Upload folder using huggingface_hub

checkpoint-12208/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-12208/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745a99cf63f2cbc7f5338621961d3d7e94002fd2289fe92bef2512c4df413b56
+size 4886466168

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fa5aaf8ac56c17c821980c9aee44fcbc2a617fc570e875e6fdb93d92886c72
+size 4832007448

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a223e87240e50dfb05634ea909cf1ec715d37a12b681b14a3a6e97f28688f2b
+size 4999813112

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3047d199c611c6d12b1cca780f033ad89df9c076f742674f7ac4a892ca9573b3
+size 4999813128

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2f91d749d664ecd22c71f3d54488966fc6899a03924b8fea3613c8f83398a8
+size 4832007496

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f2d8b8f0e65a8aa708d12594e9fb6ab68b0464ad926db206e465f78094fc19
+size 4999813120

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec219f3729c07bd285dfd1cb2dbbad45e04b293dbc2b6bf3af5189bed69a52f
+size 2571158184

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-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-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-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-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313be27f89af7b522c9e783b55d824a6ea19213f5e79cca816dfde5986c3564e
+size 15385036334

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.17628371743776353,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004476405013573615,
+      "grad_norm": 6.075733184814453,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.0566,
+      "step": 31
+    },
+    {
+      "epoch": 0.000895281002714723,
+      "grad_norm": 4.2440948486328125,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 0.9468,
+      "step": 62
+    },
+    {
+      "epoch": 0.0013429215040720846,
+      "grad_norm": 4.090479373931885,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 0.9075,
+      "step": 93
+    },
+    {
+      "epoch": 0.001790562005429446,
+      "grad_norm": 4.219390392303467,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 0.8884,
+      "step": 124
+    },
+    {
+      "epoch": 0.0022382025067868077,
+      "grad_norm": 4.051790237426758,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 0.8847,
+      "step": 155
+    },
+    {
+      "epoch": 0.002685843008144169,
+      "grad_norm": 3.5890421867370605,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.8729,
+      "step": 186
+    },
+    {
+      "epoch": 0.0031334835095015307,
+      "grad_norm": 4.262433052062988,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.8809,
+      "step": 217
+    },
+    {
+      "epoch": 0.003581124010858892,
+      "grad_norm": 3.98620343208313,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.8665,
+      "step": 248
+    },
+    {
+      "epoch": 0.004028764512216254,
+      "grad_norm": 3.7834768295288086,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.8628,
+      "step": 279
+    },
+    {
+      "epoch": 0.0044764050135736155,
+      "grad_norm": 4.5324506759643555,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.875,
+      "step": 310
+    },
+    {
+      "epoch": 0.0049240455149309765,
+      "grad_norm": 3.8203251361846924,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.8642,
+      "step": 341
+    },
+    {
+      "epoch": 0.005371686016288338,
+      "grad_norm": 4.361064434051514,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.8655,
+      "step": 372
+    },
+    {
+      "epoch": 0.005819326517645699,
+      "grad_norm": 3.2510569095611572,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.8494,
+      "step": 403
+    },
+    {
+      "epoch": 0.006266967019003061,
+      "grad_norm": 3.7586708068847656,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.8469,
+      "step": 434
+    },
+    {
+      "epoch": 0.006714607520360423,
+      "grad_norm": 3.5017266273498535,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.8615,
+      "step": 465
+    },
+    {
+      "epoch": 0.007162248021717784,
+      "grad_norm": 3.680084228515625,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.8471,
+      "step": 496
+    },
+    {
+      "epoch": 0.007609888523075146,
+      "grad_norm": 2.9426188468933105,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.8513,
+      "step": 527
+    },
+    {
+      "epoch": 0.008057529024432507,
+      "grad_norm": 3.8481788635253906,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.8435,
+      "step": 558
+    },
+    {
+      "epoch": 0.008505169525789868,
+      "grad_norm": 3.373544454574585,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.8446,
+      "step": 589
+    },
+    {
+      "epoch": 0.008952810027147231,
+      "grad_norm": 3.8154516220092773,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.8353,
+      "step": 620
+    },
+    {
+      "epoch": 0.009400450528504592,
+      "grad_norm": 4.436877727508545,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.8263,
+      "step": 651
+    },
+    {
+      "epoch": 0.009848091029861953,
+      "grad_norm": 3.512199640274048,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.8396,
+      "step": 682
+    },
+    {
+      "epoch": 0.010295731531219316,
+      "grad_norm": 3.8799757957458496,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.8312,
+      "step": 713
+    },
+    {
+      "epoch": 0.010743372032576677,
+      "grad_norm": 4.304780960083008,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.8201,
+      "step": 744
+    },
+    {
+      "epoch": 0.011191012533934038,
+      "grad_norm": 3.452643394470215,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.8306,
+      "step": 775
+    },
+    {
+      "epoch": 0.011638653035291399,
+      "grad_norm": 2.92769455909729,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.8218,
+      "step": 806
+    },
+    {
+      "epoch": 0.012086293536648762,
+      "grad_norm": 3.661085844039917,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.8273,
+      "step": 837
+    },
+    {
+      "epoch": 0.012533934038006123,
+      "grad_norm": 3.26717472076416,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.824,
+      "step": 868
+    },
+    {
+      "epoch": 0.012981574539363484,
+      "grad_norm": 3.8160181045532227,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.8193,
+      "step": 899
+    },
+    {
+      "epoch": 0.013429215040720846,
+      "grad_norm": 3.761385679244995,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.8156,
+      "step": 930
+    },
+    {
+      "epoch": 0.013876855542078207,
+      "grad_norm": 2.7427189350128174,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.8211,
+      "step": 961
+    },
+    {
+      "epoch": 0.014324496043435568,
+      "grad_norm": 2.2174184322357178,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.811,
+      "step": 992
+    },
+    {
+      "epoch": 0.01477213654479293,
+      "grad_norm": 2.678250312805176,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.8114,
+      "step": 1023
+    },
+    {
+      "epoch": 0.015219777046150292,
+      "grad_norm": 4.4316487312316895,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.8111,
+      "step": 1054
+    },
+    {
+      "epoch": 0.015667417547507653,
+      "grad_norm": 3.3831615447998047,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.8088,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016115058048865014,
+      "grad_norm": 3.7894206047058105,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.8187,
+      "step": 1116
+    },
+    {
+      "epoch": 0.016562698550222375,
+      "grad_norm": 2.4324352741241455,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.7968,
+      "step": 1147
+    },
+    {
+      "epoch": 0.017010339051579736,
+      "grad_norm": 3.6596791744232178,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.8064,
+      "step": 1178
+    },
+    {
+      "epoch": 0.0174579795529371,
+      "grad_norm": 2.322706460952759,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.7998,
+      "step": 1209
+    },
+    {
+      "epoch": 0.017905620054294462,
+      "grad_norm": 3.25221848487854,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.7999,
+      "step": 1240
+    },
+    {
+      "epoch": 0.018353260555651823,
+      "grad_norm": 2.626753807067871,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.7926,
+      "step": 1271
+    },
+    {
+      "epoch": 0.018800901057009184,
+      "grad_norm": 2.859938383102417,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.7938,
+      "step": 1302
+    },
+    {
+      "epoch": 0.019248541558366545,
+      "grad_norm": 2.6591029167175293,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.7913,
+      "step": 1333
+    },
+    {
+      "epoch": 0.019696182059723906,
+      "grad_norm": 3.4592838287353516,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.7873,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020143822561081267,
+      "grad_norm": 2.5634524822235107,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.7921,
+      "step": 1395
+    },
+    {
+      "epoch": 0.02059146306243863,
+      "grad_norm": 3.134092092514038,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.7968,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021039103563795993,
+      "grad_norm": 2.347602605819702,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.786,
+      "step": 1457
+    },
+    {
+      "epoch": 0.021486744065153354,
+      "grad_norm": 2.948688268661499,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.7935,
+      "step": 1488
+    },
+    {
+      "epoch": 0.021934384566510715,
+      "grad_norm": 2.1757874488830566,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.7786,
+      "step": 1519
+    },
+    {
+      "epoch": 0.022382025067868076,
+      "grad_norm": 2.951026439666748,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.7778,
+      "step": 1550
+    },
+    {
+      "epoch": 0.022829665569225437,
+      "grad_norm": 3.962952136993408,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.7873,
+      "step": 1581
+    },
+    {
+      "epoch": 0.023277306070582798,
+      "grad_norm": 3.359558343887329,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.7774,
+      "step": 1612
+    },
+    {
+      "epoch": 0.023724946571940162,
+      "grad_norm": 2.9352834224700928,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.7733,
+      "step": 1643
+    },
+    {
+      "epoch": 0.024172587073297523,
+      "grad_norm": 3.6340250968933105,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.7738,
+      "step": 1674
+    },
+    {
+      "epoch": 0.024620227574654884,
+      "grad_norm": 2.717247724533081,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.7737,
+      "step": 1705
+    },
+    {
+      "epoch": 0.025067868076012245,
+      "grad_norm": 3.018810510635376,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.7824,
+      "step": 1736
+    },
+    {
+      "epoch": 0.025515508577369606,
+      "grad_norm": 2.2435100078582764,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.7726,
+      "step": 1767
+    },
+    {
+      "epoch": 0.025963149078726967,
+      "grad_norm": 3.1678667068481445,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.7749,
+      "step": 1798
+    },
+    {
+      "epoch": 0.02641078958008433,
+      "grad_norm": 2.422478675842285,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.7656,
+      "step": 1829
+    },
+    {
+      "epoch": 0.026858430081441693,
+      "grad_norm": 2.430635929107666,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.77,
+      "step": 1860
+    },
+    {
+      "epoch": 0.027306070582799054,
+      "grad_norm": 2.199424982070923,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.7596,
+      "step": 1891
+    },
+    {
+      "epoch": 0.027753711084156415,
+      "grad_norm": 2.752176284790039,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.7723,
+      "step": 1922
+    },
+    {
+      "epoch": 0.028201351585513776,
+      "grad_norm": 2.764007568359375,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.7604,
+      "step": 1953
+    },
+    {
+      "epoch": 0.028648992086871137,
+      "grad_norm": 2.045133590698242,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.7714,
+      "step": 1984
+    },
+    {
+      "epoch": 0.029096632588228498,
+      "grad_norm": 3.263131856918335,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.7577,
+      "step": 2015
+    },
+    {
+      "epoch": 0.02954427308958586,
+      "grad_norm": 2.2480087280273438,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.7543,
+      "step": 2046
+    },
+    {
+      "epoch": 0.029991913590943223,
+      "grad_norm": 2.9011387825012207,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.7568,
+      "step": 2077
+    },
+    {
+      "epoch": 0.030439554092300584,
+      "grad_norm": 2.7179999351501465,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.7489,
+      "step": 2108
+    },
+    {
+      "epoch": 0.030887194593657945,
+      "grad_norm": 3.0504350662231445,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.7598,
+      "step": 2139
+    },
+    {
+      "epoch": 0.031334835095015307,
+      "grad_norm": 2.9903855323791504,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.7509,
+      "step": 2170
+    },
+    {
+      "epoch": 0.03178247559637267,
+      "grad_norm": 1.9252121448516846,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.7327,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03223011609773003,
+      "grad_norm": 2.261479139328003,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.7596,
+      "step": 2232
+    },
+    {
+      "epoch": 0.03267775659908739,
+      "grad_norm": 2.475863218307495,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.7566,
+      "step": 2263
+    },
+    {
+      "epoch": 0.03312539710044475,
+      "grad_norm": 1.7898969650268555,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.753,
+      "step": 2294
+    },
+    {
+      "epoch": 0.033573037601802115,
+      "grad_norm": 2.8534107208251953,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.7449,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03402067810315947,
+      "grad_norm": 2.765749454498291,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.7357,
+      "step": 2356
+    },
+    {
+      "epoch": 0.03446831860451684,
+      "grad_norm": 1.8090626001358032,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.736,
+      "step": 2387
+    },
+    {
+      "epoch": 0.0349159591058742,
+      "grad_norm": 1.6179667711257935,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.7399,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03536359960723156,
+      "grad_norm": 3.8357365131378174,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.748,
+      "step": 2449
+    },
+    {
+      "epoch": 0.035811240108588924,
+      "grad_norm": 1.7962925434112549,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.7339,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03625888060994628,
+      "grad_norm": 2.528853178024292,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.7387,
+      "step": 2511
+    },
+    {
+      "epoch": 0.036706521111303646,
+      "grad_norm": 2.2113044261932373,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.7414,
+      "step": 2542
+    },
+    {
+      "epoch": 0.037154161612661,
+      "grad_norm": 1.895753264427185,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.7307,
+      "step": 2573
+    },
+    {
+      "epoch": 0.03760180211401837,
+      "grad_norm": 2.3641865253448486,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.7373,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03804944261537573,
+      "grad_norm": 2.4185962677001953,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.7207,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03849708311673309,
+      "grad_norm": 1.8405852317810059,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.7331,
+      "step": 2666
+    },
+    {
+      "epoch": 0.038944723618090454,
+      "grad_norm": 2.796203136444092,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.7312,
+      "step": 2697
+    },
+    {
+      "epoch": 0.03939236411944781,
+      "grad_norm": 2.0833380222320557,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.7396,
+      "step": 2728
+    },
+    {
+      "epoch": 0.039840004620805176,
+      "grad_norm": 3.2164361476898193,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.731,
+      "step": 2759
+    },
+    {
+      "epoch": 0.040287645122162534,
+      "grad_norm": 3.1149556636810303,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.7291,
+      "step": 2790
+    },
+    {
+      "epoch": 0.0407352856235199,
+      "grad_norm": 2.1158149242401123,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7314,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04118292612487726,
+      "grad_norm": 1.573134422302246,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.722,
+      "step": 2852
+    },
+    {
+      "epoch": 0.04163056662623462,
+      "grad_norm": 2.4656667709350586,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.7376,
+      "step": 2883
+    },
+    {
+      "epoch": 0.042078207127591985,
+      "grad_norm": 2.0156564712524414,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.7261,
+      "step": 2914
+    },
+    {
+      "epoch": 0.04252584762894934,
+      "grad_norm": 1.8054187297821045,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.7318,
+      "step": 2945
+    },
+    {
+      "epoch": 0.04297348813030671,
+      "grad_norm": 2.247424602508545,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.7252,
+      "step": 2976
+    },
+    {
+      "epoch": 0.043421128631664065,
+      "grad_norm": 2.238030195236206,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.7263,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04386876913302143,
+      "grad_norm": 2.017012357711792,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.725,
+      "step": 3038
+    },
+    {
+      "epoch": 0.044316409634378794,
+      "grad_norm": 1.7042877674102783,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.7187,
+      "step": 3069
+    },
+    {
+      "epoch": 0.04476405013573615,
+      "grad_norm": 2.4380805492401123,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7318,
+      "step": 3100
+    },
+    {
+      "epoch": 0.045211690637093516,
+      "grad_norm": 2.590555191040039,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.7213,
+      "step": 3131
+    },
+    {
+      "epoch": 0.04565933113845087,
+      "grad_norm": 1.5544863939285278,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.7179,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04610697163980824,
+      "grad_norm": 2.105193614959717,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.7177,
+      "step": 3193
+    },
+    {
+      "epoch": 0.046554612141165595,
+      "grad_norm": 2.108760356903076,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.724,
+      "step": 3224
+    },
+    {
+      "epoch": 0.04700225264252296,
+      "grad_norm": 3.2209384441375732,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7285,
+      "step": 3255
+    },
+    {
+      "epoch": 0.047449893143880324,
+      "grad_norm": 1.7396947145462036,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7189,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04789753364523768,
+      "grad_norm": 1.815233826637268,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.718,
+      "step": 3317
+    },
+    {
+      "epoch": 0.048345174146595046,
+      "grad_norm": 2.3554177284240723,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7145,
+      "step": 3348
+    },
+    {
+      "epoch": 0.048792814647952404,
+      "grad_norm": 2.7524783611297607,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7198,
+      "step": 3379
+    },
+    {
+      "epoch": 0.04924045514930977,
+      "grad_norm": 2.151045322418213,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7085,
+      "step": 3410
+    },
+    {
+      "epoch": 0.049688095650667126,
+      "grad_norm": 2.099945306777954,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.7059,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05013573615202449,
+      "grad_norm": 2.2688772678375244,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7071,
+      "step": 3472
+    },
+    {
+      "epoch": 0.050583376653381855,
+      "grad_norm": 1.9718475341796875,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7064,
+      "step": 3503
+    },
+    {
+      "epoch": 0.05103101715473921,
+      "grad_norm": 1.8137073516845703,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7049,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05147865765609658,
+      "grad_norm": 3.5721960067749023,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7171,
+      "step": 3565
+    },
+    {
+      "epoch": 0.051926298157453935,
+      "grad_norm": 2.6050193309783936,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.7081,
+      "step": 3596
+    },
+    {
+      "epoch": 0.0523739386588113,
+      "grad_norm": 1.6417428255081177,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7101,
+      "step": 3627
+    },
+    {
+      "epoch": 0.05282157916016866,
+      "grad_norm": 2.1848113536834717,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7026,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05326921966152602,
+      "grad_norm": 1.8033145666122437,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7045,
+      "step": 3689
+    },
+    {
+      "epoch": 0.053716860162883386,
+      "grad_norm": 1.6396067142486572,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7011,
+      "step": 3720
+    },
+    {
+      "epoch": 0.05416450066424074,
+      "grad_norm": 1.7694982290267944,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7081,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05461214116559811,
+      "grad_norm": 3.1106865406036377,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7054,
+      "step": 3782
+    },
+    {
+      "epoch": 0.055059781666955465,
+      "grad_norm": 2.4519076347351074,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.697,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05550742216831283,
+      "grad_norm": 2.0600473880767822,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7106,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05595506266967019,
+      "grad_norm": 2.4080190658569336,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.6965,
+      "step": 3875
+    },
+    {
+      "epoch": 0.05640270317102755,
