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 sha256:849ce0f394c01bb000c38906fa9ae25096cb9760f53c6bfaf621204b0f86e0ad
+size 4884766656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f823406c545199e5ab88dbf92ed2401fa6e38412732da26ba8642d826ff336a
+size 4999819320

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c41ba0e11bcf530f84d1eb63ef9157fb0de5cbcfc78cfc715d0f33892121362
+size 4915916184

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072aeda7bd5a89d8979b44d27a4c0e5aab045288945d3b48d15683df92f33a26
+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:d42991cee6facb136d1c91177ed76e001ef308443116a73b5b2908ee6bda821d
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16298886cacd891de56cc5307f9af4d65a5882acacc7df316f44ff49f1d4bf48
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf308ebdb48c8c352e17eea2dc140a58ca6d156258ddbb386f12304e673f63a6
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3603971c1c01fc26da75c49f91fb807270a83afb6ff3d7b709794cad55f00d
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8315c910d3db7830df45477a4abb5ea96d5074a81bb8664252fe851c401c84
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377c2a575cc44bf5a38cb0ca9bd2e2320144d67e5c8a2729463ac9652b297da5
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727f5a67accac1b4c2d7d8407a2a73a39d54e77a6495177cf2f9d0e0a98a0ebf
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca7f248ab81ab58747cc28c845801fce4e71e45dc5bdb37a0660ab4446c3d4e
+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": 5.224651487674664,
+      "learning_rate": 9.8e-05,
+      "loss": 3.5816,
+      "step": 50
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "grad_norm": 2.01015126986115,
+      "learning_rate": 9.999935133869078e-05,
+      "loss": 2.5833,
+      "step": 100
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "eval_loss": 2.363119602203369,
+      "eval_runtime": 14.19,
+      "eval_samples_per_second": 70.472,
+      "eval_steps_per_second": 2.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.05221477678182926,
+      "grad_norm": 2.0022819274249044,
+      "learning_rate": 9.999735215226256e-05,
+      "loss": 2.2755,
+      "step": 150
+    },
+    {
+      "epoch": 0.06961970237577235,
+      "grad_norm": 1.6461953915222625,
+      "learning_rate": 9.99940022305635e-05,
+      "loss": 2.0748,
+      "step": 200
+    },
+    {
+      "epoch": 0.06961970237577235,
+      "eval_loss": 1.9755463600158691,
+      "eval_runtime": 14.1933,
+      "eval_samples_per_second": 70.456,
+      "eval_steps_per_second": 2.255,
+      "step": 200
+    },
+    {
+      "epoch": 0.08702462796971543,
+      "grad_norm": 2.6377868770726347,
+      "learning_rate": 9.998930167415193e-05,
+      "loss": 1.9693,
+      "step": 250
+    },
+    {
+      "epoch": 0.10442955356365852,
+      "grad_norm": 1.5548988343454404,
+      "learning_rate": 9.998325062412963e-05,
+      "loss": 1.9227,
+      "step": 300
+    },
+    {
+      "epoch": 0.10442955356365852,
+      "eval_loss": 1.9035626649856567,
+      "eval_runtime": 14.2175,
+      "eval_samples_per_second": 70.336,
+      "eval_steps_per_second": 2.251,
+      "step": 300
+    },
+    {
+      "epoch": 0.12183447915760161,
+      "grad_norm": 2.556731248258851,
+      "learning_rate": 9.997584926213766e-05,
+      "loss": 1.8892,
+      "step": 350
+    },
+    {
+      "epoch": 0.1392394047515447,
+      "grad_norm": 2.5023478358310043,
+      "learning_rate": 9.996709781035086e-05,
+      "loss": 1.8608,
+      "step": 400
+    },
+    {
+      "epoch": 0.1392394047515447,
+      "eval_loss": 1.8291828632354736,
+      "eval_runtime": 14.1802,
+      "eval_samples_per_second": 70.521,
+      "eval_steps_per_second": 2.257,
+      "step": 400
+    },
+    {
+      "epoch": 0.15664433034548778,
+      "grad_norm": 2.497261259947572,
+      "learning_rate": 9.99569965314713e-05,
+      "loss": 1.8471,
+      "step": 450
+    },
+    {
+      "epoch": 0.17404925593943085,
+      "grad_norm": 1.7217816389226563,
+      "learning_rate": 9.994554572872018e-05,
+      "loss": 1.8176,
+      "step": 500
+    },
+    {
+      "epoch": 0.17404925593943085,
+      "eval_loss": 1.8023170232772827,
+      "eval_runtime": 14.1941,
+      "eval_samples_per_second": 70.452,
+      "eval_steps_per_second": 2.254,
+      "step": 500
+    },
+    {
+      "epoch": 0.19145418153337396,
+      "grad_norm": 1.1495196492570159,
+      "learning_rate": 9.993274574582892e-05,
+      "loss": 1.8074,
+      "step": 550
+    },
+    {
+      "epoch": 0.20885910712731703,
+      "grad_norm": 2.7997716083418323,
+      "learning_rate": 9.991859696702875e-05,
