Add files using upload-large-folder tool

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "Emu3ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "auto_map": {
+    "AutoConfig": "BAAI/Emu3-Stage1--configuration_emu3.Emu3Config",
+    "AutoModelForCausalLM": "BAAI/Emu3-Stage1--modeling_emu3.Emu3ForCausalLM"
+  },
+  "boi_token_id": 151852,
+  "bos_token_id": 151849,
+  "eof_token_id": 151847,
+  "eoi_token_id": 151853,
+  "eol_token_id": 151846,
+  "eos_token_id": 151850,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_area": 65536,
+  "img_token_id": 151851,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4300,
+  "model_type": "Emu3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 184622
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151849,
+  "eos_token_id": 151850,
+  "pad_token_id": 151643,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edbebb8eca543254dc1389227b72b02e57139bcbc47f357df780c3fa76692c0
+size 4884766656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf8fceb3fe431202b0dae67639d116b3a3965f361d7246e551b5058c191569a
+size 4999819320

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9cb17abdbaf1b281b61d22cf58666e56a3039ef3db32abf17387e6f83c58154
+size 4915916184

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe52df896047eec2b95571362a6a7855d7aa203511662b58bf0e51e768a5ac7
+size 2183554760

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16984023040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7453da2134e4d357848222c6dc48fd0a0dac2ef99070ac837e1f1de84e4a590
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b1ee8dbb604a9a0a5ca0ea336e8b77b4136c673f28826d516058e4da75adae
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783d904c2eff3806e7d17e1d9d0a31326f480dc99e9d2229a72054ae5ca080b4
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e74550e331788b35f4827e121efed1e8f8d74b222eae676299a5a6a50a0bf2
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59ccff08919b9abb99e5c65cd13037a2392d6b7f49846d255aa8091373f38b9
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21b12c5b2d26e24aa59c7b08bf6e6e51434cdf7c236741972590dbb341b3b40
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9dcc293c1cc86f1c283d4ce4a50e3a3a039bf7aa0402b77352faf8714fdc1f
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd34820b3fd7404de24ae53aa470e883f0a7d20de781389876f763334b8226c
+size 15984

trainer_state.json

@@ -0,0 +1,2498 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.8994865546949784,
+  "eval_steps": 100,
+  "global_step": 11200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017404925593943087,
+      "grad_norm": 6.07357337417729,
+      "learning_rate": 4.9e-05,
+      "loss": 3.6087,
+      "step": 50
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "grad_norm": 3.5663292481821296,
+      "learning_rate": 4.999971170608479e-05,
+      "loss": 2.545,
+      "step": 100
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "eval_loss": 2.3234446048736572,
+      "eval_runtime": 13.9956,
+      "eval_samples_per_second": 71.451,
+      "eval_steps_per_second": 2.286,
+      "step": 100
+    },
+    {
+      "epoch": 0.05221477678182926,
+      "grad_norm": 3.76347751871297,
+      "learning_rate": 4.999882317878336e-05,
+      "loss": 2.2721,
+      "step": 150
+    },
+    {
+      "epoch": 0.06961970237577235,
+      "grad_norm": 6.121069966490686,
+      "learning_rate": 4.99973343246949e-05,
+      "loss": 2.0721,
+      "step": 200
+    },
+    {
+      "epoch": 0.06961970237577235,
+      "eval_loss": 1.9963123798370361,
+      "eval_runtime": 14.05,
+      "eval_samples_per_second": 71.174,
+      "eval_steps_per_second": 2.278,
+      "step": 200
+    },
+    {
+      "epoch": 0.08702462796971543,
+      "grad_norm": 2.0071155926776294,
+      "learning_rate": 4.9995245188511975e-05,
+      "loss": 1.9929,
+      "step": 250
+    },
+    {
+      "epoch": 0.10442955356365852,
+      "grad_norm": 1.7760725594180993,
+      "learning_rate": 4.9992555832946495e-05,
+      "loss": 1.9184,
+      "step": 300
+    },
+    {
+      "epoch": 0.10442955356365852,
+      "eval_loss": 1.8656612634658813,
+      "eval_runtime": 13.9964,
+      "eval_samples_per_second": 71.447,
+      "eval_steps_per_second": 2.286,
+      "step": 300
+    },
+    {
+      "epoch": 0.12183447915760161,
+      "grad_norm": 1.8447005346692253,
+      "learning_rate": 4.9989266338727845e-05,
+      "loss": 1.8957,
+      "step": 350
+    },
+    {
+      "epoch": 0.1392394047515447,
+      "grad_norm": 2.304515920283501,
+      "learning_rate": 4.998537680460039e-05,
+      "loss": 1.8629,
+      "step": 400
+    },
+    {
+      "epoch": 0.1392394047515447,
+      "eval_loss": 1.8171635866165161,
+      "eval_runtime": 14.0311,
+      "eval_samples_per_second": 71.27,
+      "eval_steps_per_second": 2.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.15664433034548778,
+      "grad_norm": 2.028746062309368,
+      "learning_rate": 4.998088734732058e-05,
+      "loss": 1.8457,
+      "step": 450
+    },
+    {
+      "epoch": 0.17404925593943085,
+      "grad_norm": 1.5394435777337994,
+      "learning_rate": 4.997579810165342e-05,
+      "loss": 1.8232,
+      "step": 500
+    },
+    {
+      "epoch": 0.17404925593943085,
+      "eval_loss": 1.7938146591186523,
+      "eval_runtime": 13.9792,
+      "eval_samples_per_second": 71.535,
+      "eval_steps_per_second": 2.289,
+      "step": 500
+    },
+    {
+      "epoch": 0.19145418153337396,
+      "grad_norm": 1.890814268154515,
+      "learning_rate": 4.997010922036841e-05,
+      "loss": 1.8101,
+      "step": 550
+    },
+    {
+      "epoch": 0.20885910712731703,
+      "grad_norm": 2.872076377134816,
+      "learning_rate": 4.9963820874235e-05,
+      "loss": 1.7842,
+      "step": 600
+    },
+    {
+      "epoch": 0.20885910712731703,
+      "eval_loss": 1.779714584350586,
+      "eval_runtime": 13.9665,
+      "eval_samples_per_second": 71.6,
+      "eval_steps_per_second": 2.291,
+      "step": 600
+    },
+    {
+      "epoch": 0.2262640327212601,
+      "grad_norm": 2.481027223933055,
+      "learning_rate": 4.995693325201745e-05,
+      "loss": 1.794,
+      "step": 650
+    },
+    {
+      "epoch": 0.24366895831520322,
+      "grad_norm": 0.8094796094808727,
+      "learning_rate": 4.99494465604691e-05,
+      "loss": 1.7793,
+      "step": 700
+    },
+    {
+      "epoch": 0.24366895831520322,
+      "eval_loss": 1.7532519102096558,
+      "eval_runtime": 14.0406,
+      "eval_samples_per_second": 71.222,
+      "eval_steps_per_second": 2.279,
+      "step": 700
+    },
+    {
+      "epoch": 0.26107388390914626,
+      "grad_norm": 1.2444472352367841,
+      "learning_rate": 4.994136102432626e-05,
+      "loss": 1.7694,
+      "step": 750
+    },
+    {
+      "epoch": 0.2784788095030894,
+      "grad_norm": 3.529061157225736,
+      "learning_rate": 4.99326768863014e-05,
+      "loss": 1.7661,
+      "step": 800
+    },
+    {
+      "epoch": 0.2784788095030894,
+      "eval_loss": 1.75984525680542,
+      "eval_runtime": 13.9384,
+      "eval_samples_per_second": 71.744,
+      "eval_steps_per_second": 2.296,
+      "step": 800
+    },
+    {
+      "epoch": 0.2958837350970325,
+      "grad_norm": 1.377228521670443,
+      "learning_rate": 4.992339440707591e-05,
+      "loss": 1.7622,
+      "step": 850
+    },
+    {
+      "epoch": 0.31328866069097555,
+      "grad_norm": 1.6693867914447456,
+      "learning_rate": 4.991351386529222e-05,
+      "loss": 1.753,
+      "step": 900
+    },
+    {
+      "epoch": 0.31328866069097555,
+      "eval_loss": 1.72667396068573,
+      "eval_runtime": 14.0823,
+      "eval_samples_per_second": 71.011,
+      "eval_steps_per_second": 2.272,
+      "step": 900
+    },
+    {
+      "epoch": 0.33069358628491863,
+      "grad_norm": 1.7888888121121684,
+      "learning_rate": 4.9903035557545474e-05,
+      "loss": 1.7394,
+      "step": 950
+    },
+    {
+      "epoch": 0.3480985118788617,
+      "grad_norm": 1.1475145633011983,
+      "learning_rate": 4.9891959798374635e-05,
+      "loss": 1.7418,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3480985118788617,
+      "eval_loss": 1.7262976169586182,
+      "eval_runtime": 13.9499,
+      "eval_samples_per_second": 71.685,
+      "eval_steps_per_second": 2.294,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3655034374728048,
+      "grad_norm": 1.2690065543406053,
+      "learning_rate": 4.9880286920252995e-05,