+      "grad_norm": 2.3117220401763916,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.6968,
+      "step": 3906
+    },
+    {
+      "epoch": 0.056850343672384916,
+      "grad_norm": 2.364525318145752,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7037,
+      "step": 3937
+    },
+    {
+      "epoch": 0.057297984173742274,
+      "grad_norm": 1.6029551029205322,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.6971,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05774562467509964,
+      "grad_norm": 2.7199840545654297,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.6979,
+      "step": 3999
+    },
+    {
+      "epoch": 0.058193265176456996,
+      "grad_norm": 2.0529887676239014,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.697,
+      "step": 4030
+    },
+    {
+      "epoch": 0.05864090567781436,
+      "grad_norm": 2.0358359813690186,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7008,
+      "step": 4061
+    },
+    {
+      "epoch": 0.05908854617917172,
+      "grad_norm": 2.069599151611328,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.7075,
+      "step": 4092
+    },
+    {
+      "epoch": 0.05953618668052908,
+      "grad_norm": 3.084198236465454,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7067,
+      "step": 4123
+    },
+    {
+      "epoch": 0.05998382718188645,
+      "grad_norm": 1.7525622844696045,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7049,
+      "step": 4154
+    },
+    {
+      "epoch": 0.060431467683243804,
+      "grad_norm": 1.757623553276062,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7019,
+      "step": 4185
+    },
+    {
+      "epoch": 0.06087910818460117,
+      "grad_norm": 2.1729736328125,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.6991,
+      "step": 4216
+    },
+    {
+      "epoch": 0.061326748685958526,
+      "grad_norm": 1.9989466667175293,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7014,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06177438918731589,
+      "grad_norm": 2.2553014755249023,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7064,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06222202968867325,
+      "grad_norm": 2.462275743484497,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.6945,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06266967019003061,
+      "grad_norm": 2.624544382095337,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.6992,
+      "step": 4340
+    },
+    {
+      "epoch": 0.06311731069138797,
+      "grad_norm": 1.2823548316955566,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.6905,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06356495119274534,
+      "grad_norm": 2.2118582725524902,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.6969,
+      "step": 4402
+    },
+    {
+      "epoch": 0.0640125916941027,
+      "grad_norm": 2.3164892196655273,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.6848,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06446023219546006,
+      "grad_norm": 1.6639585494995117,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.6883,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06490787269681741,
+      "grad_norm": 1.915570855140686,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.6929,
+      "step": 4495
+    },
+    {
+      "epoch": 0.06535551319817479,
+      "grad_norm": 1.8555858135223389,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.6952,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06580315369953214,
+      "grad_norm": 2.1268434524536133,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.6908,
+      "step": 4557
+    },
+    {
+      "epoch": 0.0662507942008895,
+      "grad_norm": 2.199445962905884,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.6919,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06669843470224687,
+      "grad_norm": 1.9284214973449707,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.6932,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06714607520360423,
+      "grad_norm": 2.8380227088928223,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.6858,
+      "step": 4650
+    },
+    {
+      "epoch": 0.06759371570496159,
+      "grad_norm": 2.0919442176818848,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.6913,
+      "step": 4681
+    },
+    {
+      "epoch": 0.06804135620631895,
+      "grad_norm": 2.1968653202056885,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.691,
+      "step": 4712
+    },
+    {
+      "epoch": 0.06848899670767632,
+      "grad_norm": 1.9843740463256836,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.6904,
+      "step": 4743
+    },
+    {
+      "epoch": 0.06893663720903367,
+      "grad_norm": 2.016184091567993,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.6916,
+      "step": 4774
+    },
+    {
+      "epoch": 0.06938427771039103,
+      "grad_norm": 1.797019124031067,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.6931,
+      "step": 4805
+    },
+    {
+      "epoch": 0.0698319182117484,
+      "grad_norm": 1.433285117149353,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.6809,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07027955871310576,
+      "grad_norm": 1.4553332328796387,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.6995,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07072719921446312,
+      "grad_norm": 2.220764636993408,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.6807,
+      "step": 4898
+    },
+    {
+      "epoch": 0.07117483971582048,
+      "grad_norm": 1.9182664155960083,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.6834,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07162248021717785,
+      "grad_norm": 1.5292731523513794,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.6795,
+      "step": 4960
+    },
+    {
+      "epoch": 0.0720701207185352,
+      "grad_norm": 1.618630051612854,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.6829,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07251776121989256,
+      "grad_norm": 2.463080644607544,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.6867,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07296540172124993,
+      "grad_norm": 2.0314955711364746,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.6914,
+      "step": 5053
+    },
+    {
+      "epoch": 0.07341304222260729,
+      "grad_norm": 2.511078119277954,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.6838,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07386068272396465,
+      "grad_norm": 1.8808708190917969,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.6842,
+      "step": 5115
+    },
+    {
+      "epoch": 0.074308323225322,
+      "grad_norm": 1.6079555749893188,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.6828,
+      "step": 5146
+    },
+    {
+      "epoch": 0.07475596372667938,
+      "grad_norm": 1.607474446296692,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.69,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07520360422803674,
+      "grad_norm": 2.38283371925354,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.6877,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0756512447293941,
+      "grad_norm": 2.5603227615356445,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.6824,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07609888523075146,
+      "grad_norm": 2.540479898452759,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.6787,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07654652573210882,
+      "grad_norm": 1.7890712022781372,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.6779,
+      "step": 5301
+    },
+    {
+      "epoch": 0.07699416623346618,
+      "grad_norm": 2.279125213623047,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.6783,
+      "step": 5332
+    },
+    {
+      "epoch": 0.07744180673482354,
+      "grad_norm": 1.6013977527618408,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.6774,
+      "step": 5363
+    },
+    {
+      "epoch": 0.07788944723618091,
+      "grad_norm": 1.2730411291122437,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.6811,
+      "step": 5394
+    },
+    {
+      "epoch": 0.07833708773753827,
+      "grad_norm": 1.764948844909668,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.6771,
+      "step": 5425
+    },
+    {
+      "epoch": 0.07878472823889562,
+      "grad_norm": 1.6873563528060913,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.701,
+      "step": 5456
+    },
+    {
+      "epoch": 0.079232368740253,
+      "grad_norm": 2.386568069458008,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.6785,
+      "step": 5487
+    },
+    {
+      "epoch": 0.07968000924161035,
+      "grad_norm": 1.3919615745544434,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.6808,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08012764974296771,
+      "grad_norm": 2.006275177001953,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.6713,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08057529024432507,
+      "grad_norm": 1.995177149772644,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.6744,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08102293074568244,
+      "grad_norm": 1.4058161973953247,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.67,
+      "step": 5611
+    },
+    {
+      "epoch": 0.0814705712470398,
+      "grad_norm": 2.0186007022857666,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.6647,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08191821174839715,
+      "grad_norm": 1.7829797267913818,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.6786,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08236585224975453,
+      "grad_norm": 2.12453556060791,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.6824,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08281349275111188,
+      "grad_norm": 1.557865023612976,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.6847,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08326113325246924,
+      "grad_norm": 2.1795268058776855,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.67,
+      "step": 5766
+    },
+    {
+      "epoch": 0.0837087737538266,
+      "grad_norm": 2.0731284618377686,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.6827,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08415641425518397,
+      "grad_norm": 1.54974365234375,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.6757,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08460405475654133,
+      "grad_norm": 1.7679517269134521,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.6673,
+      "step": 5859
+    },
+    {
+      "epoch": 0.08505169525789869,
+      "grad_norm": 2.4018664360046387,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.6751,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08549933575925606,
+      "grad_norm": 2.198348045349121,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.6771,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08594697626061341,
+      "grad_norm": 2.421766996383667,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.6825,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08639461676197077,
+      "grad_norm": 1.5196090936660767,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.6734,
+      "step": 5983
+    },
+    {
+      "epoch": 0.08684225726332813,
+      "grad_norm": 1.947550892829895,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.671,
+      "step": 6014
+    },
+    {
+      "epoch": 0.0872898977646855,
+      "grad_norm": 1.999944806098938,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.673,
+      "step": 6045
+    },
+    {
+      "epoch": 0.08773753826604286,
+      "grad_norm": 2.322126626968384,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.6758,
+      "step": 6076
+    },
+    {
+      "epoch": 0.08818517876740022,
+      "grad_norm": 1.4106264114379883,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.6685,
+      "step": 6107
+    },
+    {
+      "epoch": 0.08863281926875759,
+      "grad_norm": 2.846497058868408,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.6664,
+      "step": 6138
+    },
+    {
+      "epoch": 0.08908045977011494,
+      "grad_norm": 1.5854451656341553,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.6696,
+      "step": 6169
+    },
+    {
+      "epoch": 0.0895281002714723,
+      "grad_norm": 1.4877409934997559,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.6824,
+      "step": 6200
+    },
+    {
+      "epoch": 0.08997574077282966,
+      "grad_norm": 2.564678907394409,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.6743,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09042338127418703,
+      "grad_norm": 1.6551730632781982,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.6688,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09087102177554439,
+      "grad_norm": 1.542798638343811,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.6732,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09131866227690175,
+      "grad_norm": 1.8403035402297974,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.6812,
+      "step": 6324
+    },
+    {
+      "epoch": 0.09176630277825912,
+      "grad_norm": 1.7633146047592163,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.6738,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09221394327961648,
+      "grad_norm": 1.353498101234436,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.6732,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09266158378097383,
+      "grad_norm": 2.0140905380249023,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.6795,
+      "step": 6417
+    },
+    {
+      "epoch": 0.09310922428233119,
+      "grad_norm": 1.9759689569473267,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.678,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09355686478368856,
+      "grad_norm": 1.9719219207763672,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.6633,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09400450528504592,
+      "grad_norm": 1.7268098592758179,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.6675,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09445214578640328,
+      "grad_norm": 2.3125104904174805,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.6688,
+      "step": 6541
+    },
+    {
+      "epoch": 0.09489978628776065,
+      "grad_norm": 3.1883366107940674,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.6708,
+      "step": 6572
+    },
+    {
+      "epoch": 0.095347426789118,
+      "grad_norm": 1.3998332023620605,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.6692,
+      "step": 6603
+    },
+    {
+      "epoch": 0.09579506729047536,
+      "grad_norm": 1.2298917770385742,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.6679,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09624270779183272,
+      "grad_norm": 1.4910554885864258,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.6663,
+      "step": 6665
+    },
+    {
+      "epoch": 0.09669034829319009,
+      "grad_norm": 1.5662206411361694,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.6677,
+      "step": 6696
+    },
+    {
+      "epoch": 0.09713798879454745,
+      "grad_norm": 1.3008075952529907,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.6663,
+      "step": 6727
+    },
+    {
+      "epoch": 0.09758562929590481,
+      "grad_norm": 2.1645631790161133,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.6758,
+      "step": 6758
+    },
+    {
+      "epoch": 0.09803326979726218,
+      "grad_norm": 1.4836088418960571,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.667,
+      "step": 6789
+    },
+    {
+      "epoch": 0.09848091029861954,
+      "grad_norm": 1.49858820438385,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.6716,
+      "step": 6820
+    },
+    {
+      "epoch": 0.0989285507999769,
+      "grad_norm": 2.0113542079925537,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.6629,
+      "step": 6851
+    },
+    {
+      "epoch": 0.09937619130133425,
+      "grad_norm": 1.1643431186676025,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.6672,
+      "step": 6882
+    },
+    {
+      "epoch": 0.09982383180269162,
+      "grad_norm": 1.825980544090271,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.6674,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10027147230404898,
+      "grad_norm": 1.2358912229537964,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.6596,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10071911280540634,
+      "grad_norm": 2.1445295810699463,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.665,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10116675330676371,
+      "grad_norm": 1.7739466428756714,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.669,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10161439380812107,
+      "grad_norm": 1.4754871129989624,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.657,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10206203430947842,
+      "grad_norm": 1.5860286951065063,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.6672,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10250967481083578,
+      "grad_norm": 1.3789246082305908,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.6664,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10295731531219315,
+      "grad_norm": 1.6928731203079224,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.6629,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10340495581355051,
+      "grad_norm": 1.5635676383972168,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.6656,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10385259631490787,
+      "grad_norm": 1.3450698852539062,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.6637,
+      "step": 7192
+    },
+    {
+      "epoch": 0.10430023681626524,
+      "grad_norm": 1.955698847770691,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.6638,
+      "step": 7223
+    },
+    {
+      "epoch": 0.1047478773176226,
+      "grad_norm": 2.6813876628875732,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.6661,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10519551781897996,
+      "grad_norm": 1.7577868700027466,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.6579,
+      "step": 7285
+    },
+    {
+      "epoch": 0.10564315832033731,
+      "grad_norm": 1.3784778118133545,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.6677,
+      "step": 7316
+    },
+    {
+      "epoch": 0.10609079882169468,
+      "grad_norm": 1.690073847770691,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.6606,
+      "step": 7347
+    },
+    {
+      "epoch": 0.10653843932305204,
+      "grad_norm": 1.9649986028671265,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.6701,
+      "step": 7378
+    },
+    {
+      "epoch": 0.1069860798244094,
+      "grad_norm": 1.6628475189208984,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.659,
+      "step": 7409
+    },
+    {
+      "epoch": 0.10743372032576677,
+      "grad_norm": 1.4179651737213135,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.6568,
+      "step": 7440
+    },
+    {
+      "epoch": 0.10788136082712413,
+      "grad_norm": 2.3137412071228027,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.6615,
+      "step": 7471
+    },
+    {
+      "epoch": 0.10832900132848149,
+      "grad_norm": 2.24027156829834,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.6526,
+      "step": 7502
+    },
+    {
+      "epoch": 0.10877664182983884,
+      "grad_norm": 3.1159045696258545,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.6675,
+      "step": 7533
+    },
+    {
+      "epoch": 0.10922428233119622,
+      "grad_norm": 1.8783204555511475,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.6602,
+      "step": 7564
+    },
+    {
+      "epoch": 0.10967192283255357,
+      "grad_norm": 16.97314453125,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.6592,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11011956333391093,
+      "grad_norm": 2.2325730323791504,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.6516,
+      "step": 7626
+    },
+    {
+      "epoch": 0.1105672038352683,
+      "grad_norm": 1.4192359447479248,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.6582,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11101484433662566,
+      "grad_norm": 1.3031502962112427,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.6642,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11146248483798302,
+      "grad_norm": 1.3589367866516113,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.6567,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11191012533934037,
+      "grad_norm": 1.380942463874817,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.6566,
+      "step": 7750
+    },
+    {
+      "epoch": 0.11235776584069775,
+      "grad_norm": 1.7768518924713135,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.6649,
+      "step": 7781
+    },
+    {
+      "epoch": 0.1128054063420551,
+      "grad_norm": 1.8216607570648193,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.6681,
+      "step": 7812
+    },
+    {
+      "epoch": 0.11325304684341246,
+      "grad_norm": 1.8983733654022217,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.6531,
+      "step": 7843
+    },
+    {
+      "epoch": 0.11370068734476983,
+      "grad_norm": 1.8444031476974487,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.6607,
+      "step": 7874
+    },
+    {
+      "epoch": 0.11414832784612719,
+      "grad_norm": 2.833496332168579,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.6504,
+      "step": 7905
+    },
+    {
+      "epoch": 0.11459596834748455,
+      "grad_norm": 1.5405519008636475,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.6563,
+      "step": 7936
+    },
+    {
+      "epoch": 0.1150436088488419,
+      "grad_norm": 1.1646043062210083,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.6436,
+      "step": 7967
+    },
+    {
+      "epoch": 0.11549124935019928,
+      "grad_norm": 1.9327855110168457,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.6592,
+      "step": 7998
+    },
+    {
+      "epoch": 0.11593888985155663,
+      "grad_norm": 1.5157870054244995,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.6532,
+      "step": 8029
+    },
+    {
+      "epoch": 0.11638653035291399,
+      "grad_norm": 2.015371084213257,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.6571,
+      "step": 8060
+    },
+    {
+      "epoch": 0.11683417085427136,