+      "loss": 1.7859,
+      "step": 600
+    },
+    {
+      "epoch": 0.20885910712731703,
+      "eval_loss": 1.7785776853561401,
+      "eval_runtime": 14.2068,
+      "eval_samples_per_second": 70.389,
+      "eval_steps_per_second": 2.252,
+      "step": 600
+    },
+    {
+      "epoch": 0.2262640327212601,
+      "grad_norm": 1.3663550548904462,
+      "learning_rate": 9.990309981703925e-05,
+      "loss": 1.7924,
+      "step": 650
+    },
+    {
+      "epoch": 0.24366895831520322,
+      "grad_norm": 1.189230686367751,
+      "learning_rate": 9.988625476105546e-05,
+      "loss": 1.7825,
+      "step": 700
+    },
+    {
+      "epoch": 0.24366895831520322,
+      "eval_loss": 1.7615989446640015,
+      "eval_runtime": 14.165,
+      "eval_samples_per_second": 70.596,
+      "eval_steps_per_second": 2.259,
+      "step": 700
+    },
+    {
+      "epoch": 0.26107388390914626,
+      "grad_norm": 1.524728525818709,
+      "learning_rate": 9.986806230473407e-05,
+      "loss": 1.7739,
+      "step": 750
+    },
+    {
+      "epoch": 0.2784788095030894,
+      "grad_norm": 1.098130935980223,
+      "learning_rate": 9.984852299417815e-05,
+      "loss": 1.771,
+      "step": 800
+    },
+    {
+      "epoch": 0.2784788095030894,
+      "eval_loss": 1.7450162172317505,
+      "eval_runtime": 14.1809,
+      "eval_samples_per_second": 70.517,
+      "eval_steps_per_second": 2.257,
+      "step": 800
+    },
+    {
+      "epoch": 0.2958837350970325,
+      "grad_norm": 1.0548890863205609,
+      "learning_rate": 9.982763741592078e-05,
+      "loss": 1.7623,
+      "step": 850
+    },
+    {
+      "epoch": 0.31328866069097555,
+      "grad_norm": 0.7386764098331656,
+      "learning_rate": 9.980540619690747e-05,
+      "loss": 1.7588,
+      "step": 900
+    },
+    {
+      "epoch": 0.31328866069097555,
+      "eval_loss": 1.734774112701416,
+      "eval_runtime": 14.2131,
+      "eval_samples_per_second": 70.358,
+      "eval_steps_per_second": 2.251,
+      "step": 900
+    },
+    {
+      "epoch": 0.33069358628491863,
+      "grad_norm": 1.0044330694002532,
+      "learning_rate": 9.978183000447731e-05,
+      "loss": 1.7475,
+      "step": 950
+    },
+    {
+      "epoch": 0.3480985118788617,
+      "grad_norm": 0.7343666916495631,
+      "learning_rate": 9.97569095463429e-05,
+      "loss": 1.7543,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3480985118788617,
+      "eval_loss": 1.7300388813018799,
+      "eval_runtime": 14.1681,
+      "eval_samples_per_second": 70.581,
+      "eval_steps_per_second": 2.259,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3655034374728048,
+      "grad_norm": 1.3577857575542804,
+      "learning_rate": 9.973064557056923e-05,
+      "loss": 1.7423,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3829083630667479,
+      "grad_norm": 1.1392364193674505,
+      "learning_rate": 9.970303886555105e-05,
+      "loss": 1.7298,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3829083630667479,
+      "eval_loss": 1.7258219718933105,
+      "eval_runtime": 14.1337,
+      "eval_samples_per_second": 70.753,
+      "eval_steps_per_second": 2.264,
+      "step": 1100
+    },
+    {
+      "epoch": 0.400313288660691,
+      "grad_norm": 0.9113533413204287,
+      "learning_rate": 9.967409025998939e-05,
+      "loss": 1.7337,
+      "step": 1150
+    },
+    {
+      "epoch": 0.41771821425463407,
+      "grad_norm": 1.4547875914167818,
+      "learning_rate": 9.964380062286653e-05,
+      "loss": 1.7408,
+      "step": 1200
+    },
+    {
+      "epoch": 0.41771821425463407,
+      "eval_loss": 1.7191509008407593,
+      "eval_runtime": 14.1729,
+      "eval_samples_per_second": 70.557,
+      "eval_steps_per_second": 2.258,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43512313984857715,
+      "grad_norm": 1.3950715870037775,
+      "learning_rate": 9.961217086342002e-05,
+      "loss": 1.7391,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4525280654425202,
+      "grad_norm": 0.7097097270035738,
+      "learning_rate": 9.957920193111528e-05,
+      "loss": 1.7265,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4525280654425202,
+      "eval_loss": 1.7083090543746948,
+      "eval_runtime": 14.1902,
+      "eval_samples_per_second": 70.471,
+      "eval_steps_per_second": 2.255,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4699329910364633,
+      "grad_norm": 1.2193424381306277,
+      "learning_rate": 9.954489481561721e-05,
+      "loss": 1.7133,
+      "step": 1350
+    },
+    {
+      "epoch": 0.48733791663040643,
+      "grad_norm": 1.0359902451377283,
+      "learning_rate": 9.950925054676047e-05,