+      "loss": 1.7323,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3829083630667479,
+      "grad_norm": 1.3554029672368741,
+      "learning_rate": 4.986801727357825e-05,
+      "loss": 1.7214,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3829083630667479,
+      "eval_loss": 1.7105458974838257,
+      "eval_runtime": 14.0176,
+      "eval_samples_per_second": 71.339,
+      "eval_steps_per_second": 2.283,
+      "step": 1100
+    },
+    {
+      "epoch": 0.400313288660691,
+      "grad_norm": 1.1363622763657797,
+      "learning_rate": 4.9855151226661954e-05,
+      "loss": 1.7249,
+      "step": 1150
+    },
+    {
+      "epoch": 0.41771821425463407,
+      "grad_norm": 0.821944816072442,
+      "learning_rate": 4.984168916571846e-05,
+      "loss": 1.7315,
+      "step": 1200
+    },
+    {
+      "epoch": 0.41771821425463407,
+      "eval_loss": 1.7037900686264038,
+      "eval_runtime": 13.9751,
+      "eval_samples_per_second": 71.556,
+      "eval_steps_per_second": 2.29,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43512313984857715,
+      "grad_norm": 1.2782341420995915,
+      "learning_rate": 4.9827631494853346e-05,
+      "loss": 1.734,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4525280654425202,
+      "grad_norm": 0.9283632211124734,
+      "learning_rate": 4.9812978636051235e-05,
+      "loss": 1.7198,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4525280654425202,
+      "eval_loss": 1.6981171369552612,
+      "eval_runtime": 14.0083,
+      "eval_samples_per_second": 71.386,
+      "eval_steps_per_second": 2.284,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4699329910364633,
+      "grad_norm": 1.0677942729129404,
+      "learning_rate": 4.9797731029163206e-05,
+      "loss": 1.7041,
+      "step": 1350
+    },
+    {
+      "epoch": 0.48733791663040643,
+      "grad_norm": 1.1328848186202982,
+      "learning_rate": 4.978188913189354e-05,
+      "loss": 1.7106,
+      "step": 1400
+    },
+    {
+      "epoch": 0.48733791663040643,
+      "eval_loss": 1.6910983324050903,
+      "eval_runtime": 13.9325,
+      "eval_samples_per_second": 71.775,
+      "eval_steps_per_second": 2.297,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5047428422243495,
+      "grad_norm": 0.8854373258207832,
+      "learning_rate": 4.976545341978598e-05,
+      "loss": 1.7079,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5221477678182925,
+      "grad_norm": 1.5301565843095193,
+      "learning_rate": 4.9748424386209455e-05,
+      "loss": 1.7065,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5221477678182925,
+      "eval_loss": 1.6862553358078003,
+      "eval_runtime": 14.0162,
+      "eval_samples_per_second": 71.346,
+      "eval_steps_per_second": 2.283,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5395526934122357,
+      "grad_norm": 1.4228459883867106,
+      "learning_rate": 4.973080254234331e-05,
+      "loss": 1.7037,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5569576190061788,
+      "grad_norm": 0.8012113010542086,
+      "learning_rate": 4.971258841716191e-05,
+      "loss": 1.695,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5569576190061788,
+      "eval_loss": 1.6799589395523071,
+      "eval_runtime": 13.9995,
+      "eval_samples_per_second": 71.431,
+      "eval_steps_per_second": 2.286,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5743625446001218,
+      "grad_norm": 1.190690319783776,
+      "learning_rate": 4.969378255741879e-05,
+      "loss": 1.69,
+      "step": 1650
+    },
+    {
+      "epoch": 0.591767470194065,
+      "grad_norm": 0.8887720624675962,
+      "learning_rate": 4.967438552763023e-05,
+      "loss": 1.7013,
+      "step": 1700
+    },
+    {
+      "epoch": 0.591767470194065,
+      "eval_loss": 1.6794394254684448,
+      "eval_runtime": 14.0089,
+      "eval_samples_per_second": 71.383,
+      "eval_steps_per_second": 2.284,
+      "step": 1700
+    },
+    {
+      "epoch": 0.609172395788008,
+      "grad_norm": 0.7315204698775325,
+      "learning_rate": 4.9654397910058326e-05,
+      "loss": 1.6958,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6265773213819511,
+      "grad_norm": 0.9699559384796247,
+      "learning_rate": 4.963382030469349e-05,
+      "loss": 1.6788,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6265773213819511,
+      "eval_loss": 1.6714988946914673,
+      "eval_runtime": 14.0096,
+      "eval_samples_per_second": 71.379,
+      "eval_steps_per_second": 2.284,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6439822469758941,
+      "grad_norm": 0.8473820751122184,
+      "learning_rate": 4.9612653329236446e-05,
+      "loss": 1.6879,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6613871725698373,
+      "grad_norm": 1.0060512118979683,
+      "learning_rate": 4.959089761907972e-05,
+      "loss": 1.6724,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6613871725698373,
+      "eval_loss": 1.6676414012908936,
+      "eval_runtime": 13.9883,
+      "eval_samples_per_second": 71.488,
+      "eval_steps_per_second": 2.288,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6787920981637804,
+      "grad_norm": 1.6044912820626946,
+      "learning_rate": 4.95685538272885e-05,
+      "loss": 1.6811,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6961970237577234,
+      "grad_norm": 0.9205203899330789,
+      "learning_rate": 4.95456226245811e-05,
+      "loss": 1.6807,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6961970237577234,
+      "eval_loss": 1.664583444595337,
+      "eval_runtime": 13.9774,
+      "eval_samples_per_second": 71.544,
+      "eval_steps_per_second": 2.289,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7136019493516665,
+      "grad_norm": 1.3251835254853215,
+      "learning_rate": 4.952210469930877e-05,
+      "loss": 1.6798,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7310068749456096,
+      "grad_norm": 0.9832051746397106,
+      "learning_rate": 4.949800075743509e-05,
+      "loss": 1.677,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7310068749456096,
+      "eval_loss": 1.6596543788909912,
+      "eval_runtime": 14.0141,
+      "eval_samples_per_second": 71.357,
+      "eval_steps_per_second": 2.283,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7484118005395527,
+      "grad_norm": 1.2949214337555768,
+      "learning_rate": 4.947331152251474e-05,
+      "loss": 1.6645,
+      "step": 2150
+    },
+    {
+      "epoch": 0.7658167261334958,
+      "grad_norm": 1.0901276287938682,
+      "learning_rate": 4.9448037735671757e-05,
+      "loss": 1.6681,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7658167261334958,
+      "eval_loss": 1.65700364112854,
+      "eval_runtime": 14.0206,
+      "eval_samples_per_second": 71.323,
+      "eval_steps_per_second": 2.282,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7832216517274389,
+      "grad_norm": 1.048369032858913,
+      "learning_rate": 4.942218015557737e-05,
+      "loss": 1.6695,
+      "step": 2250
+    },
+    {
+      "epoch": 0.800626577321382,
+      "grad_norm": 1.211637616168943,
+      "learning_rate": 4.939573955842714e-05,
+      "loss": 1.6642,
+      "step": 2300
+    },
+    {
+      "epoch": 0.800626577321382,
+      "eval_loss": 1.6546015739440918,
+      "eval_runtime": 13.9713,
+      "eval_samples_per_second": 71.575,
+      "eval_steps_per_second": 2.29,
+      "step": 2300
+    },
+    {
+      "epoch": 0.818031502915325,
+      "grad_norm": 1.1547651007185253,
+      "learning_rate": 4.93687167379177e-05,
+      "loss": 1.6666,
+      "step": 2350
+    },
+    {
+      "epoch": 0.8354364285092681,
+      "grad_norm": 0.8815838845151333,
+      "learning_rate": 4.934111250522293e-05,
+      "loss": 1.6704,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8354364285092681,
+      "eval_loss": 1.6485086679458618,
+      "eval_runtime": 13.9864,
+      "eval_samples_per_second": 71.498,
+      "eval_steps_per_second": 2.288,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8528413541032112,
+      "grad_norm": 1.2788967756098748,
+      "learning_rate": 4.9312927688969614e-05,
+      "loss": 1.6665,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8702462796971543,
+      "grad_norm": 1.0757149545926434,
+      "learning_rate": 4.9284163135212544e-05,
+      "loss": 1.6586,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8702462796971543,
+      "eval_loss": 1.6465007066726685,
+      "eval_runtime": 14.0157,
+      "eval_samples_per_second": 71.348,
