    },
+    {
+      "epoch": 2.5490648810898175,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.2301843557509495e-06,
+      "loss": 0.1242,
+      "step": 1380
+    },
+    {
+      "epoch": 2.556453474948049,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.1908349836799638e-06,
+      "loss": 0.1109,
+      "step": 1384
+    },
+    {
+      "epoch": 2.5638420688062804,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.152085336677704e-06,
+      "loss": 0.1256,
+      "step": 1388
+    },
+    {
+      "epoch": 2.5712306626645116,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.1139380528074528e-06,
+      "loss": 0.1256,
+      "step": 1392
+    },
+    {
+      "epoch": 2.5786192565227433,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.0763957291237948e-06,
+      "loss": 0.1268,
+      "step": 1396
+    },
+    {
+      "epoch": 2.5860078503809745,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.039460921495834e-06,
+      "loss": 0.1144,
+      "step": 1400
+    },
+    {
+      "epoch": 2.5933964442392057,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.00313614443317e-06,
+      "loss": 0.1215,
+      "step": 1404
+    },
+    {
+      "epoch": 2.6007850380974373,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.6742387091473e-07,
+      "loss": 0.1278,
+      "step": 1408
+    },
+    {
+      "epoch": 2.6081736319556685,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.323265322203934e-07,
+      "loss": 0.123,
+      "step": 1412
+    },
+    {
+      "epoch": 2.6155622258138997,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.97846517765486e-07,
+      "loss": 0.119,
+      "step": 1416
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 1.6796875,
+      "learning_rate": 8.639861749380962e-07,
+      "loss": 0.1142,
+      "step": 1420
+    },
+    {
+      "epoch": 2.6303394135303626,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.307478089392718e-07,
+      "loss": 0.1225,
+      "step": 1424
+    },
+    {
+      "epoch": 2.637728007388594,
+      "grad_norm": 1.6796875,
+      "learning_rate": 7.98133682626081e-07,
+      "loss": 0.1313,
+      "step": 1428
+    },
+    {
+      "epoch": 2.6451166012468255,
+      "grad_norm": 1.5859375,
+      "learning_rate": 7.661460163575607e-07,
+      "loss": 0.119,
+      "step": 1432
+    },
+    {
+      "epoch": 2.6525051951050567,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.347869878435554e-07,
+      "loss": 0.13,
+      "step": 1436
+    },
+    {
+      "epoch": 2.659893788963288,
+      "grad_norm": 1.7265625,
+      "learning_rate": 7.040587319964476e-07,
+      "loss": 0.1259,
+      "step": 1440
+    },
+    {
+      "epoch": 2.6672823828215195,
+      "grad_norm": 1.671875,
+      "learning_rate": 6.739633407858359e-07,
+      "loss": 0.1216,
+      "step": 1444
+    },
+    {
+      "epoch": 2.6746709766797507,
+      "grad_norm": 1.796875,
+      "learning_rate": 6.445028630960925e-07,
+      "loss": 0.1169,
+      "step": 1448
+    },
+    {
+      "epoch": 2.682059570537982,
+      "grad_norm": 1.5546875,
+      "learning_rate": 6.156793045868914e-07,
+      "loss": 0.1146,
+      "step": 1452
+    },
+    {
+      "epoch": 2.6894481643962136,
+      "grad_norm": 1.8125,
+      "learning_rate": 5.874946275566496e-07,
+      "loss": 0.1302,
+      "step": 1456
+    },
+    {
+      "epoch": 2.696836758254445,
+      "grad_norm": 1.5625,
+      "learning_rate": 5.599507508089508e-07,
+      "loss": 0.1178,
+      "step": 1460
+    },
+    {
+      "epoch": 2.704225352112676,
+      "grad_norm": 1.8046875,
+      "learning_rate": 5.33049549521899e-07,
+      "loss": 0.118,
+      "step": 1464
+    },
+    {
+      "epoch": 2.7116139459709077,
+      "grad_norm": 1.484375,
+      "learning_rate": 5.067928551204692e-07,
+      "loss": 0.1124,
+      "step": 1468
+    },
+    {
+      "epoch": 2.719002539829139,
+      "grad_norm": 1.59375,
+      "learning_rate": 4.811824551518141e-07,
+      "loss": 0.1259,
+      "step": 1472
+    },
+    {
+      "epoch": 2.72639113368737,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.5622009316357187e-07,
+      "loss": 0.12,
+      "step": 1476
+    },
+    {
+      "epoch": 2.7337797275456017,
+      "grad_norm": 1.875,
+      "learning_rate": 4.3190746858517317e-07,
+      "loss": 0.1299,
+      "step": 1480
+    },
+    {
+      "epoch": 2.741168321403833,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.0824623661213316e-07,
+      "loss": 0.1205,
+      "step": 1484
+    },
+    {
+      "epoch": 2.748556915262064,
+      "grad_norm": 1.828125,
+      "learning_rate": 3.8523800809337485e-07,
+      "loss": 0.1235,
+      "step": 1488
+    },
+    {
+      "epoch": 2.755945509120296,
+      "grad_norm": 1.640625,
+      "learning_rate": 3.628843494215595e-07,
+      "loss": 0.1149,
+      "step": 1492
+    },
+    {
+      "epoch": 2.763334102978527,
+      "grad_norm": 1.8125,
+      "learning_rate": 3.4118678242644697e-07,
+      "loss": 0.1228,
+      "step": 1496
+    },
+    {
+      "epoch": 2.770722696836758,
+      "grad_norm": 1.7890625,
+      "learning_rate": 3.201467842712902e-07,
+      "loss": 0.1225,
+      "step": 1500
+    },
+    {
+      "epoch": 2.77811129069499,