+      "loss": 1.7219,
+      "step": 1400
+    },
+    {
+      "epoch": 0.48733791663040643,
+      "eval_loss": 1.7060251235961914,
+      "eval_runtime": 14.1957,
+      "eval_samples_per_second": 70.444,
+      "eval_steps_per_second": 2.254,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5047428422243495,
+      "grad_norm": 0.8883112233878396,
+      "learning_rate": 9.947227019451845e-05,
+      "loss": 1.718,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5221477678182925,
+      "grad_norm": 1.6600465700603348,
+      "learning_rate": 9.943395486897128e-05,
+      "loss": 1.7155,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5221477678182925,
+      "eval_loss": 1.708118200302124,
+      "eval_runtime": 14.1648,
+      "eval_samples_per_second": 70.598,
+      "eval_steps_per_second": 2.259,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5395526934122357,
+      "grad_norm": 1.3636186882766423,
+      "learning_rate": 9.939430572027245e-05,
+      "loss": 1.7124,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5569576190061788,
+      "grad_norm": 0.8138102316752223,
+      "learning_rate": 9.935332393861429e-05,
+      "loss": 1.7036,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5569576190061788,
+      "eval_loss": 1.6921547651290894,
+      "eval_runtime": 14.1891,
+      "eval_samples_per_second": 70.477,
+      "eval_steps_per_second": 2.255,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5743625446001218,
+      "grad_norm": 0.85358743278151,
+      "learning_rate": 9.931101075419227e-05,
+      "loss": 1.6992,
+      "step": 1650
+    },
+    {
+      "epoch": 0.591767470194065,
+      "grad_norm": 0.9378346406714159,
+      "learning_rate": 9.926736743716801e-05,
+      "loss": 1.7114,
+      "step": 1700
+    },
+    {
+      "epoch": 0.591767470194065,
+      "eval_loss": 1.6926075220108032,
+      "eval_runtime": 14.1548,
+      "eval_samples_per_second": 70.648,
+      "eval_steps_per_second": 2.261,
+      "step": 1700
+    },
+    {
+      "epoch": 0.609172395788008,
+      "grad_norm": 0.7374768174339537,
+      "learning_rate": 9.922239529763122e-05,
+      "loss": 1.7286,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6265773213819511,
+      "grad_norm": 0.8958414498241435,
+      "learning_rate": 9.917609568556033e-05,
+      "loss": 1.6946,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6265773213819511,
+      "eval_loss": 1.6861408948898315,
+      "eval_runtime": 14.2244,
+      "eval_samples_per_second": 70.302,
+      "eval_steps_per_second": 2.25,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6439822469758941,
+      "grad_norm": 0.6100798904781664,
+      "learning_rate": 9.9128469990782e-05,
+      "loss": 1.7007,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6613871725698373,
+      "grad_norm": 1.4603608185922945,
+      "learning_rate": 9.907951964292936e-05,
+      "loss": 1.6843,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6613871725698373,
+      "eval_loss": 1.6854504346847534,
+      "eval_runtime": 14.2162,
+      "eval_samples_per_second": 70.342,
+      "eval_steps_per_second": 2.251,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6787920981637804,
+      "grad_norm": 1.4095316221753802,
+      "learning_rate": 9.902924611139913e-05,
+      "loss": 1.6945,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6961970237577234,
+      "grad_norm": 1.1737727115924308,
+      "learning_rate": 9.897765090530746e-05,
+      "loss": 1.6915,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6961970237577234,
+      "eval_loss": 1.6767446994781494,
+      "eval_runtime": 14.2006,
+      "eval_samples_per_second": 70.42,
+      "eval_steps_per_second": 2.253,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7136019493516665,
+      "grad_norm": 0.6241203884158069,
+      "learning_rate": 9.892473557344474e-05,
+      "loss": 1.694,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7310068749456096,
+      "grad_norm": 0.717957189850993,
+      "learning_rate": 9.887050170422896e-05,
+      "loss": 1.6905,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7310068749456096,
+      "eval_loss": 1.6781814098358154,
+      "eval_runtime": 14.1564,
+      "eval_samples_per_second": 70.639,
+      "eval_steps_per_second": 2.26,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7484118005395527,
+      "grad_norm": 0.713989248537336,
+      "learning_rate": 9.881495092565816e-05,
+      "loss": 1.6785,
+      "step": 2150
+    },
+    {
+      "epoch": 0.7658167261334958,
+      "grad_norm": 1.6961561321530056,
+      "learning_rate": 9.875808490526146e-05,