+      "grad_norm": 1.4756910800933838,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.6516,
+      "step": 8091
+    },
+    {
+      "epoch": 0.11728181135562872,
+      "grad_norm": 3.0601749420166016,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.6695,
+      "step": 8122
+    },
+    {
+      "epoch": 0.11772945185698608,
+      "grad_norm": 1.9742850065231323,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.6515,
+      "step": 8153
+    },
+    {
+      "epoch": 0.11817709235834344,
+      "grad_norm": 2.2514753341674805,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.6523,
+      "step": 8184
+    },
+    {
+      "epoch": 0.11862473285970081,
+      "grad_norm": 1.3582695722579956,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.6551,
+      "step": 8215
+    },
+    {
+      "epoch": 0.11907237336105816,
+      "grad_norm": 1.1863290071487427,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.6564,
+      "step": 8246
+    },
+    {
+      "epoch": 0.11952001386241552,
+      "grad_norm": 1.2964929342269897,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.6579,
+      "step": 8277
+    },
+    {
+      "epoch": 0.1199676543637729,
+      "grad_norm": 1.5999125242233276,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.6561,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12041529486513025,
+      "grad_norm": 1.6672707796096802,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.6612,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12086293536648761,
+      "grad_norm": 1.6736791133880615,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.666,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12131057586784497,
+      "grad_norm": 1.5894031524658203,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.6611,
+      "step": 8401
+    },
+    {
+      "epoch": 0.12175821636920234,
+      "grad_norm": 1.459932565689087,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.6557,
+      "step": 8432
+    },
+    {
+      "epoch": 0.1222058568705597,
+      "grad_norm": 2.244842767715454,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.6611,
+      "step": 8463
+    },
+    {
+      "epoch": 0.12265349737191705,
+      "grad_norm": 1.4417616128921509,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.6546,
+      "step": 8494
+    },
+    {
+      "epoch": 0.12310113787327442,
+      "grad_norm": 1.7080905437469482,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.6526,
+      "step": 8525
+    },
+    {
+      "epoch": 0.12354877837463178,
+      "grad_norm": 1.9203237295150757,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.6523,
+      "step": 8556
+    },
+    {
+      "epoch": 0.12399641887598914,
+      "grad_norm": 1.6014002561569214,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.6515,
+      "step": 8587
+    },
+    {
+      "epoch": 0.1244440593773465,
+      "grad_norm": 1.4305850267410278,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.6499,
+      "step": 8618
+    },
+    {
+      "epoch": 0.12489169987870387,
+      "grad_norm": 1.7838248014450073,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.6449,
+      "step": 8649
+    },
+    {
+      "epoch": 0.12533934038006123,
+      "grad_norm": 1.8731306791305542,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.6538,
+      "step": 8680
+    },
+    {
+      "epoch": 0.1257869808814186,
+      "grad_norm": 2.0666420459747314,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.653,
+      "step": 8711
+    },
+    {
+      "epoch": 0.12623462138277594,
+      "grad_norm": 1.7400550842285156,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.649,
+      "step": 8742
+    },
+    {
+      "epoch": 0.1266822618841333,
+      "grad_norm": 1.6730947494506836,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.6569,
+      "step": 8773
+    },
+    {
+      "epoch": 0.12712990238549068,
+      "grad_norm": 1.2559434175491333,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.6479,
+      "step": 8804
+    },
+    {
+      "epoch": 0.12757754288684803,
+      "grad_norm": 1.5398365259170532,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.6485,
+      "step": 8835
+    },
+    {
+      "epoch": 0.1280251833882054,
+      "grad_norm": 2.1256911754608154,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.6457,
+      "step": 8866
+    },
+    {
+      "epoch": 0.12847282388956274,
+      "grad_norm": 1.4803603887557983,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.6508,
+      "step": 8897
+    },
+    {
+      "epoch": 0.12892046439092011,
+      "grad_norm": 1.5118730068206787,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.6503,
+      "step": 8928
+    },
+    {
+      "epoch": 0.12936810489227749,
+      "grad_norm": 1.1825127601623535,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.663,
+      "step": 8959
+    },
+    {
+      "epoch": 0.12981574539363483,
+      "grad_norm": 1.358410120010376,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.6493,
+      "step": 8990
+    },
+    {
+      "epoch": 0.1302633858949922,
+      "grad_norm": 1.8535338640213013,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.6502,
+      "step": 9021
+    },
+    {
+      "epoch": 0.13071102639634957,
+      "grad_norm": 1.7688425779342651,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.6504,
+      "step": 9052
+    },
+    {
+      "epoch": 0.13115866689770692,
+      "grad_norm": 1.4369934797286987,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.6587,
+      "step": 9083
+    },
+    {
+      "epoch": 0.1316063073990643,
+      "grad_norm": 1.590460181236267,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.6406,
+      "step": 9114
+    },
+    {
+      "epoch": 0.13205394790042166,
+      "grad_norm": 1.0730258226394653,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.6527,
+      "step": 9145
+    },
+    {
+      "epoch": 0.132501588401779,
+      "grad_norm": 1.6859849691390991,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.6492,
+      "step": 9176
+    },
+    {
+      "epoch": 0.13294922890313637,
+      "grad_norm": 1.9398038387298584,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.6471,
+      "step": 9207
+    },
+    {
+      "epoch": 0.13339686940449375,
+      "grad_norm": 1.5931581258773804,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.6516,
+      "step": 9238
+    },
+    {
+      "epoch": 0.1338445099058511,
+      "grad_norm": 1.2483857870101929,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.6458,
+      "step": 9269
+    },
+    {
+      "epoch": 0.13429215040720846,
+      "grad_norm": 1.2097086906433105,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.6491,
+      "step": 9300
+    },
+    {
+      "epoch": 0.1347397909085658,
+      "grad_norm": 1.2975740432739258,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.6476,
+      "step": 9331
+    },
+    {
+      "epoch": 0.13518743140992318,
+      "grad_norm": 1.474465012550354,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.6494,
+      "step": 9362
+    },
+    {
+      "epoch": 0.13563507191128055,
+      "grad_norm": 1.455447793006897,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.6461,
+      "step": 9393
+    },
+    {
+      "epoch": 0.1360827124126379,
+      "grad_norm": 1.806460976600647,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.6477,
+      "step": 9424
+    },
+    {
+      "epoch": 0.13653035291399526,
+      "grad_norm": 1.3280959129333496,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.6571,
+      "step": 9455
+    },
+    {
+      "epoch": 0.13697799341535263,
+      "grad_norm": 1.6380054950714111,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.6495,
+      "step": 9486
+    },
+    {
+      "epoch": 0.13742563391670998,
+      "grad_norm": 1.35837984085083,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.6473,
+      "step": 9517
+    },
+    {
+      "epoch": 0.13787327441806735,
+      "grad_norm": 1.2885377407073975,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.648,
+      "step": 9548
+    },
+    {
+      "epoch": 0.13832091491942472,
+      "grad_norm": 1.2592779397964478,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.648,
+      "step": 9579
+    },
+    {
+      "epoch": 0.13876855542078206,
+      "grad_norm": 1.4869375228881836,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.6437,
+      "step": 9610
+    },
+    {
+      "epoch": 0.13921619592213944,
+      "grad_norm": 1.3101277351379395,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.6429,
+      "step": 9641
+    },
+    {
+      "epoch": 0.1396638364234968,
+      "grad_norm": 1.488227367401123,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.651,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14011147692485415,
+      "grad_norm": 1.394073486328125,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.6437,
+      "step": 9703
+    },
+    {
+      "epoch": 0.14055911742621152,
+      "grad_norm": 1.8128383159637451,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.6494,
+      "step": 9734
+    },
+    {
+      "epoch": 0.14100675792756887,
+      "grad_norm": 1.1734645366668701,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.6453,
+      "step": 9765
+    },
+    {
+      "epoch": 0.14145439842892624,
+      "grad_norm": 1.5631510019302368,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.6423,
+      "step": 9796
+    },
+    {
+      "epoch": 0.1419020389302836,
+      "grad_norm": 1.6263147592544556,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.636,
+      "step": 9827
+    },
+    {
+      "epoch": 0.14234967943164095,
+      "grad_norm": 1.3325276374816895,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.6435,
+      "step": 9858
+    },
+    {
+      "epoch": 0.14279731993299832,
+      "grad_norm": 1.72733473777771,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.644,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1432449604343557,
+      "grad_norm": 2.609466075897217,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.6468,
+      "step": 9920
+    },
+    {
+      "epoch": 0.14369260093571304,
+      "grad_norm": 1.6878600120544434,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.6375,
+      "step": 9951
+    },
+    {
+      "epoch": 0.1441402414370704,
+      "grad_norm": 1.2290213108062744,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.6401,
+      "step": 9982
+    },
+    {
+      "epoch": 0.14458788193842778,
+      "grad_norm": 1.5059036016464233,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.6421,
+      "step": 10013
+    },
+    {
+      "epoch": 0.14503552243978513,
+      "grad_norm": 2.120579242706299,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.6494,
+      "step": 10044
+    },
+    {
+      "epoch": 0.1454831629411425,
+      "grad_norm": 1.1061620712280273,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.6378,
+      "step": 10075
+    },
+    {
+      "epoch": 0.14593080344249987,
+      "grad_norm": 1.8581500053405762,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.6409,
+      "step": 10106
+    },
+    {
+      "epoch": 0.1463784439438572,
+      "grad_norm": 1.5477920770645142,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.6434,
+      "step": 10137
+    },
+    {
+      "epoch": 0.14682608444521458,
+      "grad_norm": 1.1307681798934937,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.6358,
+      "step": 10168
+    },
+    {
+      "epoch": 0.14727372494657193,
+      "grad_norm": 2.0248334407806396,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.6422,
+      "step": 10199
+    },
+    {
+      "epoch": 0.1477213654479293,
+      "grad_norm": 1.8448565006256104,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.6433,
+      "step": 10230
+    },
+    {
+      "epoch": 0.14816900594928667,
+      "grad_norm": 1.4944031238555908,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.6398,
+      "step": 10261
+    },
+    {
+      "epoch": 0.148616646450644,
+      "grad_norm": 1.2218773365020752,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.6418,
+      "step": 10292
+    },
+    {
+      "epoch": 0.14906428695200138,
+      "grad_norm": 1.8015800714492798,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.6368,
+      "step": 10323
+    },
+    {
+      "epoch": 0.14951192745335876,
+      "grad_norm": 1.1341733932495117,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.6444,
+      "step": 10354
+    },
+    {
+      "epoch": 0.1499595679547161,
+      "grad_norm": 1.2966457605361938,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.6394,
+      "step": 10385
+    },
+    {
+      "epoch": 0.15040720845607347,
+      "grad_norm": 1.2461808919906616,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.6334,
+      "step": 10416
+    },
+    {
+      "epoch": 0.15085484895743084,
+      "grad_norm": 1.256179690361023,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.6401,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1513024894587882,
+      "grad_norm": 1.381158709526062,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.6371,
+      "step": 10478
+    },
+    {
+      "epoch": 0.15175012996014556,
+      "grad_norm": 1.3707715272903442,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.639,
+      "step": 10509
+    },
+    {
+      "epoch": 0.15219777046150293,
+      "grad_norm": 1.4662877321243286,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.6366,
+      "step": 10540
+    },
+    {
+      "epoch": 0.15264541096286027,
+      "grad_norm": 2.7053873538970947,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.641,
+      "step": 10571
+    },
+    {
+      "epoch": 0.15309305146421764,
+      "grad_norm": 1.1371270418167114,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.6414,
+      "step": 10602
+    },
+    {
+      "epoch": 0.153540691965575,
+      "grad_norm": 1.2193849086761475,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.6452,
+      "step": 10633
+    },
+    {
+      "epoch": 0.15398833246693236,
+      "grad_norm": 1.4237920045852661,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.6303,
+      "step": 10664
+    },
+    {
+      "epoch": 0.15443597296828973,
+      "grad_norm": 1.6140167713165283,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.6444,
+      "step": 10695
+    },
+    {
+      "epoch": 0.15488361346964707,
+      "grad_norm": 1.9708229303359985,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.6384,
+      "step": 10726
+    },
+    {
+      "epoch": 0.15533125397100445,
+      "grad_norm": 1.5792853832244873,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.6366,
+      "step": 10757
+    },
+    {
+      "epoch": 0.15577889447236182,
+      "grad_norm": 1.7933409214019775,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.6383,
+      "step": 10788
+    },
+    {
+      "epoch": 0.15622653497371916,
+      "grad_norm": 1.5458565950393677,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.6395,
+      "step": 10819
+    },
+    {
+      "epoch": 0.15667417547507653,
+      "grad_norm": 1.6291790008544922,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.6417,
+      "step": 10850
+    },
+    {
+      "epoch": 0.1571218159764339,
+      "grad_norm": 1.3599265813827515,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.6353,
+      "step": 10881
+    },
+    {
+      "epoch": 0.15756945647779125,
+      "grad_norm": 1.2267005443572998,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.635,
+      "step": 10912
+    },
+    {
+      "epoch": 0.15801709697914862,
+      "grad_norm": 1.3194752931594849,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.6392,
+      "step": 10943
+    },
+    {
+      "epoch": 0.158464737480506,
+      "grad_norm": 1.5103986263275146,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.6352,
+      "step": 10974
+    },
+    {
+      "epoch": 0.15891237798186333,
+      "grad_norm": 1.4630755186080933,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.643,
+      "step": 11005
+    },
+    {
+      "epoch": 0.1593600184832207,
+      "grad_norm": 2.1795740127563477,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.6419,
+      "step": 11036
+    },
+    {
+      "epoch": 0.15980765898457805,
+      "grad_norm": 1.4607034921646118,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.6351,
+      "step": 11067
+    },
+    {
+      "epoch": 0.16025529948593542,
+      "grad_norm": 1.380959153175354,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.6305,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1607029399872928,
+      "grad_norm": 1.7195000648498535,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.6395,
+      "step": 11129
+    },
+    {
+      "epoch": 0.16115058048865014,
+      "grad_norm": 1.8665319681167603,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.6353,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1615982209900075,
+      "grad_norm": 1.0405871868133545,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.63,
+      "step": 11191
+    },
+    {
+      "epoch": 0.16204586149136488,
+      "grad_norm": 1.7168961763381958,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.6329,
+      "step": 11222
+    },
+    {
+      "epoch": 0.16249350199272222,
+      "grad_norm": 1.1099616289138794,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.6401,
+      "step": 11253
+    },
+    {
+      "epoch": 0.1629411424940796,
+      "grad_norm": 1.1965970993041992,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.6373,
+      "step": 11284
+    },
+    {
+      "epoch": 0.16338878299543697,
+      "grad_norm": 1.6090087890625,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.6312,
+      "step": 11315
+    },
+    {
+      "epoch": 0.1638364234967943,
+      "grad_norm": 1.2915993928909302,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.6328,
+      "step": 11346
+    },
+    {
+      "epoch": 0.16428406399815168,
+      "grad_norm": 1.4257746934890747,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6329,
+      "step": 11377
+    },
+    {
+      "epoch": 0.16473170449950905,
+      "grad_norm": 1.2581380605697632,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6298,
+      "step": 11408
+    },
+    {
+      "epoch": 0.1651793450008664,
+      "grad_norm": 2.141317844390869,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.6377,
+      "step": 11439
+    },
+    {
+      "epoch": 0.16562698550222377,
+      "grad_norm": 1.7912797927856445,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6453,
+      "step": 11470
+    },
+    {
+      "epoch": 0.1660746260035811,
+      "grad_norm": 1.0920274257659912,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.6388,
+      "step": 11501
+    },
+    {
+      "epoch": 0.16652226650493848,
+      "grad_norm": 1.3893146514892578,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.6366,
+      "step": 11532
+    },
+    {
+      "epoch": 0.16696990700629585,
+      "grad_norm": 1.510326623916626,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.6289,
+      "step": 11563
+    },
+    {
+      "epoch": 0.1674175475076532,
+      "grad_norm": 1.5738197565078735,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.6291,
+      "step": 11594
+    },
+    {
+      "epoch": 0.16786518800901057,
+      "grad_norm": 1.4003592729568481,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.6331,
+      "step": 11625
+    },
+    {
+      "epoch": 0.16831282851036794,
+      "grad_norm": 1.1500325202941895,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.6288,
+      "step": 11656
+    },
+    {
+      "epoch": 0.16876046901172528,
+      "grad_norm": 1.0949345827102661,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.6338,
+      "step": 11687
+    },
+    {
+      "epoch": 0.16920810951308266,
+      "grad_norm": 1.1545714139938354,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.6253,
+      "step": 11718
+    },
+    {
+      "epoch": 0.16965575001444003,
+      "grad_norm": 1.8404380083084106,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.6331,
+      "step": 11749
+    },
+    {
+      "epoch": 0.17010339051579737,
+      "grad_norm": 1.1443259716033936,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.6266,
+      "step": 11780
+    },
+    {
+      "epoch": 0.17055103101715474,
+      "grad_norm": 2.1884586811065674,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.6255,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1709986715185121,
+      "grad_norm": 1.5698285102844238,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.6354,
+      "step": 11842
+    },
+    {
+      "epoch": 0.17144631201986946,
+      "grad_norm": 1.1452069282531738,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6383,
+      "step": 11873
+    },
+    {
+      "epoch": 0.17189395252122683,
+      "grad_norm": 1.4942229986190796,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6213,
+      "step": 11904
+    },
+    {
+      "epoch": 0.17234159302258417,
+      "grad_norm": 1.8997704982757568,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6239,
+      "step": 11935
+    },
+    {
+      "epoch": 0.17278923352394154,
+      "grad_norm": 1.3202483654022217,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6273,
+      "step": 11966
+    },
+    {
+      "epoch": 0.17323687402529891,
+      "grad_norm": 1.464176058769226,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6337,
+      "step": 11997
+    },
+    {
+      "epoch": 0.17368451452665626,
+      "grad_norm": 1.6081420183181763,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.6329,
+      "step": 12028
+    },
+    {
+      "epoch": 0.17413215502801363,
+      "grad_norm": 1.2481945753097534,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6265,
+      "step": 12059
+    },
+    {
+      "epoch": 0.174579795529371,
+      "grad_norm": 1.096362829208374,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.6293,
+      "step": 12090
+    },
+    {
+      "epoch": 0.17502743603072834,
+      "grad_norm": 1.3475576639175415,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.6411,
+      "step": 12121
+    },
+    {
+      "epoch": 0.17547507653208572,
+      "grad_norm": 1.2768501043319702,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.6375,
+      "step": 12152
+    },
+    {
+      "epoch": 0.1759227170334431,
+      "grad_norm": 2.0324909687042236,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.6263,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.006624315386364e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326c2ae4159344fc785388c97ab51f9004242fca8111ff540004b508cfbcb169
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01327c89905520d53abaed218b91e64e7c4ec8fb34551351872fb10974cb171
+size 4886466168