+      "eval_steps_per_second": 2.283,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8876512052910974,
+      "grad_norm": 0.9368397945653969,
+      "learning_rate": 4.925481970740913e-05,
+      "loss": 1.6622,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9050561308850404,
+      "grad_norm": 1.2877310576716585,
+      "learning_rate": 4.9224898286393486e-05,
+      "loss": 1.6532,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9050561308850404,
+      "eval_loss": 1.6464436054229736,
+      "eval_runtime": 14.0065,
+      "eval_samples_per_second": 71.395,
+      "eval_steps_per_second": 2.285,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9224610564789836,
+      "grad_norm": 1.1714391439428165,
+      "learning_rate": 4.919439977034997e-05,
+      "loss": 1.6512,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9398659820729266,
+      "grad_norm": 1.11375610693323,
+      "learning_rate": 4.916332507478631e-05,
+      "loss": 1.6408,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9398659820729266,
+      "eval_loss": 1.6425988674163818,
+      "eval_runtime": 13.9384,
+      "eval_samples_per_second": 71.744,
+      "eval_steps_per_second": 2.296,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9572709076668697,
+      "grad_norm": 0.740049431872551,
+      "learning_rate": 4.913167513250595e-05,
+      "loss": 1.648,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9746758332608129,
+      "grad_norm": 1.353726058408381,
+      "learning_rate": 4.909945089358022e-05,
+      "loss": 1.6464,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9746758332608129,
+      "eval_loss": 1.6430168151855469,
+      "eval_runtime": 13.9818,
+      "eval_samples_per_second": 71.521,
+      "eval_steps_per_second": 2.289,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9920807588547559,
+      "grad_norm": 0.7896432929313317,
+      "learning_rate": 4.906665332531975e-05,
+      "loss": 1.6523,
+      "step": 2850
+    },
+    {
+      "epoch": 1.009746758332608,
+      "grad_norm": 0.7591020143028239,
+      "learning_rate": 4.903328341224537e-05,
+      "loss": 1.6531,
+      "step": 2900
+    },
+    {
+      "epoch": 1.009746758332608,
+      "eval_loss": 1.636893630027771,
+      "eval_runtime": 14.0408,
+      "eval_samples_per_second": 71.221,
+      "eval_steps_per_second": 2.279,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0271516839265513,
+      "grad_norm": 0.785567616684764,
+      "learning_rate": 4.899934215605867e-05,
+      "loss": 1.6095,
+      "step": 2950
+    },
+    {
+      "epoch": 1.0445566095204943,
+      "grad_norm": 0.6496709588539313,
+      "learning_rate": 4.8964830575611876e-05,
+      "loss": 1.6169,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0445566095204943,
+      "eval_loss": 1.6327561140060425,
+      "eval_runtime": 14.0121,
+      "eval_samples_per_second": 71.367,
+      "eval_steps_per_second": 2.284,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0619615351144374,
+      "grad_norm": 1.0307342387456608,
+      "learning_rate": 4.8929749706877246e-05,
+      "loss": 1.6061,
+      "step": 3050
+    },
+    {
+      "epoch": 1.0793664607083804,
+      "grad_norm": 0.8079301722246791,
+      "learning_rate": 4.8894100602916016e-05,
+      "loss": 1.6199,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0793664607083804,
+      "eval_loss": 1.6337392330169678,
+      "eval_runtime": 14.0185,
+      "eval_samples_per_second": 71.334,
+      "eval_steps_per_second": 2.283,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0967713863023236,
+      "grad_norm": 0.7473705601316266,
+      "learning_rate": 4.8857884333846735e-05,
+      "loss": 1.6114,
+      "step": 3150
+    },
+    {
+      "epoch": 1.1141763118962666,
+      "grad_norm": 1.2192071702470884,
+      "learning_rate": 4.882110198681321e-05,
+      "loss": 1.6094,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1141763118962666,
+      "eval_loss": 1.6318168640136719,
+      "eval_runtime": 13.9864,
+      "eval_samples_per_second": 71.498,
+      "eval_steps_per_second": 2.288,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1315812374902097,
+      "grad_norm": 0.9888531694645865,
+      "learning_rate": 4.878375466595181e-05,
+      "loss": 1.6139,
+      "step": 3250
+    },
+    {
+      "epoch": 1.148986163084153,
+      "grad_norm": 0.8550909287275011,
+      "learning_rate": 4.874584349235836e-05,
+      "loss": 1.601,
+      "step": 3300
+    },
+    {
+      "epoch": 1.148986163084153,
+      "eval_loss": 1.6282851696014404,
+      "eval_runtime": 13.9933,
+      "eval_samples_per_second": 71.463,
+      "eval_steps_per_second": 2.287,
+      "step": 3300
+    },
+    {
+      "epoch": 1.166391088678096,
+      "grad_norm": 1.2063759248291055,
+      "learning_rate": 4.8707369604054474e-05,
+      "loss": 1.5998,
+      "step": 3350
+    },
+    {
+      "epoch": 1.183796014272039,
+      "grad_norm": 0.6341552384920974,
+      "learning_rate": 4.866833415595341e-05,
+      "loss": 1.6082,
+      "step": 3400
+    },
+    {
+      "epoch": 1.183796014272039,
+      "eval_loss": 1.6227760314941406,
+      "eval_runtime": 14.032,
+      "eval_samples_per_second": 71.266,
+      "eval_steps_per_second": 2.281,
+      "step": 3400
+    },
+    {
+      "epoch": 1.201200939865982,
+      "grad_norm": 0.675165295355897,
+      "learning_rate": 4.8628738319825365e-05,
+      "loss": 1.5991,
+      "step": 3450
+    },
+    {
+      "epoch": 1.2186058654599252,
+      "grad_norm": 0.9698012232943588,
+      "learning_rate": 4.8588583284262324e-05,
+      "loss": 1.6175,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2186058654599252,
+      "eval_loss": 1.6227885484695435,
+      "eval_runtime": 13.9808,
+      "eval_samples_per_second": 71.527,
+      "eval_steps_per_second": 2.289,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2360107910538682,
+      "grad_norm": 0.7064806896703955,
+      "learning_rate": 4.854787025464238e-05,
+      "loss": 1.6003,
+      "step": 3550
+    },
+    {
+      "epoch": 1.2534157166478113,
+      "grad_norm": 0.5984772772171928,
+      "learning_rate": 4.850660045309358e-05,
+      "loss": 1.6061,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2534157166478113,
+      "eval_loss": 1.619645118713379,
+      "eval_runtime": 14.0435,
+      "eval_samples_per_second": 71.207,
+      "eval_steps_per_second": 2.279,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2708206422417545,
+      "grad_norm": 0.8428216369485679,
+      "learning_rate": 4.8464775118457174e-05,
+      "loss": 1.6033,
+      "step": 3650
+    },
+    {
+      "epoch": 1.2882255678356975,
+      "grad_norm": 1.0213649998959717,
+      "learning_rate": 4.842239550625048e-05,
+      "loss": 1.6101,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2882255678356975,
+      "eval_loss": 1.619710922241211,
+      "eval_runtime": 13.9393,
+      "eval_samples_per_second": 71.739,
+      "eval_steps_per_second": 2.296,
+      "step": 3700
+    },
+    {
+      "epoch": 1.3056304934296405,
+      "grad_norm": 1.0089461514034055,
+      "learning_rate": 4.8379462888629166e-05,
+      "loss": 1.5997,
+      "step": 3750
+    },
+    {
+      "epoch": 1.3230354190235838,
+      "grad_norm": 0.7527069966901813,
+      "learning_rate": 4.8335978554349094e-05,
+      "loss": 1.5978,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3230354190235838,
+      "eval_loss": 1.6153150796890259,
+      "eval_runtime": 13.9935,
+      "eval_samples_per_second": 71.462,
+      "eval_steps_per_second": 2.287,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3404403446175268,
+      "grad_norm": 0.6599591226592018,
+      "learning_rate": 4.8291943808727605e-05,
+      "loss": 1.6024,
+      "step": 3850
+    },
+    {
+      "epoch": 1.3578452702114698,
+      "grad_norm": 0.7292499200644743,
+      "learning_rate": 4.8247359973604324e-05,
+      "loss": 1.6123,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3578452702114698,
+      "eval_loss": 1.612821102142334,
+      "eval_runtime": 13.9912,
+      "eval_samples_per_second": 71.474,
+      "eval_steps_per_second": 2.287,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3752501958054129,
+      "grad_norm": 1.1210984888321722,
+      "learning_rate": 4.8202228387301554e-05,
+      "loss": 1.595,
+      "step": 3950
+    },
+    {
+      "epoch": 1.392655121399356,
+      "grad_norm": 0.5893087273399503,
+      "learning_rate": 4.8156550404584e-05,