+      "loss": 1.683,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7658167261334958,
+      "eval_loss": 1.689602017402649,
+      "eval_runtime": 14.1672,
+      "eval_samples_per_second": 70.585,
+      "eval_steps_per_second": 2.259,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7832216517274389,
+      "grad_norm": 0.8275650716779648,
+      "learning_rate": 9.869990535004906e-05,
+      "loss": 1.6858,
+      "step": 2250
+    },
+    {
+      "epoch": 0.800626577321382,
+      "grad_norm": 0.5691953766407909,
+      "learning_rate": 9.864041400646105e-05,
+      "loss": 1.6763,
+      "step": 2300
+    },
+    {
+      "epoch": 0.800626577321382,
+      "eval_loss": 1.6652159690856934,
+      "eval_runtime": 14.2094,
+      "eval_samples_per_second": 70.376,
+      "eval_steps_per_second": 2.252,
+      "step": 2300
+    },
+    {
+      "epoch": 0.818031502915325,
+      "grad_norm": 0.7573933191424803,
+      "learning_rate": 9.857961266031481e-05,
+      "loss": 1.6785,
+      "step": 2350
+    },
+    {
+      "epoch": 0.8354364285092681,
+      "grad_norm": 0.6924121696414417,
+      "learning_rate": 9.851750313675159e-05,
+      "loss": 1.6833,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8354364285092681,
+      "eval_loss": 1.6645046472549438,
+      "eval_runtime": 14.1618,
+      "eval_samples_per_second": 70.613,
+      "eval_steps_per_second": 2.26,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8528413541032112,
+      "grad_norm": 0.6001197165520973,
+      "learning_rate": 9.845408730018163e-05,
+      "loss": 1.6809,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8702462796971543,
+      "grad_norm": 1.040986311462392,
+      "learning_rate": 9.838936705422821e-05,
+      "loss": 1.6723,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8702462796971543,
+      "eval_loss": 1.6651116609573364,
+      "eval_runtime": 16.0729,
+      "eval_samples_per_second": 62.217,
+      "eval_steps_per_second": 1.991,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8876512052910974,
+      "grad_norm": 0.7703719087126286,
+      "learning_rate": 9.832334434167053e-05,
+      "loss": 1.6758,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9050561308850404,
+      "grad_norm": 0.8236590047203298,
+      "learning_rate": 9.825602114438532e-05,
+      "loss": 1.6665,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9050561308850404,
+      "eval_loss": 1.6595755815505981,
+      "eval_runtime": 14.1488,
+      "eval_samples_per_second": 70.678,
+      "eval_steps_per_second": 2.262,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9224610564789836,
+      "grad_norm": 1.3966523691983288,
+      "learning_rate": 9.818739948328745e-05,
+      "loss": 1.6649,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9398659820729266,
+      "grad_norm": 0.7343985025715206,
+      "learning_rate": 9.811748141826919e-05,
+      "loss": 1.6532,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9398659820729266,
+      "eval_loss": 1.6552517414093018,
+      "eval_runtime": 14.2028,
+      "eval_samples_per_second": 70.409,
+      "eval_steps_per_second": 2.253,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9572709076668697,
+      "grad_norm": 0.7688939367455496,
+      "learning_rate": 9.804626904813839e-05,
+      "loss": 1.6597,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9746758332608129,
+      "grad_norm": 1.0722401609793455,
+      "learning_rate": 9.797376451055551e-05,
+      "loss": 1.6581,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9746758332608129,
+      "eval_loss": 1.656619906425476,
+      "eval_runtime": 14.1856,
+      "eval_samples_per_second": 70.494,
+      "eval_steps_per_second": 2.256,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9920807588547559,
+      "grad_norm": 0.8328376734593738,
+      "learning_rate": 9.789996998196943e-05,
+      "loss": 1.6649,
+      "step": 2850
+    },
+    {
+      "epoch": 1.009746758332608,
+      "grad_norm": 0.5902121192870661,
+      "learning_rate": 9.782488767755206e-05,
+      "loss": 1.666,
+      "step": 2900
+    },
+    {
+      "epoch": 1.009746758332608,
+      "eval_loss": 1.6525744199752808,
+      "eval_runtime": 14.219,
+      "eval_samples_per_second": 70.329,
+      "eval_steps_per_second": 2.251,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0271516839265513,
+      "grad_norm": 1.3497294634730705,
+      "learning_rate": 9.7748519851132e-05,
+      "loss": 1.6148,
+      "step": 2950
+    },
+    {
+      "epoch": 1.0445566095204943,
+      "grad_norm": 1.0857671019695037,
+      "learning_rate": 9.76708687951267e-05,