+      "grad_norm": 1.8203125,
+      "learning_rate": 2.99765787352273e-07,
+      "loss": 0.1192,
+      "step": 1504
+    },
+    {
+      "epoch": 2.785499884553221,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.8004517920098726e-07,
+      "loss": 0.1283,
+      "step": 1508
+    },
+    {
+      "epoch": 2.7928884784114523,
+      "grad_norm": 1.5546875,
+      "learning_rate": 2.6098630238997835e-07,
+      "loss": 0.1179,
+      "step": 1512
+    },
+    {
+      "epoch": 2.800277072269684,
+      "grad_norm": 1.765625,
+      "learning_rate": 2.425904544413349e-07,
+      "loss": 0.1164,
+      "step": 1516
+    },
+    {
+      "epoch": 2.807665666127915,
+      "grad_norm": 1.8359375,
+      "learning_rate": 2.2485888773836172e-07,
+      "loss": 0.1299,
+      "step": 1520
+    },
+    {
+      "epoch": 2.8150542599861463,
+      "grad_norm": 1.609375,
+      "learning_rate": 2.0779280944030812e-07,
+      "loss": 0.1215,
+      "step": 1524
+    },
+    {
+      "epoch": 2.822442853844378,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.9139338140019782e-07,
+      "loss": 0.1244,
+      "step": 1528
+    },
+    {
+      "epoch": 2.829831447702609,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.7566172008571692e-07,
+      "loss": 0.1172,
+      "step": 1532
+    },
+    {
+      "epoch": 2.8372200415608404,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.605988965032168e-07,
+      "loss": 0.1228,
+      "step": 1536
+    },
+    {
+      "epoch": 2.844608635419072,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.4620593612479361e-07,
+      "loss": 0.1129,
+      "step": 1540
+    },
+    {
+      "epoch": 2.8519972292773033,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.3248381881847294e-07,
+      "loss": 0.1259,
+      "step": 1544
+    },
+    {
+      "epoch": 2.8593858231355345,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.1943347878150658e-07,
+      "loss": 0.1233,
+      "step": 1548
+    },
+    {
+      "epoch": 2.866774416993766,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.0705580447676889e-07,
+      "loss": 0.1252,
+      "step": 1552
+    },
+    {
+      "epoch": 2.8741630108519973,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.535163857227525e-08,
+      "loss": 0.1219,
+      "step": 1556
+    },
+    {
+      "epoch": 2.8815516047102285,
+      "grad_norm": 1.7734375,
+      "learning_rate": 8.432177788380236e-08,
+      "loss": 0.1171,
+      "step": 1560
+    },
+    {
+      "epoch": 2.88894019856846,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.396697332065606e-08,
+      "loss": 0.1175,
+      "step": 1564
+    },
+    {
+      "epoch": 2.8963287924266914,
+      "grad_norm": 1.765625,
+      "learning_rate": 6.428792983453669e-08,
+      "loss": 0.1326,
+      "step": 1568
+    },
+    {
+      "epoch": 2.9037173862849226,
+      "grad_norm": 1.5390625,
+      "learning_rate": 5.528530637155749e-08,
+      "loss": 0.1088,
+      "step": 1572
+    },
+    {
+      "epoch": 2.9111059801431542,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.6959715827370464e-08,
+      "loss": 0.1195,
+      "step": 1576
+    },
+    {
+      "epoch": 2.9184945740013855,
+      "grad_norm": 1.8515625,
+      "learning_rate": 3.931172500545644e-08,
+      "loss": 0.1165,
+      "step": 1580
+    },
+    {
+      "epoch": 2.9258831678596167,
+      "grad_norm": 1.625,
+      "learning_rate": 3.234185457852368e-08,
+      "loss": 0.1211,
+      "step": 1584
+    },
+    {
+      "epoch": 2.9332717617178483,
+      "grad_norm": 1.6171875,
+      "learning_rate": 2.6050579053067403e-08,
+      "loss": 0.1153,
+      "step": 1588
+    },
+    {
+      "epoch": 2.9406603555760795,
+      "grad_norm": 1.5546875,
+      "learning_rate": 2.0438326737066695e-08,
+      "loss": 0.1173,
+      "step": 1592
+    },
+    {
+      "epoch": 2.9480489494343107,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.550547971081784e-08,
+      "loss": 0.1266,
+      "step": 1596
+    },
+    {
+      "epoch": 2.9554375432925424,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.1252373800932915e-08,
+      "loss": 0.1255,
+      "step": 1600
+    },
+    {
+      "epoch": 2.9628261371507736,
+      "grad_norm": 1.78125,
+      "learning_rate": 7.679298557468073e-09,
+      "loss": 0.1189,
+      "step": 1604
+    },
+    {
+      "epoch": 2.970214731009005,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.7864972342159814e-09,
+      "loss": 0.1232,
+      "step": 1608
+    },
+    {
+      "epoch": 2.9776033248672364,
+      "grad_norm": 1.6171875,
+      "learning_rate": 2.5741667721423948e-09,
+      "loss": 0.1102,
+      "step": 1612
+    },
+    {
+      "epoch": 2.9849919187254677,
+      "grad_norm": 1.625,
+      "learning_rate": 1.0424577859802222e-09,
+      "loss": 0.121,
+      "step": 1616
+    },
+    {
+      "epoch": 2.992380512583699,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.9147455397772185e-10,
+      "loss": 0.1198,
+      "step": 1620
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5921753493211185e+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 sha256:840367e8c92b2a0e10e8e82e133ab663c89d1d1accfd635f8673020a8200df93
+size 5432