+      "loss": 1.6056,
+      "step": 4000
+    },
+    {
+      "epoch": 1.392655121399356,
+      "eval_loss": 1.6076596975326538,
+      "eval_runtime": 14.0138,
+      "eval_samples_per_second": 71.358,
+      "eval_steps_per_second": 2.283,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4100600469932991,
+      "grad_norm": 1.1601240317764614,
+      "learning_rate": 4.81103273966182e-05,
+      "loss": 1.591,
+      "step": 4050
+    },
+    {
+      "epoch": 1.4274649725872421,
+      "grad_norm": 0.6658774333699882,
+      "learning_rate": 4.806356075093125e-05,
+      "loss": 1.5944,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4274649725872421,
+      "eval_loss": 1.6094013452529907,
+      "eval_runtime": 13.9967,
+      "eval_samples_per_second": 71.445,
+      "eval_steps_per_second": 2.286,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4448698981811852,
+      "grad_norm": 0.9722493291962953,
+      "learning_rate": 4.801625187136928e-05,
+      "loss": 1.5919,
+      "step": 4150
+    },
+    {
+      "epoch": 1.4622748237751284,
+      "grad_norm": 0.6034495360815867,
+      "learning_rate": 4.796840217805524e-05,
+      "loss": 1.5971,
+      "step": 4200
+    },
+    {
+      "epoch": 1.4622748237751284,
+      "eval_loss": 1.6052404642105103,
+      "eval_runtime": 14.2403,
+      "eval_samples_per_second": 70.223,
+      "eval_steps_per_second": 2.247,
+      "step": 4200
+    },
+    {
+      "epoch": 1.4796797493690714,
+      "grad_norm": 0.6329224233323587,
+      "learning_rate": 4.792001310734627e-05,
+      "loss": 1.5887,
+      "step": 4250
+    },
+    {
+      "epoch": 1.4970846749630145,
+      "grad_norm": 0.4863367308791887,
+      "learning_rate": 4.7871086111790634e-05,
+      "loss": 1.5889,
+      "step": 4300
+    },
+    {
+      "epoch": 1.4970846749630145,
+      "eval_loss": 1.6018826961517334,
+      "eval_runtime": 13.9744,
+      "eval_samples_per_second": 71.559,
+      "eval_steps_per_second": 2.29,
+      "step": 4300
+    },
+    {
+      "epoch": 1.5144896005569577,
+      "grad_norm": 0.9659581402091176,
+      "learning_rate": 4.782162266008402e-05,
+      "loss": 1.5973,
+      "step": 4350
+    },
+    {
+      "epoch": 1.5318945261509007,
+      "grad_norm": 0.6230264173988969,
+      "learning_rate": 4.7771624237025556e-05,
+      "loss": 1.6011,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5318945261509007,
+      "eval_loss": 1.6019304990768433,
+      "eval_runtime": 14.0183,
+      "eval_samples_per_second": 71.335,
+      "eval_steps_per_second": 2.283,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5492994517448437,
+      "grad_norm": 0.510207427178355,
+      "learning_rate": 4.772109234347319e-05,
+      "loss": 1.5908,
+      "step": 4450
+    },
+    {
+      "epoch": 1.566704377338787,
+      "grad_norm": 0.93423236140836,
+      "learning_rate": 4.767002849629866e-05,
+      "loss": 1.591,
+      "step": 4500
+    },
+    {
+      "epoch": 1.566704377338787,
+      "eval_loss": 1.6014844179153442,
+      "eval_runtime": 13.9746,
+      "eval_samples_per_second": 71.558,
+      "eval_steps_per_second": 2.29,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58410930293273,
+      "grad_norm": 0.6758808109530141,
+      "learning_rate": 4.761843422834188e-05,
+      "loss": 1.5849,
+      "step": 4550
+    },
+    {
+      "epoch": 1.601514228526673,
+      "grad_norm": 0.5379258818854082,
+      "learning_rate": 4.756631108836508e-05,
+      "loss": 1.5854,
+      "step": 4600
+    },
+    {
+      "epoch": 1.601514228526673,
+      "eval_loss": 1.5978697538375854,
+      "eval_runtime": 14.0029,
+      "eval_samples_per_second": 71.414,
+      "eval_steps_per_second": 2.285,
+      "step": 4600
+    },
+    {
+      "epoch": 1.6189191541206163,
+      "grad_norm": 0.5909606065327258,
+      "learning_rate": 4.7513660641006165e-05,
+      "loss": 1.5833,
+      "step": 4650
+    },
+    {
+      "epoch": 1.636324079714559,
+      "grad_norm": 1.023013373233777,
+      "learning_rate": 4.746048446673184e-05,
+      "loss": 1.5873,
+      "step": 4700
+    },
+    {
+      "epoch": 1.636324079714559,
+      "eval_loss": 1.5967607498168945,
+      "eval_runtime": 13.9738,
+      "eval_samples_per_second": 71.562,
+      "eval_steps_per_second": 2.29,
+      "step": 4700
+    },
+    {
+      "epoch": 1.6537290053085023,
+      "grad_norm": 0.6372756642593507,
+      "learning_rate": 4.740678416179009e-05,
+      "loss": 1.581,
+      "step": 4750
+    },
+    {
+      "epoch": 1.6711339309024456,
+      "grad_norm": 0.5784388626980227,
+      "learning_rate": 4.735256133816237e-05,
+      "loss": 1.5755,
+      "step": 4800
+    },
+    {
+      "epoch": 1.6711339309024456,
+      "eval_loss": 1.5935559272766113,
+      "eval_runtime": 14.0039,
+      "eval_samples_per_second": 71.408,
+      "eval_steps_per_second": 2.285,
+      "step": 4800
+    },
+    {
+      "epoch": 1.6885388564963884,
+      "grad_norm": 0.8001549248943342,
+      "learning_rate": 4.7297817623515114e-05,
+      "loss": 1.5896,
+      "step": 4850
+    },
+    {
+      "epoch": 1.7059437820903316,
+      "grad_norm": 0.9138283791586076,
+      "learning_rate": 4.724255466115095e-05,
+      "loss": 1.5898,
+      "step": 4900
+    },
+    {
+      "epoch": 1.7059437820903316,
+      "eval_loss": 1.5930613279342651,
+      "eval_runtime": 14.0797,
+      "eval_samples_per_second": 71.024,
+      "eval_steps_per_second": 2.273,
+      "step": 4900
+    },
+    {
+      "epoch": 1.7233487076842746,
+      "grad_norm": 0.5583757810052768,
+      "learning_rate": 4.7186774109959306e-05,
+      "loss": 1.5719,
+      "step": 4950
+    },
+    {
+      "epoch": 1.7407536332782176,
+      "grad_norm": 0.6698213257447616,
+      "learning_rate": 4.7130477644366656e-05,
+      "loss": 1.5842,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7407536332782176,
+      "eval_loss": 1.5888005495071411,
+      "eval_runtime": 13.9853,
+      "eval_samples_per_second": 71.503,
+      "eval_steps_per_second": 2.288,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7581585588721609,
+      "grad_norm": 0.729413212458277,
+      "learning_rate": 4.7073666954286275e-05,
+      "loss": 1.5882,
+      "step": 5050
+    },
+    {
+      "epoch": 1.775563484466104,
+      "grad_norm": 0.5635621433923584,
+      "learning_rate": 4.7016343745067436e-05,
+      "loss": 1.5845,
+      "step": 5100
+    },
+    {
+      "epoch": 1.775563484466104,
+      "eval_loss": 1.5877995491027832,
+      "eval_runtime": 13.9683,
+      "eval_samples_per_second": 71.591,
+      "eval_steps_per_second": 2.291,
+      "step": 5100
+    },
+    {
+      "epoch": 1.792968410060047,
+      "grad_norm": 0.7101325374582853,
+      "learning_rate": 4.69585097374443e-05,
+      "loss": 1.5815,
+      "step": 5150
+    },
+    {
+      "epoch": 1.8103733356539902,
+      "grad_norm": 1.0099442818196882,
+      "learning_rate": 4.690016666748421e-05,
+      "loss": 1.5754,
+      "step": 5200
+    },
+    {
+      "epoch": 1.8103733356539902,
+      "eval_loss": 1.5878440141677856,
+      "eval_runtime": 13.9816,
+      "eval_samples_per_second": 71.522,
+      "eval_steps_per_second": 2.289,
+      "step": 5200
+    },
+    {
+      "epoch": 1.8277782612479332,
+      "grad_norm": 0.9861038562211553,
+      "learning_rate": 4.684131628653562e-05,
+      "loss": 1.5747,
+      "step": 5250
+    },
+    {
+      "epoch": 1.8451831868418762,
+      "grad_norm": 0.6476902712711115,
+      "learning_rate": 4.678196036117547e-05,
+      "loss": 1.5822,
+      "step": 5300
+    },
+    {
+      "epoch": 1.8451831868418762,
+      "eval_loss": 1.5809299945831299,
+      "eval_runtime": 13.9435,
+      "eval_samples_per_second": 71.718,
+      "eval_steps_per_second": 2.295,
+      "step": 5300
+    },
+    {
+      "epoch": 1.8625881124358195,
+      "grad_norm": 0.8920609219765819,
+      "learning_rate": 4.672210067315619e-05,
+      "loss": 1.5751,
+      "step": 5350
+    },
+    {
+      "epoch": 1.8799930380297625,
+      "grad_norm": 1.0023436798205103,
+      "learning_rate": 4.6661739019352244e-05,
+      "loss": 1.5736,
+      "step": 5400
+    },
+    {
+      "epoch": 1.8799930380297625,
+      "eval_loss": 1.5810316801071167,
+      "eval_runtime": 14.0243,
+      "eval_samples_per_second": 71.305,
+      "eval_steps_per_second": 2.282,
+      "step": 5400
+    },
+    {
+      "epoch": 1.8973979636237055,
+      "grad_norm": 0.6409767838575461,