+      "loss": 1.6215,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0445566095204943,
+      "eval_loss": 1.6470530033111572,
+      "eval_runtime": 14.2027,
+      "eval_samples_per_second": 70.409,
+      "eval_steps_per_second": 2.253,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0619615351144374,
+      "grad_norm": 0.7600787872008034,
+      "learning_rate": 9.75919368404738e-05,
+      "loss": 1.6102,
+      "step": 3050
+    },
+    {
+      "epoch": 1.0793664607083804,
+      "grad_norm": 0.5975569538868418,
+      "learning_rate": 9.751172635656103e-05,
+      "loss": 1.6235,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0793664607083804,
+      "eval_loss": 1.6456007957458496,
+      "eval_runtime": 14.1759,
+      "eval_samples_per_second": 70.542,
+      "eval_steps_per_second": 2.257,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0967713863023236,
+      "grad_norm": 0.8523556660651893,
+      "learning_rate": 9.743023975115513e-05,
+      "loss": 1.6145,
+      "step": 3150
+    },
+    {
+      "epoch": 1.1141763118962666,
+      "grad_norm": 0.6662613091564613,
+      "learning_rate": 9.73474794703297e-05,
+      "loss": 1.616,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1141763118962666,
+      "eval_loss": 1.6436479091644287,
+      "eval_runtime": 14.2201,
+      "eval_samples_per_second": 70.323,
+      "eval_steps_per_second": 2.25,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1315812374902097,
+      "grad_norm": 1.0014858310703798,
+      "learning_rate": 9.726344799839156e-05,
+      "loss": 1.6199,
+      "step": 3250
+    },
+    {
+      "epoch": 1.148986163084153,
+      "grad_norm": 0.8999822439007208,
+      "learning_rate": 9.71781478578063e-05,
+      "loss": 1.6062,
+      "step": 3300
+    },
+    {
+      "epoch": 1.148986163084153,
+      "eval_loss": 1.641990065574646,
+      "eval_runtime": 14.9777,
+      "eval_samples_per_second": 66.766,
+      "eval_steps_per_second": 2.137,
+      "step": 3300
+    },
+    {
+      "epoch": 1.166391088678096,
+      "grad_norm": 1.0267159917163893,
+      "learning_rate": 9.709158160912257e-05,
+      "loss": 1.6052,
+      "step": 3350
+    },
+    {
+      "epoch": 1.183796014272039,
+      "grad_norm": 0.8248173174284201,
+      "learning_rate": 9.700375185089517e-05,
+      "loss": 1.6132,
+      "step": 3400
+    },
+    {
+      "epoch": 1.183796014272039,
+      "eval_loss": 1.6383293867111206,
+      "eval_runtime": 14.0557,
+      "eval_samples_per_second": 71.146,
+      "eval_steps_per_second": 2.277,
+      "step": 3400
+    },
+    {
+      "epoch": 1.201200939865982,
+      "grad_norm": 1.5374825914990502,
+      "learning_rate": 9.691466121960706e-05,
+      "loss": 1.6058,
+      "step": 3450
+    },
+    {
+      "epoch": 1.2186058654599252,
+      "grad_norm": 0.8035410560111882,
+      "learning_rate": 9.682431238959022e-05,
+      "loss": 1.6274,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2186058654599252,
+      "eval_loss": 1.6350009441375732,
+      "eval_runtime": 14.1397,
+      "eval_samples_per_second": 70.723,
+      "eval_steps_per_second": 2.263,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2360107910538682,
+      "grad_norm": 0.8277696146602792,
+      "learning_rate": 9.673270807294535e-05,
+      "loss": 1.6044,
+      "step": 3550
+    },
+    {
+      "epoch": 1.2534157166478113,
+      "grad_norm": 0.7213590940694181,
+      "learning_rate": 9.663985101946054e-05,
+      "loss": 1.6111,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2534157166478113,
+      "eval_loss": 1.632244348526001,
+      "eval_runtime": 14.1679,
+      "eval_samples_per_second": 70.582,
+      "eval_steps_per_second": 2.259,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2708206422417545,
+      "grad_norm": 0.9481505755747548,
+      "learning_rate": 9.654574401652863e-05,
+      "loss": 1.6097,
+      "step": 3650
+    },
+    {
+      "epoch": 1.2882255678356975,
+      "grad_norm": 1.2819901910209912,
+      "learning_rate": 9.645038988906358e-05,
+      "loss": 1.6163,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2882255678356975,
+      "eval_loss": 1.6331335306167603,
+      "eval_runtime": 14.1789,
+      "eval_samples_per_second": 70.527,
+      "eval_steps_per_second": 2.257,
+      "step": 3700
+    },
+    {
+      "epoch": 1.3056304934296405,
+      "grad_norm": 0.7806882827911785,
+      "learning_rate": 9.635379149941563e-05,
+      "loss": 1.6055,
+      "step": 3750
+    },
+    {
+      "epoch": 1.3230354190235838,
+      "grad_norm": 0.4318159947229749,
+      "learning_rate": 9.625595174728545e-05,