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fa5aaf8ac56c17c821980c9aee44fcbc2a617fc570e875e6fdb93d92886c72
+size 4832007448

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a223e87240e50dfb05634ea909cf1ec715d37a12b681b14a3a6e97f28688f2b
+size 4999813112

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3047d199c611c6d12b1cca780f033ad89df9c076f742674f7ac4a892ca9573b3
+size 4999813128

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2f91d749d664ecd22c71f3d54488966fc6899a03924b8fea3613c8f83398a8
+size 4832007496

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4711d3ff379bc31841a894411ff02a203d5ea850f12bd86fd2cedef13133fc87
+size 4999813120

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04367da4e43fceaa4b6705deb3890497852d6432899c5c5105dd76791666f8fd
+size 2571158184

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-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-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-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-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d93ba9980243e907f315053329ac017fb8aedf9f0cabe4fcda4e34fa64712
+size 15385036334

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2203546467972044,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004476405013573615,
+      "grad_norm": 6.075733184814453,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.0566,
+      "step": 31
+    },
+    {
+      "epoch": 0.000895281002714723,
+      "grad_norm": 4.2440948486328125,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 0.9468,
+      "step": 62
+    },
+    {
+      "epoch": 0.0013429215040720846,
+      "grad_norm": 4.090479373931885,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 0.9075,
+      "step": 93
+    },
+    {
+      "epoch": 0.001790562005429446,
+      "grad_norm": 4.219390392303467,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 0.8884,
+      "step": 124
+    },
+    {
+      "epoch": 0.0022382025067868077,
+      "grad_norm": 4.051790237426758,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 0.8847,
+      "step": 155
+    },
+    {
+      "epoch": 0.002685843008144169,
+      "grad_norm": 3.5890421867370605,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.8729,
+      "step": 186
+    },
+    {
+      "epoch": 0.0031334835095015307,
+      "grad_norm": 4.262433052062988,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.8809,
+      "step": 217
+    },
+    {
+      "epoch": 0.003581124010858892,
+      "grad_norm": 3.98620343208313,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.8665,
+      "step": 248
+    },
+    {
+      "epoch": 0.004028764512216254,
+      "grad_norm": 3.7834768295288086,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.8628,
+      "step": 279
+    },
+    {
+      "epoch": 0.0044764050135736155,
+      "grad_norm": 4.5324506759643555,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.875,
+      "step": 310
+    },
+    {
+      "epoch": 0.0049240455149309765,
+      "grad_norm": 3.8203251361846924,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.8642,
+      "step": 341
+    },
+    {
+      "epoch": 0.005371686016288338,
+      "grad_norm": 4.361064434051514,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.8655,
+      "step": 372
+    },
+    {
+      "epoch": 0.005819326517645699,
+      "grad_norm": 3.2510569095611572,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.8494,
+      "step": 403
+    },
+    {
+      "epoch": 0.006266967019003061,
+      "grad_norm": 3.7586708068847656,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.8469,
+      "step": 434
+    },
+    {
+      "epoch": 0.006714607520360423,
+      "grad_norm": 3.5017266273498535,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.8615,
+      "step": 465
+    },
+    {
+      "epoch": 0.007162248021717784,
+      "grad_norm": 3.680084228515625,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.8471,
+      "step": 496
+    },
+    {
+      "epoch": 0.007609888523075146,
+      "grad_norm": 2.9426188468933105,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.8513,
+      "step": 527
+    },
+    {
+      "epoch": 0.008057529024432507,
+      "grad_norm": 3.8481788635253906,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.8435,
+      "step": 558
+    },
+    {
+      "epoch": 0.008505169525789868,
+      "grad_norm": 3.373544454574585,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.8446,
+      "step": 589
+    },
+    {
+      "epoch": 0.008952810027147231,
+      "grad_norm": 3.8154516220092773,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.8353,
+      "step": 620
+    },
+    {
+      "epoch": 0.009400450528504592,
+      "grad_norm": 4.436877727508545,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.8263,
+      "step": 651
+    },
+    {
+      "epoch": 0.009848091029861953,
+      "grad_norm": 3.512199640274048,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.8396,
+      "step": 682
+    },
+    {
+      "epoch": 0.010295731531219316,
+      "grad_norm": 3.8799757957458496,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.8312,
+      "step": 713
+    },
+    {
+      "epoch": 0.010743372032576677,
+      "grad_norm": 4.304780960083008,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.8201,
+      "step": 744
+    },
+    {
+      "epoch": 0.011191012533934038,
+      "grad_norm": 3.452643394470215,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.8306,
+      "step": 775
+    },
+    {
+      "epoch": 0.011638653035291399,
+      "grad_norm": 2.92769455909729,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.8218,
+      "step": 806
+    },
+    {
+      "epoch": 0.012086293536648762,
+      "grad_norm": 3.661085844039917,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.8273,
+      "step": 837
+    },
+    {
+      "epoch": 0.012533934038006123,
+      "grad_norm": 3.26717472076416,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.824,
+      "step": 868
+    },
+    {
+      "epoch": 0.012981574539363484,
+      "grad_norm": 3.8160181045532227,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.8193,
+      "step": 899
+    },
+    {
+      "epoch": 0.013429215040720846,
+      "grad_norm": 3.761385679244995,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.8156,
+      "step": 930
+    },
+    {
+      "epoch": 0.013876855542078207,
+      "grad_norm": 2.7427189350128174,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.8211,
+      "step": 961
+    },
+    {
+      "epoch": 0.014324496043435568,
+      "grad_norm": 2.2174184322357178,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.811,
+      "step": 992
+    },
+    {
+      "epoch": 0.01477213654479293,
+      "grad_norm": 2.678250312805176,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.8114,
+      "step": 1023
+    },
+    {
+      "epoch": 0.015219777046150292,
+      "grad_norm": 4.4316487312316895,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.8111,
+      "step": 1054
+    },
+    {
+      "epoch": 0.015667417547507653,
+      "grad_norm": 3.3831615447998047,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.8088,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016115058048865014,
+      "grad_norm": 3.7894206047058105,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.8187,
+      "step": 1116
+    },
+    {
+      "epoch": 0.016562698550222375,
+      "grad_norm": 2.4324352741241455,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.7968,
+      "step": 1147
+    },
+    {
+      "epoch": 0.017010339051579736,
+      "grad_norm": 3.6596791744232178,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.8064,
+      "step": 1178
+    },
+    {
+      "epoch": 0.0174579795529371,
+      "grad_norm": 2.322706460952759,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.7998,
+      "step": 1209
+    },
+    {
+      "epoch": 0.017905620054294462,
+      "grad_norm": 3.25221848487854,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.7999,
+      "step": 1240
+    },
+    {
+      "epoch": 0.018353260555651823,
+      "grad_norm": 2.626753807067871,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.7926,
+      "step": 1271
+    },
+    {
+      "epoch": 0.018800901057009184,
+      "grad_norm": 2.859938383102417,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.7938,
+      "step": 1302
+    },
+    {
+      "epoch": 0.019248541558366545,
+      "grad_norm": 2.6591029167175293,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.7913,
+      "step": 1333
+    },
+    {
+      "epoch": 0.019696182059723906,
+      "grad_norm": 3.4592838287353516,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.7873,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020143822561081267,
+      "grad_norm": 2.5634524822235107,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.7921,
+      "step": 1395
+    },
+    {
+      "epoch": 0.02059146306243863,
+      "grad_norm": 3.134092092514038,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.7968,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021039103563795993,
+      "grad_norm": 2.347602605819702,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.786,
+      "step": 1457
+    },
+    {
+      "epoch": 0.021486744065153354,
+      "grad_norm": 2.948688268661499,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.7935,
+      "step": 1488
+    },
+    {
+      "epoch": 0.021934384566510715,
+      "grad_norm": 2.1757874488830566,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.7786,
+      "step": 1519
+    },
+    {
+      "epoch": 0.022382025067868076,
+      "grad_norm": 2.951026439666748,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.7778,
+      "step": 1550
+    },
+    {
+      "epoch": 0.022829665569225437,
+      "grad_norm": 3.962952136993408,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.7873,
+      "step": 1581
+    },
+    {
+      "epoch": 0.023277306070582798,
+      "grad_norm": 3.359558343887329,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.7774,
+      "step": 1612
+    },
+    {
+      "epoch": 0.023724946571940162,
+      "grad_norm": 2.9352834224700928,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.7733,
+      "step": 1643
+    },
+    {
+      "epoch": 0.024172587073297523,
+      "grad_norm": 3.6340250968933105,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.7738,
+      "step": 1674
+    },
+    {
+      "epoch": 0.024620227574654884,
+      "grad_norm": 2.717247724533081,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.7737,
+      "step": 1705
+    },
+    {
+      "epoch": 0.025067868076012245,
+      "grad_norm": 3.018810510635376,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.7824,
+      "step": 1736
+    },
+    {
+      "epoch": 0.025515508577369606,
+      "grad_norm": 2.2435100078582764,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.7726,
+      "step": 1767
+    },
+    {
+      "epoch": 0.025963149078726967,
+      "grad_norm": 3.1678667068481445,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.7749,
+      "step": 1798
+    },
+    {
+      "epoch": 0.02641078958008433,
+      "grad_norm": 2.422478675842285,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.7656,
+      "step": 1829
+    },
+    {
+      "epoch": 0.026858430081441693,
+      "grad_norm": 2.430635929107666,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.77,
+      "step": 1860
+    },
+    {
+      "epoch": 0.027306070582799054,
+      "grad_norm": 2.199424982070923,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.7596,
+      "step": 1891
+    },
+    {
+      "epoch": 0.027753711084156415,
+      "grad_norm": 2.752176284790039,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.7723,
+      "step": 1922
+    },
+    {
+      "epoch": 0.028201351585513776,
+      "grad_norm": 2.764007568359375,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.7604,
+      "step": 1953
+    },
+    {
+      "epoch": 0.028648992086871137,
+      "grad_norm": 2.045133590698242,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.7714,
+      "step": 1984
+    },
+    {
+      "epoch": 0.029096632588228498,
+      "grad_norm": 3.263131856918335,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.7577,
+      "step": 2015
+    },
+    {
+      "epoch": 0.02954427308958586,
+      "grad_norm": 2.2480087280273438,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.7543,
+      "step": 2046
+    },
+    {
+      "epoch": 0.029991913590943223,
+      "grad_norm": 2.9011387825012207,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.7568,
+      "step": 2077
+    },
+    {
+      "epoch": 0.030439554092300584,
+      "grad_norm": 2.7179999351501465,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.7489,
+      "step": 2108
+    },
+    {
+      "epoch": 0.030887194593657945,
+      "grad_norm": 3.0504350662231445,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.7598,
+      "step": 2139
+    },
+    {
+      "epoch": 0.031334835095015307,
+      "grad_norm": 2.9903855323791504,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.7509,
+      "step": 2170
+    },
+    {
+      "epoch": 0.03178247559637267,
+      "grad_norm": 1.9252121448516846,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.7327,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03223011609773003,
+      "grad_norm": 2.261479139328003,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.7596,
+      "step": 2232
+    },
+    {
+      "epoch": 0.03267775659908739,
+      "grad_norm": 2.475863218307495,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.7566,
+      "step": 2263
+    },
+    {
+      "epoch": 0.03312539710044475,
+      "grad_norm": 1.7898969650268555,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.753,
+      "step": 2294
+    },
+    {
+      "epoch": 0.033573037601802115,
+      "grad_norm": 2.8534107208251953,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.7449,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03402067810315947,
+      "grad_norm": 2.765749454498291,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.7357,
+      "step": 2356
+    },
+    {
+      "epoch": 0.03446831860451684,
+      "grad_norm": 1.8090626001358032,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.736,
+      "step": 2387
+    },
+    {
+      "epoch": 0.0349159591058742,
+      "grad_norm": 1.6179667711257935,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.7399,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03536359960723156,
+      "grad_norm": 3.8357365131378174,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.748,
+      "step": 2449
+    },
+    {
+      "epoch": 0.035811240108588924,
+      "grad_norm": 1.7962925434112549,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.7339,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03625888060994628,
+      "grad_norm": 2.528853178024292,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.7387,
+      "step": 2511
+    },
+    {
+      "epoch": 0.036706521111303646,
+      "grad_norm": 2.2113044261932373,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.7414,
+      "step": 2542
+    },
+    {
+      "epoch": 0.037154161612661,
+      "grad_norm": 1.895753264427185,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.7307,
+      "step": 2573
+    },
+    {
+      "epoch": 0.03760180211401837,
+      "grad_norm": 2.3641865253448486,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.7373,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03804944261537573,
+      "grad_norm": 2.4185962677001953,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.7207,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03849708311673309,
+      "grad_norm": 1.8405852317810059,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.7331,
+      "step": 2666
+    },
+    {
+      "epoch": 0.038944723618090454,
+      "grad_norm": 2.796203136444092,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.7312,
+      "step": 2697
+    },
+    {
+      "epoch": 0.03939236411944781,
+      "grad_norm": 2.0833380222320557,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.7396,
+      "step": 2728
+    },
+    {
+      "epoch": 0.039840004620805176,
+      "grad_norm": 3.2164361476898193,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.731,
+      "step": 2759
+    },
+    {
+      "epoch": 0.040287645122162534,
+      "grad_norm": 3.1149556636810303,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.7291,
+      "step": 2790
+    },
+    {
+      "epoch": 0.0407352856235199,
+      "grad_norm": 2.1158149242401123,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7314,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04118292612487726,
+      "grad_norm": 1.573134422302246,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.722,
+      "step": 2852
+    },
+    {
+      "epoch": 0.04163056662623462,
+      "grad_norm": 2.4656667709350586,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.7376,
+      "step": 2883
+    },
+    {
+      "epoch": 0.042078207127591985,
+      "grad_norm": 2.0156564712524414,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.7261,
+      "step": 2914
+    },
+    {
+      "epoch": 0.04252584762894934,
+      "grad_norm": 1.8054187297821045,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.7318,
+      "step": 2945
+    },
+    {
+      "epoch": 0.04297348813030671,
+      "grad_norm": 2.247424602508545,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.7252,
+      "step": 2976
+    },
+    {
+      "epoch": 0.043421128631664065,
+      "grad_norm": 2.238030195236206,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.7263,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04386876913302143,
+      "grad_norm": 2.017012357711792,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.725,
+      "step": 3038
+    },
+    {
+      "epoch": 0.044316409634378794,
+      "grad_norm": 1.7042877674102783,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.7187,
+      "step": 3069
+    },
+    {
+      "epoch": 0.04476405013573615,
+      "grad_norm": 2.4380805492401123,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7318,
+      "step": 3100
+    },
+    {
+      "epoch": 0.045211690637093516,
+      "grad_norm": 2.590555191040039,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.7213,
+      "step": 3131
+    },
+    {
+      "epoch": 0.04565933113845087,
+      "grad_norm": 1.5544863939285278,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.7179,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04610697163980824,
+      "grad_norm": 2.105193614959717,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.7177,
+      "step": 3193
+    },
+    {
+      "epoch": 0.046554612141165595,
+      "grad_norm": 2.108760356903076,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.724,
+      "step": 3224
+    },
+    {
+      "epoch": 0.04700225264252296,
+      "grad_norm": 3.2209384441375732,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7285,
+      "step": 3255
+    },
+    {
+      "epoch": 0.047449893143880324,
+      "grad_norm": 1.7396947145462036,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7189,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04789753364523768,
+      "grad_norm": 1.815233826637268,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.718,
+      "step": 3317
+    },
+    {
+      "epoch": 0.048345174146595046,
+      "grad_norm": 2.3554177284240723,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7145,
+      "step": 3348
+    },
+    {
+      "epoch": 0.048792814647952404,
+      "grad_norm": 2.7524783611297607,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7198,
+      "step": 3379
+    },
+    {
+      "epoch": 0.04924045514930977,
+      "grad_norm": 2.151045322418213,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7085,
+      "step": 3410
+    },
+    {
+      "epoch": 0.049688095650667126,
+      "grad_norm": 2.099945306777954,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.7059,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05013573615202449,
+      "grad_norm": 2.2688772678375244,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7071,
+      "step": 3472
+    },
+    {
+      "epoch": 0.050583376653381855,
+      "grad_norm": 1.9718475341796875,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7064,
+      "step": 3503
+    },
+    {
+      "epoch": 0.05103101715473921,
+      "grad_norm": 1.8137073516845703,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7049,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05147865765609658,
+      "grad_norm": 3.5721960067749023,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7171,
+      "step": 3565
+    },
+    {
+      "epoch": 0.051926298157453935,
+      "grad_norm": 2.6050193309783936,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.7081,
+      "step": 3596
+    },
+    {
+      "epoch": 0.0523739386588113,
+      "grad_norm": 1.6417428255081177,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7101,
+      "step": 3627
+    },
+    {
+      "epoch": 0.05282157916016866,
+      "grad_norm": 2.1848113536834717,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7026,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05326921966152602,