+      "learning_rate": 4.660087721170612e-05,
+      "loss": 1.5592,
+      "step": 5450
+    },
+    {
+      "epoch": 1.9148028892176487,
+      "grad_norm": 0.9696993404169995,
+      "learning_rate": 4.6539517077173975e-05,
+      "loss": 1.5639,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9148028892176487,
+      "eval_loss": 1.5775830745697021,
+      "eval_runtime": 14.0018,
+      "eval_samples_per_second": 71.419,
+      "eval_steps_per_second": 2.285,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9322078148115915,
+      "grad_norm": 0.6681985853451967,
+      "learning_rate": 4.6477660457670835e-05,
+      "loss": 1.5788,
+      "step": 5550
+    },
+    {
+      "epoch": 1.9496127404055348,
+      "grad_norm": 0.5491471084373808,
+      "learning_rate": 4.641530921001523e-05,
+      "loss": 1.5678,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9496127404055348,
+      "eval_loss": 1.575533151626587,
+      "eval_runtime": 14.0249,
+      "eval_samples_per_second": 71.302,
+      "eval_steps_per_second": 2.282,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9670176659994778,
+      "grad_norm": 0.6947740445053832,
+      "learning_rate": 4.63524652058735e-05,
+      "loss": 1.5732,
+      "step": 5650
+    },
+    {
+      "epoch": 1.9844225915934208,
+      "grad_norm": 0.597698832959584,
+      "learning_rate": 4.628913033170359e-05,
+      "loss": 1.5641,
+      "step": 5700
+    },
+    {
+      "epoch": 1.9844225915934208,
+      "eval_loss": 1.5763437747955322,
+      "eval_runtime": 13.9979,
+      "eval_samples_per_second": 71.439,
+      "eval_steps_per_second": 2.286,
+      "step": 5700
+    },
+    {
+      "epoch": 2.0020885910712733,
+      "grad_norm": 1.3542755699053255,
+      "learning_rate": 4.622530648869846e-05,
+      "loss": 1.5802,
+      "step": 5750
+    },
+    {
+      "epoch": 2.019493516665216,
+      "grad_norm": 0.5422084960348866,
+      "learning_rate": 4.6160995592728964e-05,
+      "loss": 1.5088,
+      "step": 5800
+    },
+    {
+      "epoch": 2.019493516665216,
+      "eval_loss": 1.5745503902435303,
+      "eval_runtime": 13.9995,
+      "eval_samples_per_second": 71.431,
+      "eval_steps_per_second": 2.286,
+      "step": 5800
+    },
+    {
+      "epoch": 2.0368984422591594,
+      "grad_norm": 0.6504392686205402,
+      "learning_rate": 4.609619957428636e-05,
+      "loss": 1.5118,
+      "step": 5850
+    },
+    {
+      "epoch": 2.0543033678531026,
+      "grad_norm": 1.2584747303351034,
+      "learning_rate": 4.6030920378424405e-05,
+      "loss": 1.5085,
+      "step": 5900
+    },
+    {
+      "epoch": 2.0543033678531026,
+      "eval_loss": 1.5728845596313477,
+      "eval_runtime": 14.0,
+      "eval_samples_per_second": 71.429,
+      "eval_steps_per_second": 2.286,
+      "step": 5900
+    },
+    {
+      "epoch": 2.0717082934470454,
+      "grad_norm": 0.9297351113236545,
+      "learning_rate": 4.596515996470088e-05,
+      "loss": 1.5015,
+      "step": 5950
+    },
+    {
+      "epoch": 2.0891132190409887,
+      "grad_norm": 0.6770476529726162,
+      "learning_rate": 4.589892030711882e-05,
+      "loss": 1.5009,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0891132190409887,
+      "eval_loss": 1.5689187049865723,
+      "eval_runtime": 13.9922,
+      "eval_samples_per_second": 71.468,
+      "eval_steps_per_second": 2.287,
+      "step": 6000
+    },
+    {
+      "epoch": 2.1065181446349315,
+      "grad_norm": 0.5333302425721433,
+      "learning_rate": 4.583220339406727e-05,
+      "loss": 1.5005,
+      "step": 6050
+    },
+    {
+      "epoch": 2.1239230702288747,
+      "grad_norm": 0.7158614427338245,
+      "learning_rate": 4.57650112282616e-05,
+      "loss": 1.4947,
+      "step": 6100
+    },
+    {
+      "epoch": 2.1239230702288747,
+      "eval_loss": 1.5668717622756958,
+      "eval_runtime": 13.978,
+      "eval_samples_per_second": 71.541,
+      "eval_steps_per_second": 2.289,
+      "step": 6100
+    },
+    {
+      "epoch": 2.141327995822818,
+      "grad_norm": 0.5418041632358056,
+      "learning_rate": 4.5697345826683316e-05,
+      "loss": 1.505,
+      "step": 6150
+    },
+    {
+      "epoch": 2.1587329214167608,
+      "grad_norm": 0.6349654558761868,
+      "learning_rate": 4.56292092205196e-05,
+      "loss": 1.4941,
+      "step": 6200
+    },
+    {
+      "epoch": 2.1587329214167608,
+      "eval_loss": 1.5645283460617065,
+      "eval_runtime": 13.9969,
+      "eval_samples_per_second": 71.445,
+      "eval_steps_per_second": 2.286,
+      "step": 6200
+    },
+    {
+      "epoch": 2.176137847010704,
+      "grad_norm": 0.6318855187216622,
+      "learning_rate": 4.556060345510229e-05,
+      "loss": 1.4964,
+      "step": 6250
+    },
+    {
+      "epoch": 2.1935427726046473,
+      "grad_norm": 0.820231743084033,
+      "learning_rate": 4.5491530589846496e-05,
+      "loss": 1.5054,
+      "step": 6300
+    },
+    {
+      "epoch": 2.1935427726046473,
+      "eval_loss": 1.565173864364624,
+      "eval_runtime": 16.4402,
+      "eval_samples_per_second": 60.826,
+      "eval_steps_per_second": 1.946,
+      "step": 6300
+    },
+    {
+      "epoch": 2.21094769819859,
+      "grad_norm": 0.5808489693725816,
+      "learning_rate": 4.5421992698188806e-05,
+      "loss": 1.5161,
+      "step": 6350
+    },
+    {
+      "epoch": 2.2283526237925333,
+      "grad_norm": 0.7488137844322202,
+      "learning_rate": 4.5351991867524976e-05,
+      "loss": 1.4909,
+      "step": 6400
+    },
+    {
+      "epoch": 2.2283526237925333,
+      "eval_loss": 1.5601595640182495,
+      "eval_runtime": 13.9913,
+      "eval_samples_per_second": 71.473,
+      "eval_steps_per_second": 2.287,
+      "step": 6400
+    },
+    {
+      "epoch": 2.2457575493864765,
+      "grad_norm": 0.6548395516938676,
+      "learning_rate": 4.528153019914735e-05,
+      "loss": 1.4985,
+      "step": 6450
+    },
+    {
+      "epoch": 2.2631624749804193,
+      "grad_norm": 0.8203597618530264,
+      "learning_rate": 4.5210609808181716e-05,
+      "loss": 1.4944,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2631624749804193,
+      "eval_loss": 1.5601884126663208,
+      "eval_runtime": 13.9999,
+      "eval_samples_per_second": 71.429,
+      "eval_steps_per_second": 2.286,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2805674005743626,
+      "grad_norm": 0.9291833431724984,
+      "learning_rate": 4.513923282352388e-05,
+      "loss": 1.4979,
+      "step": 6550
+    },
+    {
+      "epoch": 2.297972326168306,
+      "grad_norm": 0.6192831769608078,
+      "learning_rate": 4.506740138777571e-05,
+      "loss": 1.5013,
+      "step": 6600
+    },
+    {
+      "epoch": 2.297972326168306,
+      "eval_loss": 1.5595694780349731,
+      "eval_runtime": 14.0125,
+      "eval_samples_per_second": 71.365,
+      "eval_steps_per_second": 2.284,
+      "step": 6600
+    },
+    {
+      "epoch": 2.3153772517622486,
+      "grad_norm": 0.5252276325498895,
+      "learning_rate": 4.499511765718082e-05,
+      "loss": 1.4985,
+      "step": 6650
+    },
+    {
+      "epoch": 2.332782177356192,
+      "grad_norm": 0.8809278512163949,
+      "learning_rate": 4.492238380155988e-05,
+      "loss": 1.5023,
+      "step": 6700
+    },
+    {
+      "epoch": 2.332782177356192,
+      "eval_loss": 1.556013822555542,
+      "eval_runtime": 14.0065,
+      "eval_samples_per_second": 71.395,
+      "eval_steps_per_second": 2.285,
+      "step": 6700
+    },
+    {
+      "epoch": 2.3501871029501347,
+      "grad_norm": 2.493527077826374,
+      "learning_rate": 4.484920200424544e-05,
+      "loss": 1.5031,
+      "step": 6750
+    },
+    {
+      "epoch": 2.367592028544078,
+      "grad_norm": 0.5602546682634547,
+      "learning_rate": 4.4775574462016446e-05,
+      "loss": 1.4949,
+      "step": 6800
+    },
+    {
+      "epoch": 2.367592028544078,
+      "eval_loss": 1.5550192594528198,
+      "eval_runtime": 13.9979,
+      "eval_samples_per_second": 71.439,
+      "eval_steps_per_second": 2.286,
+      "step": 6800
+    },
+    {
+      "epoch": 2.384996954138021,
+      "grad_norm": 0.6370530516407709,
+      "learning_rate": 4.470150338503223e-05,
+      "loss": 1.487,
+      "step": 6850
+    },
+    {
+      "epoch": 2.402401879731964,
+      "grad_norm": 0.6921040878467456,
+      "learning_rate": 4.462699099676619e-05,
+      "loss": 1.4834,
+      "step": 6900
+    },
+    {
+      "epoch": 2.402401879731964,
+      "eval_loss": 1.5544353723526,