+      "loss": 1.6021,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3230354190235838,
+      "eval_loss": 1.624240756034851,
+      "eval_runtime": 14.1494,
+      "eval_samples_per_second": 70.674,
+      "eval_steps_per_second": 2.262,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3404403446175268,
+      "grad_norm": 0.7517318396965236,
+      "learning_rate": 9.615687356963708e-05,
+      "loss": 1.609,
+      "step": 3850
+    },
+    {
+      "epoch": 1.3578452702114698,
+      "grad_norm": 1.3678568803980757,
+      "learning_rate": 9.605655994060972e-05,
+      "loss": 1.6185,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3578452702114698,
+      "eval_loss": 1.6263964176177979,
+      "eval_runtime": 14.1348,
+      "eval_samples_per_second": 70.747,
+      "eval_steps_per_second": 2.264,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3752501958054129,
+      "grad_norm": 0.684451776795263,
+      "learning_rate": 9.595501387142849e-05,
+      "loss": 1.6003,
+      "step": 3950
+    },
+    {
+      "epoch": 1.392655121399356,
+      "grad_norm": 0.6300681096210147,
+      "learning_rate": 9.5852238410314e-05,
+      "loss": 1.6116,
+      "step": 4000
+    },
+    {
+      "epoch": 1.392655121399356,
+      "eval_loss": 1.6186518669128418,
+      "eval_runtime": 14.1005,
+      "eval_samples_per_second": 70.92,
+      "eval_steps_per_second": 2.269,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4100600469932991,
+      "grad_norm": 0.67128388115318,
+      "learning_rate": 9.574823664239092e-05,
+      "loss": 1.5968,
+      "step": 4050
+    },
+    {
+      "epoch": 1.4274649725872421,
+      "grad_norm": 1.2536187487887276,
+      "learning_rate": 9.564301168959529e-05,
+      "loss": 1.6008,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4274649725872421,
+      "eval_loss": 1.620023488998413,
+      "eval_runtime": 14.0983,
+      "eval_samples_per_second": 70.931,
+      "eval_steps_per_second": 2.27,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4448698981811852,
+      "grad_norm": 0.8805397163157814,
+      "learning_rate": 9.553656671058088e-05,
+      "loss": 1.5984,
+      "step": 4150
+    },
+    {
+      "epoch": 1.4622748237751284,
+      "grad_norm": 0.5785566464846152,
+      "learning_rate": 9.542890490062429e-05,
+      "loss": 1.6035,
+      "step": 4200
+    },
+    {
+      "epoch": 1.4622748237751284,
+      "eval_loss": 1.6156837940216064,
+      "eval_runtime": 14.1116,
+      "eval_samples_per_second": 70.864,
+      "eval_steps_per_second": 2.268,
+      "step": 4200
+    },
+    {
+      "epoch": 1.4796797493690714,
+      "grad_norm": 0.6863100934352178,
+      "learning_rate": 9.532002949152912e-05,
+      "loss": 1.5932,
+      "step": 4250
+    },
+    {
+      "epoch": 1.4970846749630145,
+      "grad_norm": 0.5351016892320096,
+      "learning_rate": 9.520994375152891e-05,
+      "loss": 1.5946,
+      "step": 4300
+    },
+    {
+      "epoch": 1.4970846749630145,
+      "eval_loss": 1.6144546270370483,
+      "eval_runtime": 14.0968,
+      "eval_samples_per_second": 70.938,
+      "eval_steps_per_second": 2.27,
+      "step": 4300
+    },
+    {
+      "epoch": 1.5144896005569577,
+      "grad_norm": 0.5203388464538014,
+      "learning_rate": 9.509865098518904e-05,
+      "loss": 1.6023,
+      "step": 4350
+    },
+    {
+      "epoch": 1.5318945261509007,
+      "grad_norm": 0.7698479203549923,
+      "learning_rate": 9.49861545333075e-05,
+      "loss": 1.6069,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5318945261509007,
+      "eval_loss": 1.6156337261199951,
+      "eval_runtime": 14.0577,
+      "eval_samples_per_second": 71.135,
+      "eval_steps_per_second": 2.276,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5492994517448437,
+      "grad_norm": 0.7931906732864475,
+      "learning_rate": 9.487245777281469e-05,
+      "loss": 1.595,
+      "step": 4450
+    },
+    {
+      "epoch": 1.566704377338787,
+      "grad_norm": 0.7495495878078449,
+      "learning_rate": 9.475756411667196e-05,
+      "loss": 1.5971,
+      "step": 4500
+    },
+    {
+      "epoch": 1.566704377338787,
+      "eval_loss": 1.6118335723876953,
+      "eval_runtime": 14.0436,
+      "eval_samples_per_second": 71.207,
+      "eval_steps_per_second": 2.279,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58410930293273,
+      "grad_norm": 0.916930023005075,
+      "learning_rate": 9.464147701376923e-05,
+      "loss": 1.5922,
+      "step": 4550
+    },
+    {
+      "epoch": 1.601514228526673,
+      "grad_norm": 0.38302647796596223,
+      "learning_rate": 9.452419994882143e-05,
+      "loss": 1.5902,
+      "step": 4600
+    },