+      "grad_norm": 1.8033145666122437,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7045,
+      "step": 3689
+    },
+    {
+      "epoch": 0.053716860162883386,
+      "grad_norm": 1.6396067142486572,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7011,
+      "step": 3720
+    },
+    {
+      "epoch": 0.05416450066424074,
+      "grad_norm": 1.7694982290267944,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7081,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05461214116559811,
+      "grad_norm": 3.1106865406036377,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7054,
+      "step": 3782
+    },
+    {
+      "epoch": 0.055059781666955465,
+      "grad_norm": 2.4519076347351074,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.697,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05550742216831283,
+      "grad_norm": 2.0600473880767822,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7106,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05595506266967019,
+      "grad_norm": 2.4080190658569336,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.6965,
+      "step": 3875
+    },
+    {
+      "epoch": 0.05640270317102755,
+      "grad_norm": 2.3117220401763916,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.6968,
+      "step": 3906
+    },
+    {
+      "epoch": 0.056850343672384916,
+      "grad_norm": 2.364525318145752,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7037,
+      "step": 3937
+    },
+    {
+      "epoch": 0.057297984173742274,
+      "grad_norm": 1.6029551029205322,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.6971,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05774562467509964,
+      "grad_norm": 2.7199840545654297,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.6979,
+      "step": 3999
+    },
+    {
+      "epoch": 0.058193265176456996,
+      "grad_norm": 2.0529887676239014,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.697,
+      "step": 4030
+    },
+    {
+      "epoch": 0.05864090567781436,
+      "grad_norm": 2.0358359813690186,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7008,
+      "step": 4061
+    },
+    {
+      "epoch": 0.05908854617917172,
+      "grad_norm": 2.069599151611328,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.7075,
+      "step": 4092
+    },
+    {
+      "epoch": 0.05953618668052908,
+      "grad_norm": 3.084198236465454,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7067,
+      "step": 4123
+    },
+    {
+      "epoch": 0.05998382718188645,
+      "grad_norm": 1.7525622844696045,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7049,
+      "step": 4154
+    },
+    {
+      "epoch": 0.060431467683243804,
+      "grad_norm": 1.757623553276062,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7019,
+      "step": 4185
+    },
+    {
+      "epoch": 0.06087910818460117,
+      "grad_norm": 2.1729736328125,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.6991,
+      "step": 4216
+    },
+    {
+      "epoch": 0.061326748685958526,
+      "grad_norm": 1.9989466667175293,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7014,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06177438918731589,
+      "grad_norm": 2.2553014755249023,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7064,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06222202968867325,
+      "grad_norm": 2.462275743484497,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.6945,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06266967019003061,
+      "grad_norm": 2.624544382095337,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.6992,
+      "step": 4340
+    },
+    {
+      "epoch": 0.06311731069138797,
+      "grad_norm": 1.2823548316955566,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.6905,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06356495119274534,
+      "grad_norm": 2.2118582725524902,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.6969,
+      "step": 4402
+    },
+    {
+      "epoch": 0.0640125916941027,
+      "grad_norm": 2.3164892196655273,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.6848,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06446023219546006,
+      "grad_norm": 1.6639585494995117,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.6883,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06490787269681741,
+      "grad_norm": 1.915570855140686,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.6929,
+      "step": 4495
+    },
+    {
+      "epoch": 0.06535551319817479,
+      "grad_norm": 1.8555858135223389,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.6952,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06580315369953214,
+      "grad_norm": 2.1268434524536133,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.6908,
+      "step": 4557
+    },
+    {
+      "epoch": 0.0662507942008895,
+      "grad_norm": 2.199445962905884,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.6919,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06669843470224687,
+      "grad_norm": 1.9284214973449707,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.6932,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06714607520360423,
+      "grad_norm": 2.8380227088928223,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.6858,
+      "step": 4650
+    },
+    {
+      "epoch": 0.06759371570496159,
+      "grad_norm": 2.0919442176818848,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.6913,
+      "step": 4681
+    },
+    {
+      "epoch": 0.06804135620631895,
+      "grad_norm": 2.1968653202056885,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.691,
+      "step": 4712
+    },
+    {
+      "epoch": 0.06848899670767632,
+      "grad_norm": 1.9843740463256836,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.6904,
+      "step": 4743
+    },
+    {
+      "epoch": 0.06893663720903367,
+      "grad_norm": 2.016184091567993,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.6916,
+      "step": 4774
+    },
+    {
+      "epoch": 0.06938427771039103,
+      "grad_norm": 1.797019124031067,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.6931,
+      "step": 4805
+    },
+    {
+      "epoch": 0.0698319182117484,
+      "grad_norm": 1.433285117149353,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.6809,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07027955871310576,
+      "grad_norm": 1.4553332328796387,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.6995,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07072719921446312,
+      "grad_norm": 2.220764636993408,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.6807,
+      "step": 4898
+    },
+    {
+      "epoch": 0.07117483971582048,
+      "grad_norm": 1.9182664155960083,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.6834,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07162248021717785,
+      "grad_norm": 1.5292731523513794,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.6795,
+      "step": 4960
+    },
+    {
+      "epoch": 0.0720701207185352,
+      "grad_norm": 1.618630051612854,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.6829,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07251776121989256,
+      "grad_norm": 2.463080644607544,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.6867,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07296540172124993,
+      "grad_norm": 2.0314955711364746,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.6914,
+      "step": 5053
+    },
+    {
+      "epoch": 0.07341304222260729,
+      "grad_norm": 2.511078119277954,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.6838,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07386068272396465,
+      "grad_norm": 1.8808708190917969,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.6842,
+      "step": 5115
+    },
+    {
+      "epoch": 0.074308323225322,
+      "grad_norm": 1.6079555749893188,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.6828,
+      "step": 5146
+    },
+    {
+      "epoch": 0.07475596372667938,
+      "grad_norm": 1.607474446296692,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.69,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07520360422803674,
+      "grad_norm": 2.38283371925354,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.6877,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0756512447293941,
+      "grad_norm": 2.5603227615356445,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.6824,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07609888523075146,
+      "grad_norm": 2.540479898452759,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.6787,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07654652573210882,
+      "grad_norm": 1.7890712022781372,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.6779,
+      "step": 5301
+    },
+    {
+      "epoch": 0.07699416623346618,
+      "grad_norm": 2.279125213623047,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.6783,
+      "step": 5332
+    },
+    {
+      "epoch": 0.07744180673482354,
+      "grad_norm": 1.6013977527618408,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.6774,
+      "step": 5363
+    },
+    {
+      "epoch": 0.07788944723618091,
+      "grad_norm": 1.2730411291122437,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.6811,
+      "step": 5394
+    },
+    {
+      "epoch": 0.07833708773753827,
+      "grad_norm": 1.764948844909668,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.6771,
+      "step": 5425
+    },
+    {
+      "epoch": 0.07878472823889562,
+      "grad_norm": 1.6873563528060913,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.701,
+      "step": 5456
+    },
+    {
+      "epoch": 0.079232368740253,
+      "grad_norm": 2.386568069458008,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.6785,
+      "step": 5487
+    },
+    {
+      "epoch": 0.07968000924161035,
+      "grad_norm": 1.3919615745544434,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.6808,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08012764974296771,
+      "grad_norm": 2.006275177001953,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.6713,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08057529024432507,
+      "grad_norm": 1.995177149772644,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.6744,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08102293074568244,
+      "grad_norm": 1.4058161973953247,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.67,
+      "step": 5611
+    },
+    {
+      "epoch": 0.0814705712470398,
+      "grad_norm": 2.0186007022857666,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.6647,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08191821174839715,
+      "grad_norm": 1.7829797267913818,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.6786,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08236585224975453,
+      "grad_norm": 2.12453556060791,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.6824,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08281349275111188,
+      "grad_norm": 1.557865023612976,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.6847,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08326113325246924,
+      "grad_norm": 2.1795268058776855,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.67,
+      "step": 5766
+    },
+    {
+      "epoch": 0.0837087737538266,
+      "grad_norm": 2.0731284618377686,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.6827,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08415641425518397,
+      "grad_norm": 1.54974365234375,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.6757,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08460405475654133,
+      "grad_norm": 1.7679517269134521,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.6673,
+      "step": 5859
+    },
+    {
+      "epoch": 0.08505169525789869,
+      "grad_norm": 2.4018664360046387,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.6751,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08549933575925606,
+      "grad_norm": 2.198348045349121,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.6771,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08594697626061341,
+      "grad_norm": 2.421766996383667,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.6825,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08639461676197077,
+      "grad_norm": 1.5196090936660767,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.6734,
+      "step": 5983
+    },
+    {
+      "epoch": 0.08684225726332813,
+      "grad_norm": 1.947550892829895,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.671,
+      "step": 6014
+    },
+    {
+      "epoch": 0.0872898977646855,
+      "grad_norm": 1.999944806098938,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.673,
+      "step": 6045
+    },
+    {
+      "epoch": 0.08773753826604286,
+      "grad_norm": 2.322126626968384,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.6758,
+      "step": 6076
+    },
+    {
+      "epoch": 0.08818517876740022,
+      "grad_norm": 1.4106264114379883,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.6685,
+      "step": 6107
+    },
+    {
+      "epoch": 0.08863281926875759,
+      "grad_norm": 2.846497058868408,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.6664,
+      "step": 6138
+    },
+    {
+      "epoch": 0.08908045977011494,
+      "grad_norm": 1.5854451656341553,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.6696,
+      "step": 6169
+    },
+    {
+      "epoch": 0.0895281002714723,
+      "grad_norm": 1.4877409934997559,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.6824,
+      "step": 6200
+    },
+    {
+      "epoch": 0.08997574077282966,
+      "grad_norm": 2.564678907394409,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.6743,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09042338127418703,
+      "grad_norm": 1.6551730632781982,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.6688,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09087102177554439,
+      "grad_norm": 1.542798638343811,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.6732,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09131866227690175,
+      "grad_norm": 1.8403035402297974,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.6812,
+      "step": 6324
+    },
+    {
+      "epoch": 0.09176630277825912,
+      "grad_norm": 1.7633146047592163,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.6738,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09221394327961648,
+      "grad_norm": 1.353498101234436,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.6732,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09266158378097383,
+      "grad_norm": 2.0140905380249023,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.6795,
+      "step": 6417
+    },
+    {
+      "epoch": 0.09310922428233119,
+      "grad_norm": 1.9759689569473267,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.678,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09355686478368856,
+      "grad_norm": 1.9719219207763672,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.6633,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09400450528504592,
+      "grad_norm": 1.7268098592758179,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.6675,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09445214578640328,
+      "grad_norm": 2.3125104904174805,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.6688,
+      "step": 6541
+    },
+    {
+      "epoch": 0.09489978628776065,
+      "grad_norm": 3.1883366107940674,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.6708,
+      "step": 6572
+    },
+    {
+      "epoch": 0.095347426789118,
+      "grad_norm": 1.3998332023620605,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.6692,
+      "step": 6603
+    },
+    {
+      "epoch": 0.09579506729047536,
+      "grad_norm": 1.2298917770385742,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.6679,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09624270779183272,
+      "grad_norm": 1.4910554885864258,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.6663,
+      "step": 6665
+    },
+    {
+      "epoch": 0.09669034829319009,
+      "grad_norm": 1.5662206411361694,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.6677,
+      "step": 6696
+    },
+    {
+      "epoch": 0.09713798879454745,
+      "grad_norm": 1.3008075952529907,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.6663,
+      "step": 6727
+    },
+    {
+      "epoch": 0.09758562929590481,
+      "grad_norm": 2.1645631790161133,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.6758,
+      "step": 6758
+    },
+    {
+      "epoch": 0.09803326979726218,
+      "grad_norm": 1.4836088418960571,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.667,
+      "step": 6789
+    },
+    {
+      "epoch": 0.09848091029861954,
+      "grad_norm": 1.49858820438385,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.6716,
+      "step": 6820
+    },
+    {
+      "epoch": 0.0989285507999769,
+      "grad_norm": 2.0113542079925537,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.6629,
+      "step": 6851
+    },
+    {
+      "epoch": 0.09937619130133425,
+      "grad_norm": 1.1643431186676025,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.6672,
+      "step": 6882
+    },
+    {
+      "epoch": 0.09982383180269162,
+      "grad_norm": 1.825980544090271,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.6674,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10027147230404898,
+      "grad_norm": 1.2358912229537964,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.6596,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10071911280540634,
+      "grad_norm": 2.1445295810699463,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.665,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10116675330676371,
+      "grad_norm": 1.7739466428756714,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.669,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10161439380812107,
+      "grad_norm": 1.4754871129989624,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.657,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10206203430947842,
+      "grad_norm": 1.5860286951065063,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.6672,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10250967481083578,
+      "grad_norm": 1.3789246082305908,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.6664,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10295731531219315,
+      "grad_norm": 1.6928731203079224,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.6629,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10340495581355051,
+      "grad_norm": 1.5635676383972168,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.6656,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10385259631490787,
+      "grad_norm": 1.3450698852539062,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.6637,
+      "step": 7192
+    },
+    {
+      "epoch": 0.10430023681626524,
+      "grad_norm": 1.955698847770691,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.6638,
+      "step": 7223
+    },
+    {
+      "epoch": 0.1047478773176226,
+      "grad_norm": 2.6813876628875732,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.6661,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10519551781897996,
+      "grad_norm": 1.7577868700027466,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.6579,
+      "step": 7285
+    },
+    {
+      "epoch": 0.10564315832033731,
+      "grad_norm": 1.3784778118133545,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.6677,
+      "step": 7316
+    },
+    {
+      "epoch": 0.10609079882169468,
+      "grad_norm": 1.690073847770691,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.6606,
+      "step": 7347
+    },
+    {
+      "epoch": 0.10653843932305204,
+      "grad_norm": 1.9649986028671265,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.6701,
+      "step": 7378
+    },
+    {
+      "epoch": 0.1069860798244094,
+      "grad_norm": 1.6628475189208984,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.659,
+      "step": 7409
+    },
+    {
+      "epoch": 0.10743372032576677,
+      "grad_norm": 1.4179651737213135,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.6568,
+      "step": 7440
+    },
+    {
+      "epoch": 0.10788136082712413,
+      "grad_norm": 2.3137412071228027,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.6615,
+      "step": 7471
+    },
+    {
+      "epoch": 0.10832900132848149,
+      "grad_norm": 2.24027156829834,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.6526,
+      "step": 7502
+    },
+    {
+      "epoch": 0.10877664182983884,
+      "grad_norm": 3.1159045696258545,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.6675,
+      "step": 7533
+    },
+    {
+      "epoch": 0.10922428233119622,
+      "grad_norm": 1.8783204555511475,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.6602,