+      "eval_runtime": 13.9865,
+      "eval_samples_per_second": 71.497,
+      "eval_steps_per_second": 2.288,
+      "step": 6900
+    },
+    {
+      "epoch": 2.419806805325907,
+      "grad_norm": 0.8610525793818672,
+      "learning_rate": 4.455203953393908e-05,
+      "loss": 1.4912,
+      "step": 6950
+    },
+    {
+      "epoch": 2.4372117309198504,
+      "grad_norm": 0.7729395434067594,
+      "learning_rate": 4.447665124645185e-05,
+      "loss": 1.4978,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4372117309198504,
+      "eval_loss": 1.5510929822921753,
+      "eval_runtime": 13.9851,
+      "eval_samples_per_second": 71.505,
+      "eval_steps_per_second": 2.288,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4546166565137932,
+      "grad_norm": 0.60728121089851,
+      "learning_rate": 4.440082839731805e-05,
+      "loss": 1.4822,
+      "step": 7050
+    },
+    {
+      "epoch": 2.4720215821077365,
+      "grad_norm": 0.5719460953022453,
+      "learning_rate": 4.4324573262595994e-05,
+      "loss": 1.488,
+      "step": 7100
+    },
+    {
+      "epoch": 2.4720215821077365,
+      "eval_loss": 1.5491801500320435,
+      "eval_runtime": 13.9637,
+      "eval_samples_per_second": 71.614,
+      "eval_steps_per_second": 2.292,
+      "step": 7100
+    },
+    {
+      "epoch": 2.4894265077016797,
+      "grad_norm": 0.5494920086386093,
+      "learning_rate": 4.424788813132036e-05,
+      "loss": 1.4823,
+      "step": 7150
+    },
+    {
+      "epoch": 2.5068314332956225,
+      "grad_norm": 0.6483803635153482,
+      "learning_rate": 4.417077530543352e-05,
+      "loss": 1.498,
+      "step": 7200
+    },
+    {
+      "epoch": 2.5068314332956225,
+      "eval_loss": 1.5479047298431396,
+      "eval_runtime": 14.032,
+      "eval_samples_per_second": 71.266,
+      "eval_steps_per_second": 2.28,
+      "step": 7200
+    },
+    {
+      "epoch": 2.5242363588895658,
+      "grad_norm": 0.6182294157167969,
+      "learning_rate": 4.409323709971643e-05,
+      "loss": 1.5015,
+      "step": 7250
+    },
+    {
+      "epoch": 2.541641284483509,
+      "grad_norm": 0.6672439728117495,
+      "learning_rate": 4.401527584171915e-05,
+      "loss": 1.4848,
+      "step": 7300
+    },
+    {
+      "epoch": 2.541641284483509,
+      "eval_loss": 1.5437195301055908,
+      "eval_runtime": 14.0431,
+      "eval_samples_per_second": 71.209,
+      "eval_steps_per_second": 2.279,
+      "step": 7300
+    },
+    {
+      "epoch": 2.559046210077452,
+      "grad_norm": 0.6569153165541121,
+      "learning_rate": 4.393689387169097e-05,
+      "loss": 1.4844,
+      "step": 7350
+    },
+    {
+      "epoch": 2.576451135671395,
+      "grad_norm": 0.70328233064019,
+      "learning_rate": 4.38580935425101e-05,
+      "loss": 1.4846,
+      "step": 7400
+    },
+    {
+      "epoch": 2.576451135671395,
+      "eval_loss": 1.5450177192687988,
+      "eval_runtime": 13.9709,
+      "eval_samples_per_second": 71.578,
+      "eval_steps_per_second": 2.29,
+      "step": 7400
+    },
+    {
+      "epoch": 2.5938560612653383,
+      "grad_norm": 0.5537205492155896,
+      "learning_rate": 4.37788772196132e-05,
+      "loss": 1.4897,
+      "step": 7450
+    },
+    {
+      "epoch": 2.611260986859281,
+      "grad_norm": 0.7853101261371833,
+      "learning_rate": 4.3699247280924195e-05,
+      "loss": 1.4849,
+      "step": 7500
+    },
+    {
+      "epoch": 2.611260986859281,
+      "eval_loss": 1.543212890625,
+      "eval_runtime": 13.9687,
+      "eval_samples_per_second": 71.589,
+      "eval_steps_per_second": 2.291,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6286659124532243,
+      "grad_norm": 0.7915889506298213,
+      "learning_rate": 4.3619206116782994e-05,
+      "loss": 1.4888,
+      "step": 7550
+    },
+    {
+      "epoch": 2.6460708380471676,
+      "grad_norm": 0.5435421494025616,
+      "learning_rate": 4.353875612987372e-05,
+      "loss": 1.4903,
+      "step": 7600
+    },
+    {
+      "epoch": 2.6460708380471676,
+      "eval_loss": 1.5421267747879028,
+      "eval_runtime": 13.9954,
+      "eval_samples_per_second": 71.452,
+      "eval_steps_per_second": 2.286,
+      "step": 7600
+    },
+    {
+      "epoch": 2.6634757636411104,
+      "grad_norm": 0.7150187738565811,
+      "learning_rate": 4.3457899735152594e-05,
+      "loss": 1.4856,
+      "step": 7650
+    },
+    {
+      "epoch": 2.6808806892350536,
+      "grad_norm": 0.7286431872094431,
+      "learning_rate": 4.337663935977541e-05,
+      "loss": 1.4851,
+      "step": 7700
+    },
+    {
+      "epoch": 2.6808806892350536,
+      "eval_loss": 1.537925362586975,
+      "eval_runtime": 13.9886,
+      "eval_samples_per_second": 71.487,
+      "eval_steps_per_second": 2.288,
+      "step": 7700
+    },
+    {
+      "epoch": 2.698285614828997,
+      "grad_norm": 0.5315377291160136,
+      "learning_rate": 4.3294977443024674e-05,
+      "loss": 1.4799,
+      "step": 7750
+    },
+    {
+      "epoch": 2.7156905404229397,
+      "grad_norm": 0.7464300338497242,
+      "learning_rate": 4.3212916436236474e-05,
+      "loss": 1.4932,
+      "step": 7800
+    },
+    {
+      "epoch": 2.7156905404229397,
+      "eval_loss": 1.5362157821655273,
+      "eval_runtime": 13.9746,
+      "eval_samples_per_second": 71.559,
+      "eval_steps_per_second": 2.29,
+      "step": 7800
+    },
+    {
+      "epoch": 2.733095466016883,
+      "grad_norm": 0.7735626869311409,
+      "learning_rate": 4.313045880272675e-05,
+      "loss": 1.4868,
+      "step": 7850
+    },
+    {
+      "epoch": 2.7505003916108257,
+      "grad_norm": 0.7079246653886904,
+      "learning_rate": 4.304760701771747e-05,
+      "loss": 1.4736,
+      "step": 7900
+    },
+    {
+      "epoch": 2.7505003916108257,
+      "eval_loss": 1.5344328880310059,
+      "eval_runtime": 13.9862,
+      "eval_samples_per_second": 71.499,
+      "eval_steps_per_second": 2.288,
+      "step": 7900
+    },
+    {
+      "epoch": 2.767905317204769,
+      "grad_norm": 0.5607638781051937,
+      "learning_rate": 4.296436356826226e-05,
+      "loss": 1.4828,
+      "step": 7950
+    },
+    {
+      "epoch": 2.785310242798712,
+      "grad_norm": 0.6698483645730473,
+      "learning_rate": 4.2880730953171786e-05,
+      "loss": 1.4818,
+      "step": 8000
+    },
+    {
+      "epoch": 2.785310242798712,
+      "eval_loss": 1.5319961309432983,
+      "eval_runtime": 14.013,
+      "eval_samples_per_second": 71.362,
+      "eval_steps_per_second": 2.284,
+      "step": 8000
+    },
+    {
+      "epoch": 2.802715168392655,
+      "grad_norm": 0.503273498716246,
+      "learning_rate": 4.279671168293873e-05,
+      "loss": 1.4715,
+      "step": 8050
+    },
+    {
+      "epoch": 2.8201200939865982,
+      "grad_norm": 0.6138361015012737,
+      "learning_rate": 4.2712308279662405e-05,
+      "loss": 1.4833,
+      "step": 8100
+    },
+    {
+      "epoch": 2.8201200939865982,
+      "eval_loss": 1.5272479057312012,
+      "eval_runtime": 14.0366,
+      "eval_samples_per_second": 71.242,
+      "eval_steps_per_second": 2.28,
+      "step": 8100
+    },
+    {
+      "epoch": 2.837525019580541,
+      "grad_norm": 0.6800768745825728,
+      "learning_rate": 4.2627523276973114e-05,
+      "loss": 1.4758,
+      "step": 8150
+    },
+    {
+      "epoch": 2.8549299451744843,
+      "grad_norm": 0.7176069315448348,
+      "learning_rate": 4.254235921995601e-05,
+      "loss": 1.4746,
+      "step": 8200
+    },
+    {
+      "epoch": 2.8549299451744843,
+      "eval_loss": 1.5255234241485596,
+      "eval_runtime": 13.9681,
+      "eval_samples_per_second": 71.592,
+      "eval_steps_per_second": 2.291,
+      "step": 8200
+    },
+    {
+      "epoch": 2.8723348707684275,
+      "grad_norm": 0.7304682952222467,
+      "learning_rate": 4.245681866507474e-05,
+      "loss": 1.4712,
+      "step": 8250
+    },
+    {
+      "epoch": 2.8897397963623703,
+      "grad_norm": 0.6236989319439076,
+      "learning_rate": 4.237090418009474e-05,
+      "loss": 1.4726,
+      "step": 8300
+    },
+    {
+      "epoch": 2.8897397963623703,
+      "eval_loss": 1.5243220329284668,
+      "eval_runtime": 13.986,
+      "eval_samples_per_second": 71.5,
+      "eval_steps_per_second": 2.288,
+      "step": 8300
+    },
+    {
+      "epoch": 2.9071447219563136,
+      "grad_norm": 0.615639176805716,
+      "learning_rate": 4.228461834400609e-05,
+      "loss": 1.4768,
+      "step": 8350
+    },
+    {
+      "epoch": 2.924549647550257,