+    {
+      "epoch": 1.601514228526673,
+      "eval_loss": 1.608117938041687,
+      "eval_runtime": 14.0669,
+      "eval_samples_per_second": 71.089,
+      "eval_steps_per_second": 2.275,
+      "step": 4600
+    },
+    {
+      "epoch": 1.6189191541206163,
+      "grad_norm": 0.8959281179242939,
+      "learning_rate": 9.440573644226388e-05,
+      "loss": 1.5887,
+      "step": 4650
+    },
+    {
+      "epoch": 1.636324079714559,
+      "grad_norm": 0.5262586359913002,
+      "learning_rate": 9.428609005014662e-05,
+      "loss": 1.5935,
+      "step": 4700
+    },
+    {
+      "epoch": 1.636324079714559,
+      "eval_loss": 1.6059889793395996,
+      "eval_runtime": 14.0393,
+      "eval_samples_per_second": 71.229,
+      "eval_steps_per_second": 2.279,
+      "step": 4700
+    },
+    {
+      "epoch": 1.6537290053085023,
+      "grad_norm": 0.7596032127547677,
+      "learning_rate": 9.416526436402769e-05,
+      "loss": 1.5917,
+      "step": 4750
+    },
+    {
+      "epoch": 1.6711339309024456,
+      "grad_norm": 0.6240379162553015,
+      "learning_rate": 9.404326301086532e-05,
+      "loss": 1.5797,
+      "step": 4800
+    },
+    {
+      "epoch": 1.6711339309024456,
+      "eval_loss": 1.6034634113311768,
+      "eval_runtime": 14.0769,
+      "eval_samples_per_second": 71.038,
+      "eval_steps_per_second": 2.273,
+      "step": 4800
+    },
+    {
+      "epoch": 1.6885388564963884,
+      "grad_norm": 0.5788152574082417,
+      "learning_rate": 9.392008965290902e-05,
+      "loss": 1.595,
+      "step": 4850
+    },
+    {
+      "epoch": 1.7059437820903316,
+      "grad_norm": 0.7613056072018011,
+      "learning_rate": 9.379574798758964e-05,
+      "loss": 1.5942,
+      "step": 4900
+    },
+    {
+      "epoch": 1.7059437820903316,
+      "eval_loss": 1.6013330221176147,
+      "eval_runtime": 14.0902,
+      "eval_samples_per_second": 70.971,
+      "eval_steps_per_second": 2.271,
+      "step": 4900
+    },
+    {
+      "epoch": 1.7233487076842746,
+      "grad_norm": 0.45671087383446224,
+      "learning_rate": 9.367024174740844e-05,
+      "loss": 1.5779,
+      "step": 4950
+    },
+    {
+      "epoch": 1.7407536332782176,
+      "grad_norm": 0.5341748703612714,
+      "learning_rate": 9.354357469982498e-05,
+      "loss": 1.5901,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7407536332782176,
+      "eval_loss": 1.602180004119873,
+      "eval_runtime": 14.0601,
+      "eval_samples_per_second": 71.123,
+      "eval_steps_per_second": 2.276,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7581585588721609,
+      "grad_norm": 0.5660990008488413,
+      "learning_rate": 9.341575064714412e-05,
+      "loss": 1.5953,
+      "step": 5050
+    },
+    {
+      "epoch": 1.775563484466104,
+      "grad_norm": 0.7080232090171026,
+      "learning_rate": 9.328677342640171e-05,
+      "loss": 1.5901,
+      "step": 5100
+    },
+    {
+      "epoch": 1.775563484466104,
+      "eval_loss": 1.597787618637085,
+      "eval_runtime": 14.0639,
+      "eval_samples_per_second": 71.104,
+      "eval_steps_per_second": 2.275,
+      "step": 5100
+    },
+    {
+      "epoch": 1.792968410060047,
+      "grad_norm": 0.6465428735648749,
+      "learning_rate": 9.315664690924965e-05,
+      "loss": 1.5865,
+      "step": 5150
+    },
+    {
+      "epoch": 1.8103733356539902,
+      "grad_norm": 0.8545113512101515,
+      "learning_rate": 9.302537500183947e-05,
+      "loss": 1.5798,
+      "step": 5200
+    },
+    {
+      "epoch": 1.8103733356539902,
+      "eval_loss": 1.60050630569458,
+      "eval_runtime": 14.0705,
+      "eval_samples_per_second": 71.071,
+      "eval_steps_per_second": 2.274,
+      "step": 5200
+    },
+    {
+      "epoch": 1.8277782612479332,
+      "grad_norm": 0.7086149561628375,
+      "learning_rate": 9.289296164470513e-05,
+      "loss": 1.5798,
+      "step": 5250
+    },
+    {
+      "epoch": 1.8451831868418762,
+      "grad_norm": 0.46396866367967887,
+      "learning_rate": 9.275941081264479e-05,
+      "loss": 1.588,
+      "step": 5300
+    },
+    {
+      "epoch": 1.8451831868418762,
+      "eval_loss": 1.5937552452087402,
+      "eval_runtime": 14.0343,
+      "eval_samples_per_second": 71.254,
+      "eval_steps_per_second": 2.28,
+      "step": 5300
+    },
+    {
+      "epoch": 1.8625881124358195,
+      "grad_norm": 1.1595095063144043,
+      "learning_rate": 9.262472651460142e-05,
+      "loss": 1.5798,
+      "step": 5350
+    },
+    {
+      "epoch": 1.8799930380297625,
+      "grad_norm": 0.8316645877038753,
+      "learning_rate": 9.248891279354255e-05,
+      "loss": 1.5778,
+      "step": 5400