+      "step": 7564
+    },
+    {
+      "epoch": 0.10967192283255357,
+      "grad_norm": 16.97314453125,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.6592,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11011956333391093,
+      "grad_norm": 2.2325730323791504,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.6516,
+      "step": 7626
+    },
+    {
+      "epoch": 0.1105672038352683,
+      "grad_norm": 1.4192359447479248,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.6582,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11101484433662566,
+      "grad_norm": 1.3031502962112427,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.6642,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11146248483798302,
+      "grad_norm": 1.3589367866516113,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.6567,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11191012533934037,
+      "grad_norm": 1.380942463874817,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.6566,
+      "step": 7750
+    },
+    {
+      "epoch": 0.11235776584069775,
+      "grad_norm": 1.7768518924713135,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.6649,
+      "step": 7781
+    },
+    {
+      "epoch": 0.1128054063420551,
+      "grad_norm": 1.8216607570648193,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.6681,
+      "step": 7812
+    },
+    {
+      "epoch": 0.11325304684341246,
+      "grad_norm": 1.8983733654022217,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.6531,
+      "step": 7843
+    },
+    {
+      "epoch": 0.11370068734476983,
+      "grad_norm": 1.8444031476974487,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.6607,
+      "step": 7874
+    },
+    {
+      "epoch": 0.11414832784612719,
+      "grad_norm": 2.833496332168579,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.6504,
+      "step": 7905
+    },
+    {
+      "epoch": 0.11459596834748455,
+      "grad_norm": 1.5405519008636475,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.6563,
+      "step": 7936
+    },
+    {
+      "epoch": 0.1150436088488419,
+      "grad_norm": 1.1646043062210083,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.6436,
+      "step": 7967
+    },
+    {
+      "epoch": 0.11549124935019928,
+      "grad_norm": 1.9327855110168457,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.6592,
+      "step": 7998
+    },
+    {
+      "epoch": 0.11593888985155663,
+      "grad_norm": 1.5157870054244995,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.6532,
+      "step": 8029
+    },
+    {
+      "epoch": 0.11638653035291399,
+      "grad_norm": 2.015371084213257,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.6571,
+      "step": 8060
+    },
+    {
+      "epoch": 0.11683417085427136,
+      "grad_norm": 1.4756910800933838,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.6516,
+      "step": 8091
+    },
+    {
+      "epoch": 0.11728181135562872,
+      "grad_norm": 3.0601749420166016,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.6695,
+      "step": 8122
+    },
+    {
+      "epoch": 0.11772945185698608,
+      "grad_norm": 1.9742850065231323,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.6515,
+      "step": 8153
+    },
+    {
+      "epoch": 0.11817709235834344,
+      "grad_norm": 2.2514753341674805,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.6523,
+      "step": 8184
+    },
+    {
+      "epoch": 0.11862473285970081,
+      "grad_norm": 1.3582695722579956,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.6551,
+      "step": 8215
+    },
+    {
+      "epoch": 0.11907237336105816,
+      "grad_norm": 1.1863290071487427,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.6564,
+      "step": 8246
+    },
+    {
+      "epoch": 0.11952001386241552,
+      "grad_norm": 1.2964929342269897,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.6579,
+      "step": 8277
+    },
+    {
+      "epoch": 0.1199676543637729,
+      "grad_norm": 1.5999125242233276,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.6561,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12041529486513025,
+      "grad_norm": 1.6672707796096802,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.6612,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12086293536648761,
+      "grad_norm": 1.6736791133880615,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.666,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12131057586784497,
+      "grad_norm": 1.5894031524658203,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.6611,
+      "step": 8401
+    },
+    {
+      "epoch": 0.12175821636920234,
+      "grad_norm": 1.459932565689087,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.6557,
+      "step": 8432
+    },
+    {
+      "epoch": 0.1222058568705597,
+      "grad_norm": 2.244842767715454,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.6611,
+      "step": 8463
+    },
+    {
+      "epoch": 0.12265349737191705,
+      "grad_norm": 1.4417616128921509,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.6546,
+      "step": 8494
+    },
+    {
+      "epoch": 0.12310113787327442,
+      "grad_norm": 1.7080905437469482,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.6526,
+      "step": 8525
+    },
+    {
+      "epoch": 0.12354877837463178,
+      "grad_norm": 1.9203237295150757,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.6523,
+      "step": 8556
+    },
+    {
+      "epoch": 0.12399641887598914,
+      "grad_norm": 1.6014002561569214,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.6515,
+      "step": 8587
+    },
+    {
+      "epoch": 0.1244440593773465,
+      "grad_norm": 1.4305850267410278,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.6499,
+      "step": 8618
+    },
+    {
+      "epoch": 0.12489169987870387,
+      "grad_norm": 1.7838248014450073,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.6449,
+      "step": 8649
+    },
+    {
+      "epoch": 0.12533934038006123,
+      "grad_norm": 1.8731306791305542,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.6538,
+      "step": 8680
+    },
+    {
+      "epoch": 0.1257869808814186,
+      "grad_norm": 2.0666420459747314,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.653,
+      "step": 8711
+    },
+    {
+      "epoch": 0.12623462138277594,
+      "grad_norm": 1.7400550842285156,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.649,
+      "step": 8742
+    },
+    {
+      "epoch": 0.1266822618841333,
+      "grad_norm": 1.6730947494506836,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.6569,
+      "step": 8773
+    },
+    {
+      "epoch": 0.12712990238549068,
+      "grad_norm": 1.2559434175491333,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.6479,
+      "step": 8804
+    },
+    {
+      "epoch": 0.12757754288684803,
+      "grad_norm": 1.5398365259170532,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.6485,
+      "step": 8835
+    },
+    {
+      "epoch": 0.1280251833882054,
+      "grad_norm": 2.1256911754608154,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.6457,
+      "step": 8866
+    },
+    {
+      "epoch": 0.12847282388956274,
+      "grad_norm": 1.4803603887557983,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.6508,
+      "step": 8897
+    },
+    {
+      "epoch": 0.12892046439092011,
+      "grad_norm": 1.5118730068206787,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.6503,
+      "step": 8928
+    },
+    {
+      "epoch": 0.12936810489227749,
+      "grad_norm": 1.1825127601623535,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.663,
+      "step": 8959
+    },
+    {
+      "epoch": 0.12981574539363483,
+      "grad_norm": 1.358410120010376,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.6493,
+      "step": 8990
+    },
+    {
+      "epoch": 0.1302633858949922,
+      "grad_norm": 1.8535338640213013,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.6502,
+      "step": 9021
+    },
+    {
+      "epoch": 0.13071102639634957,
+      "grad_norm": 1.7688425779342651,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.6504,
+      "step": 9052
+    },
+    {
+      "epoch": 0.13115866689770692,
+      "grad_norm": 1.4369934797286987,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.6587,
+      "step": 9083
+    },
+    {
+      "epoch": 0.1316063073990643,
+      "grad_norm": 1.590460181236267,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.6406,
+      "step": 9114
+    },
+    {
+      "epoch": 0.13205394790042166,
+      "grad_norm": 1.0730258226394653,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.6527,
+      "step": 9145
+    },
+    {
+      "epoch": 0.132501588401779,
+      "grad_norm": 1.6859849691390991,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.6492,
+      "step": 9176
+    },
+    {
+      "epoch": 0.13294922890313637,
+      "grad_norm": 1.9398038387298584,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.6471,
+      "step": 9207
+    },
+    {
+      "epoch": 0.13339686940449375,
+      "grad_norm": 1.5931581258773804,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.6516,
+      "step": 9238
+    },
+    {
+      "epoch": 0.1338445099058511,
+      "grad_norm": 1.2483857870101929,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.6458,
+      "step": 9269
+    },
+    {
+      "epoch": 0.13429215040720846,
+      "grad_norm": 1.2097086906433105,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.6491,
+      "step": 9300
+    },
+    {
+      "epoch": 0.1347397909085658,
+      "grad_norm": 1.2975740432739258,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.6476,
+      "step": 9331
+    },
+    {
+      "epoch": 0.13518743140992318,
+      "grad_norm": 1.474465012550354,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.6494,
+      "step": 9362
+    },
+    {
+      "epoch": 0.13563507191128055,
+      "grad_norm": 1.455447793006897,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.6461,
+      "step": 9393
+    },
+    {
+      "epoch": 0.1360827124126379,
+      "grad_norm": 1.806460976600647,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.6477,
+      "step": 9424
+    },
+    {
+      "epoch": 0.13653035291399526,
+      "grad_norm": 1.3280959129333496,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.6571,
+      "step": 9455
+    },
+    {
+      "epoch": 0.13697799341535263,
+      "grad_norm": 1.6380054950714111,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.6495,
+      "step": 9486
+    },
+    {
+      "epoch": 0.13742563391670998,
+      "grad_norm": 1.35837984085083,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.6473,
+      "step": 9517
+    },
+    {
+      "epoch": 0.13787327441806735,
+      "grad_norm": 1.2885377407073975,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.648,
+      "step": 9548
+    },
+    {
+      "epoch": 0.13832091491942472,
+      "grad_norm": 1.2592779397964478,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.648,
+      "step": 9579
+    },
+    {
+      "epoch": 0.13876855542078206,
+      "grad_norm": 1.4869375228881836,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.6437,
+      "step": 9610
+    },
+    {
+      "epoch": 0.13921619592213944,
+      "grad_norm": 1.3101277351379395,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.6429,
+      "step": 9641
+    },
+    {
+      "epoch": 0.1396638364234968,
+      "grad_norm": 1.488227367401123,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.651,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14011147692485415,
+      "grad_norm": 1.394073486328125,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.6437,
+      "step": 9703
+    },
+    {
+      "epoch": 0.14055911742621152,
+      "grad_norm": 1.8128383159637451,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.6494,
+      "step": 9734
+    },
+    {
+      "epoch": 0.14100675792756887,
+      "grad_norm": 1.1734645366668701,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.6453,
+      "step": 9765
+    },
+    {
+      "epoch": 0.14145439842892624,
+      "grad_norm": 1.5631510019302368,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.6423,
+      "step": 9796
+    },
+    {
+      "epoch": 0.1419020389302836,
+      "grad_norm": 1.6263147592544556,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.636,
+      "step": 9827
+    },
+    {
+      "epoch": 0.14234967943164095,
+      "grad_norm": 1.3325276374816895,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.6435,
+      "step": 9858
+    },
+    {
+      "epoch": 0.14279731993299832,
+      "grad_norm": 1.72733473777771,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.644,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1432449604343557,
+      "grad_norm": 2.609466075897217,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.6468,
+      "step": 9920
+    },
+    {
+      "epoch": 0.14369260093571304,
+      "grad_norm": 1.6878600120544434,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.6375,
+      "step": 9951
+    },
+    {
+      "epoch": 0.1441402414370704,
+      "grad_norm": 1.2290213108062744,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.6401,
+      "step": 9982
+    },
+    {
+      "epoch": 0.14458788193842778,
+      "grad_norm": 1.5059036016464233,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.6421,
+      "step": 10013
+    },
+    {
+      "epoch": 0.14503552243978513,
+      "grad_norm": 2.120579242706299,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.6494,
+      "step": 10044
+    },
+    {
+      "epoch": 0.1454831629411425,
+      "grad_norm": 1.1061620712280273,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.6378,
+      "step": 10075
+    },
+    {
+      "epoch": 0.14593080344249987,
+      "grad_norm": 1.8581500053405762,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.6409,
+      "step": 10106
+    },
+    {
+      "epoch": 0.1463784439438572,
+      "grad_norm": 1.5477920770645142,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.6434,
+      "step": 10137
+    },
+    {
+      "epoch": 0.14682608444521458,
+      "grad_norm": 1.1307681798934937,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.6358,
+      "step": 10168
+    },
+    {
+      "epoch": 0.14727372494657193,
+      "grad_norm": 2.0248334407806396,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.6422,
+      "step": 10199
+    },
+    {
+      "epoch": 0.1477213654479293,
+      "grad_norm": 1.8448565006256104,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.6433,
+      "step": 10230
+    },
+    {
+      "epoch": 0.14816900594928667,
+      "grad_norm": 1.4944031238555908,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.6398,
+      "step": 10261
+    },
+    {
+      "epoch": 0.148616646450644,
+      "grad_norm": 1.2218773365020752,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.6418,
+      "step": 10292
+    },
+    {
+      "epoch": 0.14906428695200138,
+      "grad_norm": 1.8015800714492798,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.6368,
+      "step": 10323
+    },
+    {
+      "epoch": 0.14951192745335876,
+      "grad_norm": 1.1341733932495117,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.6444,
+      "step": 10354
+    },
+    {
+      "epoch": 0.1499595679547161,
+      "grad_norm": 1.2966457605361938,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.6394,
+      "step": 10385
+    },
+    {
+      "epoch": 0.15040720845607347,
+      "grad_norm": 1.2461808919906616,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.6334,
+      "step": 10416
+    },
+    {
+      "epoch": 0.15085484895743084,
+      "grad_norm": 1.256179690361023,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.6401,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1513024894587882,
+      "grad_norm": 1.381158709526062,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.6371,
+      "step": 10478
+    },
+    {
+      "epoch": 0.15175012996014556,
+      "grad_norm": 1.3707715272903442,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.639,
+      "step": 10509
+    },
+    {
+      "epoch": 0.15219777046150293,
+      "grad_norm": 1.4662877321243286,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.6366,
+      "step": 10540
+    },
+    {
+      "epoch": 0.15264541096286027,
+      "grad_norm": 2.7053873538970947,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.641,
+      "step": 10571
+    },
+    {
+      "epoch": 0.15309305146421764,
+      "grad_norm": 1.1371270418167114,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.6414,
+      "step": 10602
+    },
+    {
+      "epoch": 0.153540691965575,
+      "grad_norm": 1.2193849086761475,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.6452,
+      "step": 10633
+    },
+    {
+      "epoch": 0.15398833246693236,
+      "grad_norm": 1.4237920045852661,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.6303,
+      "step": 10664
+    },
+    {
+      "epoch": 0.15443597296828973,
+      "grad_norm": 1.6140167713165283,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.6444,
+      "step": 10695
+    },
+    {
+      "epoch": 0.15488361346964707,
+      "grad_norm": 1.9708229303359985,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.6384,
+      "step": 10726
+    },
+    {
+      "epoch": 0.15533125397100445,
+      "grad_norm": 1.5792853832244873,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.6366,
+      "step": 10757
+    },
+    {
+      "epoch": 0.15577889447236182,
+      "grad_norm": 1.7933409214019775,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.6383,
+      "step": 10788
+    },
+    {
+      "epoch": 0.15622653497371916,
+      "grad_norm": 1.5458565950393677,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.6395,
+      "step": 10819
+    },
+    {
+      "epoch": 0.15667417547507653,
+      "grad_norm": 1.6291790008544922,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.6417,
+      "step": 10850
+    },
+    {
+      "epoch": 0.1571218159764339,
+      "grad_norm": 1.3599265813827515,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.6353,
+      "step": 10881
+    },
+    {
+      "epoch": 0.15756945647779125,
+      "grad_norm": 1.2267005443572998,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.635,
+      "step": 10912
+    },
+    {
+      "epoch": 0.15801709697914862,
+      "grad_norm": 1.3194752931594849,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.6392,
+      "step": 10943
+    },
+    {
+      "epoch": 0.158464737480506,
+      "grad_norm": 1.5103986263275146,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.6352,
+      "step": 10974
+    },
+    {
+      "epoch": 0.15891237798186333,
+      "grad_norm": 1.4630755186080933,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.643,
+      "step": 11005
+    },
+    {
+      "epoch": 0.1593600184832207,
+      "grad_norm": 2.1795740127563477,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.6419,
+      "step": 11036
+    },
+    {
+      "epoch": 0.15980765898457805,
+      "grad_norm": 1.4607034921646118,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.6351,
+      "step": 11067
+    },
+    {
+      "epoch": 0.16025529948593542,
+      "grad_norm": 1.380959153175354,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.6305,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1607029399872928,
+      "grad_norm": 1.7195000648498535,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.6395,
+      "step": 11129
+    },
+    {
+      "epoch": 0.16115058048865014,
+      "grad_norm": 1.8665319681167603,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.6353,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1615982209900075,
+      "grad_norm": 1.0405871868133545,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.63,
+      "step": 11191
+    },
+    {
+      "epoch": 0.16204586149136488,
+      "grad_norm": 1.7168961763381958,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.6329,
+      "step": 11222
+    },
+    {
+      "epoch": 0.16249350199272222,
+      "grad_norm": 1.1099616289138794,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.6401,
+      "step": 11253
+    },
+    {
+      "epoch": 0.1629411424940796,
+      "grad_norm": 1.1965970993041992,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.6373,
+      "step": 11284
+    },
+    {
+      "epoch": 0.16338878299543697,
+      "grad_norm": 1.6090087890625,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.6312,
+      "step": 11315
+    },
+    {
+      "epoch": 0.1638364234967943,
+      "grad_norm": 1.2915993928909302,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.6328,
+      "step": 11346
+    },
+    {
+      "epoch": 0.16428406399815168,
+      "grad_norm": 1.4257746934890747,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6329,
+      "step": 11377
+    },
+    {
+      "epoch": 0.16473170449950905,
+      "grad_norm": 1.2581380605697632,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6298,
+      "step": 11408
+    },
+    {
+      "epoch": 0.1651793450008664,
+      "grad_norm": 2.141317844390869,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.6377,
+      "step": 11439
+    },
+    {
+      "epoch": 0.16562698550222377,