+      "grad_norm": 0.7789593131085253,
+      "learning_rate": 4.219796374694612e-05,
+      "loss": 1.4696,
+      "step": 8400
+    },
+    {
+      "epoch": 2.924549647550257,
+      "eval_loss": 1.5228594541549683,
+      "eval_runtime": 14.0002,
+      "eval_samples_per_second": 71.428,
+      "eval_steps_per_second": 2.286,
+      "step": 8400
+    },
+    {
+      "epoch": 2.9419545731441996,
+      "grad_norm": 0.6541490416672233,
+      "learning_rate": 4.2110942990121707e-05,
+      "loss": 1.4683,
+      "step": 8450
+    },
+    {
+      "epoch": 2.959359498738143,
+      "grad_norm": 0.8019396630848001,
+      "learning_rate": 4.20235586857311e-05,
+      "loss": 1.4769,
+      "step": 8500
+    },
+    {
+      "epoch": 2.959359498738143,
+      "eval_loss": 1.5207167863845825,
+      "eval_runtime": 14.002,
+      "eval_samples_per_second": 71.419,
+      "eval_steps_per_second": 2.285,
+      "step": 8500
+    },
+    {
+      "epoch": 2.976764424332086,
+      "grad_norm": 0.4872815656219925,
+      "learning_rate": 4.193581345688559e-05,
+      "loss": 1.4769,
+      "step": 8550
+    },
+    {
+      "epoch": 2.994169349926029,
+      "grad_norm": 0.48438009286578315,
+      "learning_rate": 4.184770993753072e-05,
+      "loss": 1.4727,
+      "step": 8600
+    },
+    {
+      "epoch": 2.994169349926029,
+      "eval_loss": 1.5173397064208984,
+      "eval_runtime": 14.0039,
+      "eval_samples_per_second": 71.408,
+      "eval_steps_per_second": 2.285,
+      "step": 8600
+    },
+    {
+      "epoch": 3.0118353494038814,
+      "grad_norm": 0.5172037034713615,
+      "learning_rate": 4.175925077236725e-05,
+      "loss": 1.4341,
+      "step": 8650
+    },
+    {
+      "epoch": 3.0292402749978242,
+      "grad_norm": 0.7660981512215144,
+      "learning_rate": 4.167043861677175e-05,
+      "loss": 1.388,
+      "step": 8700
+    },
+    {
+      "epoch": 3.0292402749978242,
+      "eval_loss": 1.5206201076507568,
+      "eval_runtime": 14.0092,
+      "eval_samples_per_second": 71.382,
+      "eval_steps_per_second": 2.284,
+      "step": 8700
+    },
+    {
+      "epoch": 3.0466452005917675,
+      "grad_norm": 0.7259175655214019,
+      "learning_rate": 4.158127613671687e-05,
+      "loss": 1.3853,
+      "step": 8750
+    },
+    {
+      "epoch": 3.0640501261857107,
+      "grad_norm": 0.759326231296325,
+      "learning_rate": 4.149176600869138e-05,
+      "loss": 1.3921,
+      "step": 8800
+    },
+    {
+      "epoch": 3.0640501261857107,
+      "eval_loss": 1.5212202072143555,
+      "eval_runtime": 13.9904,
+      "eval_samples_per_second": 71.477,
+      "eval_steps_per_second": 2.287,
+      "step": 8800
+    },
+    {
+      "epoch": 3.0814550517796535,
+      "grad_norm": 0.6816156678791402,
+      "learning_rate": 4.1401910919619735e-05,
+      "loss": 1.3935,
+      "step": 8850
+    },
+    {
+      "epoch": 3.0988599773735968,
+      "grad_norm": 0.6716116357078614,
+      "learning_rate": 4.131171356678151e-05,
+      "loss": 1.3949,
+      "step": 8900
+    },
+    {
+      "epoch": 3.0988599773735968,
+      "eval_loss": 1.5215586423873901,
+      "eval_runtime": 13.9752,
+      "eval_samples_per_second": 71.555,
+      "eval_steps_per_second": 2.29,
+      "step": 8900
+    },
+    {
+      "epoch": 3.11626490296754,
+      "grad_norm": 0.585427370042915,
+      "learning_rate": 4.1221176657730366e-05,
+      "loss": 1.3937,
+      "step": 8950
+    },
+    {
+      "epoch": 3.133669828561483,
+      "grad_norm": 0.5070038039825276,
+      "learning_rate": 4.11303029102128e-05,
+      "loss": 1.3905,
+      "step": 9000
+    },
+    {
+      "epoch": 3.133669828561483,
+      "eval_loss": 1.5187056064605713,
+      "eval_runtime": 13.9925,
+      "eval_samples_per_second": 71.467,
+      "eval_steps_per_second": 2.287,
+      "step": 9000
+    },
+    {
+      "epoch": 3.151074754155426,
+      "grad_norm": 0.5782658425686112,
+      "learning_rate": 4.103909505208659e-05,
+      "loss": 1.3818,
+      "step": 9050
+    },
+    {
+      "epoch": 3.1684796797493693,
+      "grad_norm": 0.6971195268104966,
+      "learning_rate": 4.094755582123881e-05,
+      "loss": 1.4096,
+      "step": 9100
+    },
+    {
+      "epoch": 3.1684796797493693,
+      "eval_loss": 1.513555884361267,
+      "eval_runtime": 14.0414,
+      "eval_samples_per_second": 71.218,
+      "eval_steps_per_second": 2.279,
+      "step": 9100
+    },
+    {
+      "epoch": 3.185884605343312,
+      "grad_norm": 0.601333503904311,
+      "learning_rate": 4.085568796550381e-05,
+      "loss": 1.3914,
+      "step": 9150
+    },
+    {
+      "epoch": 3.2032895309372553,
+      "grad_norm": 0.596102911328116,
+      "learning_rate": 4.076349424258056e-05,
+      "loss": 1.3898,
+      "step": 9200
+    },
+    {
+      "epoch": 3.2032895309372553,
+      "eval_loss": 1.513745903968811,
+      "eval_runtime": 14.012,
+      "eval_samples_per_second": 71.367,
+      "eval_steps_per_second": 2.284,
+      "step": 9200
+    },
+    {
+      "epoch": 3.220694456531198,
+      "grad_norm": 0.6397943716093005,
+      "learning_rate": 4.0670977419949985e-05,
+      "loss": 1.3926,
+      "step": 9250
+    },
+    {
+      "epoch": 3.2380993821251414,
+      "grad_norm": 0.5166013726068385,
+      "learning_rate": 4.057814027479184e-05,
+      "loss": 1.3874,
+      "step": 9300
+    },
+    {
+      "epoch": 3.2380993821251414,
+      "eval_loss": 1.513095736503601,
+      "eval_runtime": 13.9776,
+      "eval_samples_per_second": 71.543,
+      "eval_steps_per_second": 2.289,
+      "step": 9300
+    },
+    {
+      "epoch": 3.2555043077190846,
+      "grad_norm": 0.5888457174066127,
+      "learning_rate": 4.048498559390136e-05,
+      "loss": 1.3818,
+      "step": 9350
+    },
+    {
+      "epoch": 3.2729092333130274,
+      "grad_norm": 0.6156597160103343,
+      "learning_rate": 4.0391516173605594e-05,
+      "loss": 1.3935,
+      "step": 9400
+    },
+    {
+      "epoch": 3.2729092333130274,
+      "eval_loss": 1.5117729902267456,
+      "eval_runtime": 13.9905,
+      "eval_samples_per_second": 71.477,
+      "eval_steps_per_second": 2.287,
+      "step": 9400
+    },
+    {
+      "epoch": 3.2903141589069707,
+      "grad_norm": 0.7131915538353129,
+      "learning_rate": 4.029773481967948e-05,
+      "loss": 1.3979,
+      "step": 9450
+    },
+    {
+      "epoch": 3.307719084500914,
+      "grad_norm": 0.5758254019327259,
+      "learning_rate": 4.020364434726159e-05,
+      "loss": 1.4087,
+      "step": 9500
+    },
+    {
+      "epoch": 3.307719084500914,
+      "eval_loss": 1.5071306228637695,
+      "eval_runtime": 13.9596,
+      "eval_samples_per_second": 71.636,
+      "eval_steps_per_second": 2.292,
+      "step": 9500
+    },
+    {
+      "epoch": 3.3251240100948567,
+      "grad_norm": 0.5799334943773048,
+      "learning_rate": 4.010924758076968e-05,
+      "loss": 1.3959,
+      "step": 9550
+    },
+    {
+      "epoch": 3.3425289356888,
+      "grad_norm": 0.6537221695847955,
+      "learning_rate": 4.001454735381587e-05,
+      "loss": 1.3947,
+      "step": 9600
+    },
+    {
+      "epoch": 3.3425289356888,
+      "eval_loss": 1.510569453239441,
+      "eval_runtime": 14.0089,
+      "eval_samples_per_second": 71.383,
+      "eval_steps_per_second": 2.284,
+      "step": 9600
+    },
+    {
+      "epoch": 3.359933861282743,
+      "grad_norm": 0.5409192150645737,
+      "learning_rate": 3.9919546509121556e-05,
+      "loss": 1.3855,
+      "step": 9650
+    },
+    {
+      "epoch": 3.377338786876686,
+      "grad_norm": 0.5241132458551793,
+      "learning_rate": 3.982424789843215e-05,
+      "loss": 1.3831,
+      "step": 9700
+    },
+    {
+      "epoch": 3.377338786876686,
+      "eval_loss": 1.5041130781173706,
+      "eval_runtime": 14.0156,
+      "eval_samples_per_second": 71.349,
+      "eval_steps_per_second": 2.283,
+      "step": 9700
+    },
+    {
+      "epoch": 3.3947437124706292,
+      "grad_norm": 1.3217192216589941,
+      "learning_rate": 3.972865438243141e-05,
+      "loss": 1.3951,
+      "step": 9750
+    },
+    {
+      "epoch": 3.412148638064572,
+      "grad_norm": 0.6672183386467068,
+      "learning_rate": 3.963276883065559e-05,
+      "loss": 1.3984,
+      "step": 9800
+    },
+    {
+      "epoch": 3.412148638064572,
+      "eval_loss": 1.5004818439483643,
+      "eval_runtime": 13.9869,
+      "eval_samples_per_second": 71.495,
+      "eval_steps_per_second": 2.288,
+      "step": 9800
+    },
+    {
+      "epoch": 3.4295535636585153,
+      "grad_norm": 0.6864261952368358,
+      "learning_rate": 3.953659412140731e-05,
+      "loss": 1.3919,
+      "step": 9850
+    },
+    {
+      "epoch": 3.4469584892524585,
+      "grad_norm": 0.8020893138986491,
+      "learning_rate": 3.944013314166918e-05,
+      "loss": 1.3901,
+      "step": 9900
+    },
+    {
+      "epoch": 3.4469584892524585,
+      "eval_loss": 1.4998400211334229,
+      "eval_runtime": 13.9738,
+      "eval_samples_per_second": 71.562,
+      "eval_steps_per_second": 2.29,
+      "step": 9900
+    },
+    {
+      "epoch": 3.4643634148464013,
+      "grad_norm": 0.5280983708253972,
+      "learning_rate": 3.9343388787017045e-05,
+      "loss": 1.3925,
+      "step": 9950
+    },
+    {
+      "epoch": 3.4817683404403446,
+      "grad_norm": 0.6261045706297181,
+      "learning_rate": 3.92463639615332e-05,
+      "loss": 1.3803,
+      "step": 10000
+    },
+    {
+      "epoch": 3.4817683404403446,
+      "eval_loss": 1.494409441947937,
+      "eval_runtime": 13.9651,
+      "eval_samples_per_second": 71.607,
+      "eval_steps_per_second": 2.291,
+      "step": 10000
+    },
+    {
+      "epoch": 3.499173266034288,
+      "grad_norm": 0.6077008396812058,
+      "learning_rate": 3.914906157771907e-05,
+      "loss": 1.3903,
+      "step": 10050
+    },
+    {
+      "epoch": 3.5165781916282306,
+      "grad_norm": 0.6825591451005114,
+      "learning_rate": 3.905148455640793e-05,
+      "loss": 1.3869,
+      "step": 10100
+    },
+    {
+      "epoch": 3.5165781916282306,
+      "eval_loss": 1.4927072525024414,
+      "eval_runtime": 14.0115,
+      "eval_samples_per_second": 71.37,
+      "eval_steps_per_second": 2.284,
+      "step": 10100
+    },
+    {
+      "epoch": 3.533983117222174,
+      "grad_norm": 0.7127239486947049,
+      "learning_rate": 3.895363582667708e-05,
+      "loss": 1.3877,
+      "step": 10150
+    },
+    {
+      "epoch": 3.551388042816117,
+      "grad_norm": 0.6124269855188678,
+      "learning_rate": 3.885551832576005e-05,
+      "loss": 1.3976,
+      "step": 10200
+    },
+    {
+      "epoch": 3.551388042816117,
+      "eval_loss": 1.4895879030227661,
+      "eval_runtime": 14.0183,
+      "eval_samples_per_second": 71.336,
+      "eval_steps_per_second": 2.283,
+      "step": 10200
+    },
+    {
+      "epoch": 3.56879296841006,
+      "grad_norm": 0.5087923983285213,
+      "learning_rate": 3.875713499895833e-05,
+      "loss": 1.3923,
+      "step": 10250
+    },
+    {
+      "epoch": 3.586197894004003,
+      "grad_norm": 0.6500951563330185,
+      "learning_rate": 3.865848879955305e-05,
+      "loss": 1.3777,
+      "step": 10300
+    },
+    {
+      "epoch": 3.586197894004003,
+      "eval_loss": 1.488155484199524,
+      "eval_runtime": 13.9697,
+      "eval_samples_per_second": 71.583,
+      "eval_steps_per_second": 2.291,
+      "step": 10300
+    },
+    {
+      "epoch": 3.6036028195979464,
+      "grad_norm": 0.620126750984765,
+      "learning_rate": 3.8559582688716215e-05,
+      "loss": 1.3705,
+      "step": 10350
+    },
+    {
+      "epoch": 3.621007745191889,
+      "grad_norm": 0.593411564329284,
+      "learning_rate": 3.8460419635421905e-05,
+      "loss": 1.3854,
+      "step": 10400
+    },
+    {
+      "epoch": 3.621007745191889,
+      "eval_loss": 1.490203857421875,
+      "eval_runtime": 14.0195,
+      "eval_samples_per_second": 71.329,
+      "eval_steps_per_second": 2.283,
+      "step": 10400
+    },
+    {
+      "epoch": 3.6384126707858324,
+      "grad_norm": 0.6082624242172648,
+      "learning_rate": 3.8361002616357164e-05,
+      "loss": 1.3963,
+      "step": 10450
+    },
+    {
+      "epoch": 3.6558175963797757,
+      "grad_norm": 0.5432316719761062,
+      "learning_rate": 3.8261334615832545e-05,
+      "loss": 1.3906,
+      "step": 10500
+    },
+    {
+      "epoch": 3.6558175963797757,
+      "eval_loss": 1.486801266670227,
+      "eval_runtime": 14.0284,
+      "eval_samples_per_second": 71.284,
+      "eval_steps_per_second": 2.281,
+      "step": 10500
+    },
+    {
+      "epoch": 3.6732225219737185,
+      "grad_norm": 0.45833443577890215,
+      "learning_rate": 3.8161418625692626e-05,
+      "loss": 1.3954,
+      "step": 10550
+    },
+    {
+      "epoch": 3.6906274475676617,
+      "grad_norm": 0.6292682710059461,
+      "learning_rate": 3.806125764522616e-05,
+      "loss": 1.3899,
+      "step": 10600
+    },
+    {
+      "epoch": 3.6906274475676617,
+      "eval_loss": 1.485595703125,
+      "eval_runtime": 14.0352,
+      "eval_samples_per_second": 71.249,
+      "eval_steps_per_second": 2.28,
+      "step": 10600
+    },
+    {
+      "epoch": 3.708032373161605,
+      "grad_norm": 0.6398479114321272,
+      "learning_rate": 3.796085468107603e-05,
+      "loss": 1.3785,
+      "step": 10650
+    },
+    {
+      "epoch": 3.7254372987555477,
+      "grad_norm": 0.9194838860230665,
+      "learning_rate": 3.7860212747149026e-05,
+      "loss": 1.3943,
+      "step": 10700
+    },
+    {
+      "epoch": 3.7254372987555477,
+      "eval_loss": 1.4841216802597046,
+      "eval_runtime": 13.9765,
+      "eval_samples_per_second": 71.548,
+      "eval_steps_per_second": 2.29,
+      "step": 10700
+    },
+    {
+      "epoch": 3.742842224349491,
+      "grad_norm": 0.6034510757807239,
+      "learning_rate": 3.775933486452535e-05,
+      "loss": 1.3871,
+      "step": 10750
+    },
+    {
+      "epoch": 3.7602471499434342,
+      "grad_norm": 0.549592791064493,
+      "learning_rate": 3.765822406136796e-05,
+      "loss": 1.385,
+      "step": 10800
+    },
+    {
+      "epoch": 3.7602471499434342,
+      "eval_loss": 1.4785528182983398,
+      "eval_runtime": 14.0146,
+      "eval_samples_per_second": 71.354,
+      "eval_steps_per_second": 2.283,
+      "step": 10800
+    },
+    {
+      "epoch": 3.777652075537377,
+      "grad_norm": 3.923057882484424,
+      "learning_rate": 3.755688337283161e-05,
+      "loss": 1.3735,
+      "step": 10850
+    },
+    {
+      "epoch": 3.7950570011313203,
+      "grad_norm": 0.6208751963635791,
+      "learning_rate": 3.745531584097179e-05,
+      "loss": 1.3885,
+      "step": 10900
+    },
+    {
+      "epoch": 3.7950570011313203,
+      "eval_loss": 1.4790866374969482,
+      "eval_runtime": 13.9448,
+      "eval_samples_per_second": 71.711,
+      "eval_steps_per_second": 2.295,
+      "step": 10900
+    },
+    {
+      "epoch": 3.8124619267252635,
+      "grad_norm": 0.514334144822583,
+      "learning_rate": 3.735352451465342e-05,
+      "loss": 1.3779,
+      "step": 10950
+    },
+    {
+      "epoch": 3.8298668523192063,
+      "grad_norm": 0.5605077057085409,
+      "learning_rate": 3.725151244945926e-05,
+      "loss": 1.3871,
+      "step": 11000
+    },
+    {
+      "epoch": 3.8298668523192063,
+      "eval_loss": 1.473836898803711,
+      "eval_runtime": 13.9804,
+      "eval_samples_per_second": 71.529,
+      "eval_steps_per_second": 2.289,
+      "step": 11000
+    },
+    {
+      "epoch": 3.8472717779131496,
+      "grad_norm": 0.5589049809633155,
+      "learning_rate": 3.7149282707598284e-05,
+      "loss": 1.3788,
+      "step": 11050
+    },
+    {
+      "epoch": 3.8646767035070924,
+      "grad_norm": 0.8586729877222112,
+      "learning_rate": 3.704683835781368e-05,
+      "loss": 1.3913,
+      "step": 11100
+    },
+    {
+      "epoch": 3.8646767035070924,
+      "eval_loss": 1.4766095876693726,
+      "eval_runtime": 13.9861,
+      "eval_samples_per_second": 71.5,
+      "eval_steps_per_second": 2.288,
+      "step": 11100
+    },
+    {
+      "epoch": 3.8820816291010356,
+      "grad_norm": 0.43899438984382605,
+      "learning_rate": 3.6944182475290755e-05,
+      "loss": 1.3803,
+      "step": 11150
+    },
+    {
+      "epoch": 3.8994865546949784,
+      "grad_norm": 0.48403601878369473,
+      "learning_rate": 3.684131814156465e-05,
+      "loss": 1.3765,
+      "step": 11200
+    },
+    {
+      "epoch": 3.8994865546949784,
+      "eval_loss": 1.471179723739624,
+      "eval_runtime": 13.9803,
+      "eval_samples_per_second": 71.529,
+      "eval_steps_per_second": 2.289,
+      "step": 11200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 28720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 800,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.086550139994112e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe4d5197498d7995b6f7d11eb66384dc14abdb1550125600e1568f5d2b7a206
+size 7416