+      "grad_norm": 1.7912797927856445,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6453,
+      "step": 11470
+    },
+    {
+      "epoch": 0.1660746260035811,
+      "grad_norm": 1.0920274257659912,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.6388,
+      "step": 11501
+    },
+    {
+      "epoch": 0.16652226650493848,
+      "grad_norm": 1.3893146514892578,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.6366,
+      "step": 11532
+    },
+    {
+      "epoch": 0.16696990700629585,
+      "grad_norm": 1.510326623916626,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.6289,
+      "step": 11563
+    },
+    {
+      "epoch": 0.1674175475076532,
+      "grad_norm": 1.5738197565078735,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.6291,
+      "step": 11594
+    },
+    {
+      "epoch": 0.16786518800901057,
+      "grad_norm": 1.4003592729568481,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.6331,
+      "step": 11625
+    },
+    {
+      "epoch": 0.16831282851036794,
+      "grad_norm": 1.1500325202941895,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.6288,
+      "step": 11656
+    },
+    {
+      "epoch": 0.16876046901172528,
+      "grad_norm": 1.0949345827102661,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.6338,
+      "step": 11687
+    },
+    {
+      "epoch": 0.16920810951308266,
+      "grad_norm": 1.1545714139938354,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.6253,
+      "step": 11718
+    },
+    {
+      "epoch": 0.16965575001444003,
+      "grad_norm": 1.8404380083084106,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.6331,
+      "step": 11749
+    },
+    {
+      "epoch": 0.17010339051579737,
+      "grad_norm": 1.1443259716033936,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.6266,
+      "step": 11780
+    },
+    {
+      "epoch": 0.17055103101715474,
+      "grad_norm": 2.1884586811065674,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.6255,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1709986715185121,
+      "grad_norm": 1.5698285102844238,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.6354,
+      "step": 11842
+    },
+    {
+      "epoch": 0.17144631201986946,
+      "grad_norm": 1.1452069282531738,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6383,
+      "step": 11873
+    },
+    {
+      "epoch": 0.17189395252122683,
+      "grad_norm": 1.4942229986190796,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6213,
+      "step": 11904
+    },
+    {
+      "epoch": 0.17234159302258417,
+      "grad_norm": 1.8997704982757568,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6239,
+      "step": 11935
+    },
+    {
+      "epoch": 0.17278923352394154,
+      "grad_norm": 1.3202483654022217,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6273,
+      "step": 11966
+    },
+    {
+      "epoch": 0.17323687402529891,
+      "grad_norm": 1.464176058769226,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6337,
+      "step": 11997
+    },
+    {
+      "epoch": 0.17368451452665626,
+      "grad_norm": 1.6081420183181763,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.6329,
+      "step": 12028
+    },
+    {
+      "epoch": 0.17413215502801363,
+      "grad_norm": 1.2481945753097534,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6265,
+      "step": 12059
+    },
+    {
+      "epoch": 0.174579795529371,
+      "grad_norm": 1.096362829208374,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.6293,
+      "step": 12090
+    },
+    {
+      "epoch": 0.17502743603072834,
+      "grad_norm": 1.3475576639175415,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.6411,
+      "step": 12121
+    },
+    {
+      "epoch": 0.17547507653208572,
+      "grad_norm": 1.2768501043319702,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.6375,
+      "step": 12152
+    },
+    {
+      "epoch": 0.1759227170334431,
+      "grad_norm": 2.0324909687042236,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.6263,
+      "step": 12183
+    },
+    {
+      "epoch": 0.17637035753480043,
+      "grad_norm": 1.7318116426467896,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.6312,
+      "step": 12214
+    },
+    {
+      "epoch": 0.1768179980361578,
+      "grad_norm": 1.396030306816101,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.6338,
+      "step": 12245
+    },
+    {
+      "epoch": 0.17726563853751517,
+      "grad_norm": 1.0943025350570679,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.629,
+      "step": 12276
+    },
+    {
+      "epoch": 0.17771327903887252,
+      "grad_norm": 2.2845664024353027,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.6396,
+      "step": 12307
+    },
+    {
+      "epoch": 0.1781609195402299,
+      "grad_norm": 1.2807797193527222,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.6287,
+      "step": 12338
+    },
+    {
+      "epoch": 0.17860856004158723,
+      "grad_norm": 1.3173446655273438,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.6292,
+      "step": 12369
+    },
+    {
+      "epoch": 0.1790562005429446,
+      "grad_norm": 1.8063026666641235,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.6262,
+      "step": 12400
+    },
+    {
+      "epoch": 0.17950384104430198,
+      "grad_norm": 1.218239188194275,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.6311,
+      "step": 12431
+    },
+    {
+      "epoch": 0.17995148154565932,
+      "grad_norm": 1.2154496908187866,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.6301,
+      "step": 12462
+    },
+    {
+      "epoch": 0.1803991220470167,
+      "grad_norm": 1.2854650020599365,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.6357,
+      "step": 12493
+    },
+    {
+      "epoch": 0.18084676254837406,
+      "grad_norm": 1.4721109867095947,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.6256,
+      "step": 12524
+    },
+    {
+      "epoch": 0.1812944030497314,
+      "grad_norm": 1.8752880096435547,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.6306,
+      "step": 12555
+    },
+    {
+      "epoch": 0.18174204355108878,
+      "grad_norm": 1.7632907629013062,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.6351,
+      "step": 12586
+    },
+    {
+      "epoch": 0.18218968405244615,
+      "grad_norm": 1.2561662197113037,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.6287,
+      "step": 12617
+    },
+    {
+      "epoch": 0.1826373245538035,
+      "grad_norm": 1.157389521598816,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.6282,
+      "step": 12648
+    },
+    {
+      "epoch": 0.18308496505516086,
+      "grad_norm": 1.944783091545105,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.6334,
+      "step": 12679
+    },
+    {
+      "epoch": 0.18353260555651824,
+      "grad_norm": 1.325364351272583,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.6308,
+      "step": 12710
+    },
+    {
+      "epoch": 0.18398024605787558,
+      "grad_norm": 6.036927700042725,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.6317,
+      "step": 12741
+    },
+    {
+      "epoch": 0.18442788655923295,
+      "grad_norm": 1.1856430768966675,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.6284,
+      "step": 12772
+    },
+    {
+      "epoch": 0.1848755270605903,
+      "grad_norm": 1.2562810182571411,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.6256,
+      "step": 12803
+    },
+    {
+      "epoch": 0.18532316756194767,
+      "grad_norm": 1.4135706424713135,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.6334,
+      "step": 12834
+    },
+    {
+      "epoch": 0.18577080806330504,
+      "grad_norm": 1.1941848993301392,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.6281,
+      "step": 12865
+    },
+    {
+      "epoch": 0.18621844856466238,
+      "grad_norm": 1.6909502744674683,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.6317,
+      "step": 12896
+    },
+    {
+      "epoch": 0.18666608906601975,
+      "grad_norm": 1.3953163623809814,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.6424,
+      "step": 12927
+    },
+    {
+      "epoch": 0.18711372956737712,
+      "grad_norm": 1.4785979986190796,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.6274,
+      "step": 12958
+    },
+    {
+      "epoch": 0.18756137006873447,
+      "grad_norm": 1.2732242345809937,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.6274,
+      "step": 12989
+    },
+    {
+      "epoch": 0.18800901057009184,
+      "grad_norm": 1.1647322177886963,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.623,
+      "step": 13020
+    },
+    {
+      "epoch": 0.1884566510714492,
+      "grad_norm": 1.3010379076004028,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.6282,
+      "step": 13051
+    },
+    {
+      "epoch": 0.18890429157280655,
+      "grad_norm": 1.1766068935394287,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.6261,
+      "step": 13082
+    },
+    {
+      "epoch": 0.18935193207416393,
+      "grad_norm": 1.486527681350708,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.6232,
+      "step": 13113
+    },
+    {
+      "epoch": 0.1897995725755213,
+      "grad_norm": 1.417598843574524,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.6256,
+      "step": 13144
+    },
+    {
+      "epoch": 0.19024721307687864,
+      "grad_norm": 1.076657772064209,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.6182,
+      "step": 13175
+    },
+    {
+      "epoch": 0.190694853578236,
+      "grad_norm": 1.3538635969161987,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.6281,
+      "step": 13206
+    },
+    {
+      "epoch": 0.19114249407959336,
+      "grad_norm": 1.266701579093933,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.6229,
+      "step": 13237
+    },
+    {
+      "epoch": 0.19159013458095073,
+      "grad_norm": 1.7953287363052368,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.6242,
+      "step": 13268
+    },
+    {
+      "epoch": 0.1920377750823081,
+      "grad_norm": 1.4497145414352417,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.6247,
+      "step": 13299
+    },
+    {
+      "epoch": 0.19248541558366544,
+      "grad_norm": 1.4819296598434448,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.6258,
+      "step": 13330
+    },
+    {
+      "epoch": 0.1929330560850228,
+      "grad_norm": 1.0778093338012695,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.6194,
+      "step": 13361
+    },
+    {
+      "epoch": 0.19338069658638019,
+      "grad_norm": 1.067001223564148,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.6257,
+      "step": 13392
+    },
+    {
+      "epoch": 0.19382833708773753,
+      "grad_norm": 1.6597830057144165,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.6354,
+      "step": 13423
+    },
+    {
+      "epoch": 0.1942759775890949,
+      "grad_norm": 1.4284085035324097,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.6233,
+      "step": 13454
+    },
+    {
+      "epoch": 0.19472361809045227,
+      "grad_norm": 1.386055588722229,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.6355,
+      "step": 13485
+    },
+    {
+      "epoch": 0.19517125859180962,
+      "grad_norm": 1.1730949878692627,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.6273,
+      "step": 13516
+    },
+    {
+      "epoch": 0.195618899093167,
+      "grad_norm": 1.62460458278656,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.6177,
+      "step": 13547
+    },
+    {
+      "epoch": 0.19606653959452436,
+      "grad_norm": 0.983518660068512,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.6232,
+      "step": 13578
+    },
+    {
+      "epoch": 0.1965141800958817,
+      "grad_norm": 1.1250189542770386,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.6225,
+      "step": 13609
+    },
+    {
+      "epoch": 0.19696182059723907,
+      "grad_norm": 1.7201340198516846,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.627,
+      "step": 13640
+    },
+    {
+      "epoch": 0.19740946109859642,
+      "grad_norm": 1.4898096323013306,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.6288,
+      "step": 13671
+    },
+    {
+      "epoch": 0.1978571015999538,
+      "grad_norm": 2.0321242809295654,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.6207,
+      "step": 13702
+    },
+    {
+      "epoch": 0.19830474210131116,
+      "grad_norm": 1.0331289768218994,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.6285,
+      "step": 13733
+    },
+    {
+      "epoch": 0.1987523826026685,
+      "grad_norm": 1.5261441469192505,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.6269,
+      "step": 13764
+    },
+    {
+      "epoch": 0.19920002310402588,
+      "grad_norm": 1.9195454120635986,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.6224,
+      "step": 13795
+    },
+    {
+      "epoch": 0.19964766360538325,
+      "grad_norm": 1.4765523672103882,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.6171,
+      "step": 13826
+    },
+    {
+      "epoch": 0.2000953041067406,
+      "grad_norm": 1.3098200559616089,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.6228,
+      "step": 13857
+    },
+    {
+      "epoch": 0.20054294460809796,
+      "grad_norm": 1.5324469804763794,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.6197,
+      "step": 13888
+    },
+    {
+      "epoch": 0.20099058510945533,
+      "grad_norm": 1.2556509971618652,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.6275,
+      "step": 13919
+    },
+    {
+      "epoch": 0.20143822561081268,
+      "grad_norm": 1.0882678031921387,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.6324,
+      "step": 13950
+    },
+    {
+      "epoch": 0.20188586611217005,
+      "grad_norm": 1.974104881286621,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.6291,
+      "step": 13981
+    },
+    {
+      "epoch": 0.20233350661352742,
+      "grad_norm": 1.478338599205017,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.6258,
+      "step": 14012
+    },
+    {
+      "epoch": 0.20278114711488476,
+      "grad_norm": 2.2389965057373047,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.6197,
+      "step": 14043
+    },
+    {
+      "epoch": 0.20322878761624213,
+      "grad_norm": 1.1947026252746582,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6182,
+      "step": 14074
+    },
+    {
+      "epoch": 0.20367642811759948,
+      "grad_norm": 1.3395119905471802,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.6214,
+      "step": 14105
+    },
+    {
+      "epoch": 0.20412406861895685,
+      "grad_norm": 1.6894941329956055,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.6224,
+      "step": 14136
+    },
+    {
+      "epoch": 0.20457170912031422,
+      "grad_norm": 1.29898202419281,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.6328,
+      "step": 14167
+    },
+    {
+      "epoch": 0.20501934962167156,
+      "grad_norm": 1.1610809564590454,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.6246,
+      "step": 14198
+    },
+    {
+      "epoch": 0.20546699012302894,
+      "grad_norm": 1.3604459762573242,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.622,
+      "step": 14229
+    },
+    {
+      "epoch": 0.2059146306243863,
+      "grad_norm": 1.1559162139892578,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.6255,
+      "step": 14260
+    },
+    {
+      "epoch": 0.20636227112574365,
+      "grad_norm": 1.2945172786712646,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.6246,
+      "step": 14291
+    },
+    {
+      "epoch": 0.20680991162710102,
+      "grad_norm": 1.0370653867721558,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.6293,
+      "step": 14322
+    },
+    {
+      "epoch": 0.2072575521284584,
+      "grad_norm": 1.00487220287323,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.6176,
+      "step": 14353
+    },
+    {
+      "epoch": 0.20770519262981574,
+      "grad_norm": 1.7619637250900269,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.6186,
+      "step": 14384
+    },
+    {
+      "epoch": 0.2081528331311731,
+      "grad_norm": 1.5078710317611694,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.6228,
+      "step": 14415
+    },
+    {
+      "epoch": 0.20860047363253048,
+      "grad_norm": 2.049180030822754,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.6199,
+      "step": 14446
+    },
+    {
+      "epoch": 0.20904811413388782,
+      "grad_norm": 1.4279115200042725,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.619,
+      "step": 14477
+    },
+    {
+      "epoch": 0.2094957546352452,
+      "grad_norm": 1.566404104232788,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.6145,
+      "step": 14508
+    },
+    {
+      "epoch": 0.20994339513660254,
+      "grad_norm": 1.2448210716247559,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.6202,
+      "step": 14539
+    },
+    {
+      "epoch": 0.2103910356379599,
+      "grad_norm": 1.2128769159317017,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.6188,
+      "step": 14570
+    },
+    {
+      "epoch": 0.21083867613931728,
+      "grad_norm": 0.9219493865966797,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.6234,
+      "step": 14601
+    },
+    {
+      "epoch": 0.21128631664067463,
+      "grad_norm": 1.066727876663208,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.6185,
+      "step": 14632
+    },
+    {
+      "epoch": 0.211733957142032,
+      "grad_norm": 1.240938425064087,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.6271,
+      "step": 14663
+    },
+    {
+      "epoch": 0.21218159764338937,
+      "grad_norm": 1.1495387554168701,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.6183,
+      "step": 14694
+    },
+    {
+      "epoch": 0.2126292381447467,
+      "grad_norm": 1.2447069883346558,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.6189,
+      "step": 14725
+    },
+    {
+      "epoch": 0.21307687864610408,
+      "grad_norm": 1.1033343076705933,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.6126,
+      "step": 14756
+    },
+    {
+      "epoch": 0.21352451914746146,
+      "grad_norm": 1.050188422203064,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.6161,
+      "step": 14787
+    },
+    {
+      "epoch": 0.2139721596488188,
+      "grad_norm": 1.3965789079666138,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.6119,
+      "step": 14818
+    },
+    {
+      "epoch": 0.21441980015017617,
+      "grad_norm": 1.3627980947494507,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.6183,
+      "step": 14849
+    },
+    {
+      "epoch": 0.21486744065153354,
+      "grad_norm": 1.3708971738815308,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.623,
+      "step": 14880
+    },
+    {
+      "epoch": 0.21531508115289089,
+      "grad_norm": 1.2827285528182983,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.6188,
+      "step": 14911
+    },
+    {
+      "epoch": 0.21576272165424826,
+      "grad_norm": 1.0264792442321777,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.624,
+      "step": 14942
+    },
+    {
+      "epoch": 0.2162103621556056,
+      "grad_norm": 1.0395159721374512,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.6152,
+      "step": 14973
+    },
+    {
+      "epoch": 0.21665800265696297,
+      "grad_norm": 1.8033519983291626,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.6308,
+      "step": 15004
+    },
+    {
+      "epoch": 0.21710564315832034,
+      "grad_norm": 1.1783379316329956,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.6201,
+      "step": 15035
+    },
+    {
+      "epoch": 0.2175532836596777,
+      "grad_norm": 1.4674829244613647,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6223,
+      "step": 15066
+    },
+    {
+      "epoch": 0.21800092416103506,
+      "grad_norm": 1.4250842332839966,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.6205,
+      "step": 15097
+    },
+    {
+      "epoch": 0.21844856466239243,
+      "grad_norm": 1.0817009210586548,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.6145,
+      "step": 15128
+    },
+    {
+      "epoch": 0.21889620516374977,
+      "grad_norm": 1.1512938737869263,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.615,
+      "step": 15159
+    },
+    {
+      "epoch": 0.21934384566510715,
+      "grad_norm": 1.5644307136535645,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.6127,
+      "step": 15190
+    },
+    {
+      "epoch": 0.21979148616646452,
+      "grad_norm": 1.3980814218521118,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6248,
+      "step": 15221
+    },
+    {
+      "epoch": 0.22023912666782186,
+      "grad_norm": 1.1034141778945923,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.6157,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1258280394232955e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326c2ae4159344fc785388c97ab51f9004242fca8111ff540004b508cfbcb169
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-18312/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafa95613d23e8fc742db7e127940a166c58391be0c8d4e8340a94beb6135825
+size 4886466168

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fa5aaf8ac56c17c821980c9aee44fcbc2a617fc570e875e6fdb93d92886c72
+size 4832007448

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a223e87240e50dfb05634ea909cf1ec715d37a12b681b14a3a6e97f28688f2b
+size 4999813112

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3047d199c611c6d12b1cca780f033ad89df9c076f742674f7ac4a892ca9573b3
+size 4999813128

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2f91d749d664ecd22c71f3d54488966fc6899a03924b8fea3613c8f83398a8
+size 4832007496

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655e7ed201255da245df1dfd252e3ab9423a9e7652529249d4e64e6ee73aaaba
+size 4999813120

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140c48e7fa382f7eeb5fb72b96ae1dcd747bbde4d9fc13985b699b4db2c6dd3e
+size 2571158184

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-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-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-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-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-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-00006-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-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce278439605a19c359c19deefef82b6aa8b39fada6ea249cf9c23bb5c46573ea
+size 15385036334

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326c2ae4159344fc785388c97ab51f9004242fca8111ff540004b508cfbcb169
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-21364/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c60a5f43734ba9808978bb225526946bf4244002fb1a4196084701a04f88956
+size 4886466168

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fa5aaf8ac56c17c821980c9aee44fcbc2a617fc570e875e6fdb93d92886c72
+size 4832007448

checkpoint-21364/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a223e87240e50dfb05634ea909cf1ec715d37a12b681b14a3a6e97f28688f2b
+size 4999813112