+    },
+    {
+      "epoch": 1.8799930380297625,
+      "eval_loss": 1.5920915603637695,
+      "eval_runtime": 14.0715,
+      "eval_samples_per_second": 71.065,
+      "eval_steps_per_second": 2.274,
+      "step": 5400
+    },
+    {
+      "epoch": 1.8973979636237055,
+      "grad_norm": 0.8761341319849855,
+      "learning_rate": 9.235197372633876e-05,
+      "loss": 1.5664,
+      "step": 5450
+    },
+    {
+      "epoch": 1.9148028892176487,
+      "grad_norm": 0.6485467148901543,
+      "learning_rate": 9.221391342364145e-05,
+      "loss": 1.5677,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9148028892176487,
+      "eval_loss": 1.5863151550292969,
+      "eval_runtime": 14.0871,
+      "eval_samples_per_second": 70.987,
+      "eval_steps_per_second": 2.272,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9322078148115915,
+      "grad_norm": 0.9588711088224121,
+      "learning_rate": 9.207473602975938e-05,
+      "loss": 1.5839,
+      "step": 5550
+    },
+    {
+      "epoch": 1.9496127404055348,
+      "grad_norm": 0.43931790873869003,
+      "learning_rate": 9.193444572253426e-05,
+      "loss": 1.574,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9496127404055348,
+      "eval_loss": 1.5849186182022095,
+      "eval_runtime": 14.0645,
+      "eval_samples_per_second": 71.101,
+      "eval_steps_per_second": 2.275,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9670176659994778,
+      "grad_norm": 0.6795793348203765,
+      "learning_rate": 9.179304671321535e-05,
+      "loss": 1.5777,
+      "step": 5650
+    },
+    {
+      "epoch": 1.9844225915934208,
+      "grad_norm": 0.6176461270662813,
+      "learning_rate": 9.165054324633307e-05,
+      "loss": 1.5678,
+      "step": 5700
+    },
+    {
+      "epoch": 1.9844225915934208,
+      "eval_loss": 1.5820677280426025,
+      "eval_runtime": 14.1052,
+      "eval_samples_per_second": 70.896,
+      "eval_steps_per_second": 2.269,
+      "step": 5700
+    },
+    {
+      "epoch": 2.0020885910712733,
+      "grad_norm": 0.782555624360694,
+      "learning_rate": 9.150693959957152e-05,
+      "loss": 1.5863,
+      "step": 5750
+    },
+    {
+      "epoch": 2.019493516665216,
+      "grad_norm": 0.7711510253908263,
+      "learning_rate": 9.136224008364015e-05,
+      "loss": 1.5006,
+      "step": 5800
+    },
+    {
+      "epoch": 2.019493516665216,
+      "eval_loss": 1.5815701484680176,
+      "eval_runtime": 14.0399,
+      "eval_samples_per_second": 71.226,
+      "eval_steps_per_second": 2.279,
+      "step": 5800
+    },
+    {
+      "epoch": 2.0368984422591594,
+      "grad_norm": 0.5809585755773129,
+      "learning_rate": 9.121644904214432e-05,
+      "loss": 1.5034,
+      "step": 5850
+    },
+    {
+      "epoch": 2.0543033678531026,
+      "grad_norm": 0.4145082330936503,
+      "learning_rate": 9.10695708514549e-05,
+      "loss": 1.4994,
+      "step": 5900
+    },
+    {
+      "epoch": 2.0543033678531026,
+      "eval_loss": 1.5821447372436523,
+      "eval_runtime": 14.0598,
+      "eval_samples_per_second": 71.125,
+      "eval_steps_per_second": 2.276,
+      "step": 5900
+    },
+    {
+      "epoch": 2.0717082934470454,
+      "grad_norm": 0.5577414193307454,
+      "learning_rate": 9.092160992057697e-05,
+      "loss": 1.4934,
+      "step": 5950
+    },
+    {
+      "epoch": 2.0891132190409887,
+      "grad_norm": 0.5077291954396825,
+      "learning_rate": 9.077257069101733e-05,
+      "loss": 1.4919,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0891132190409887,
+      "eval_loss": 1.5732625722885132,
+      "eval_runtime": 14.0816,
+      "eval_samples_per_second": 71.015,
+      "eval_steps_per_second": 2.272,
+      "step": 6000
+    },
+    {
+      "epoch": 2.1065181446349315,
+      "grad_norm": 0.4907623613867345,
+      "learning_rate": 9.062245763665137e-05,
+      "loss": 1.4933,
+      "step": 6050
+    },
+    {
+      "epoch": 2.1239230702288747,
+      "grad_norm": 0.49160985362367293,
+      "learning_rate": 9.04712752635886e-05,
+      "loss": 1.4876,
+      "step": 6100
+    },
+    {
+      "epoch": 2.1239230702288747,
+      "eval_loss": 1.5737123489379883,
+      "eval_runtime": 14.0837,
+      "eval_samples_per_second": 71.004,
+      "eval_steps_per_second": 2.272,
+      "step": 6100
+    },
+    {
+      "epoch": 2.141327995822818,
+      "grad_norm": 0.948878020362848,
+      "learning_rate": 9.031902811003746e-05,
+      "loss": 1.4974,
+      "step": 6150
+    },
+    {
+      "epoch": 2.1587329214167608,
+      "grad_norm": 0.716453462989888,
+      "learning_rate": 9.016572074616909e-05,
+      "loss": 1.4867,
+      "step": 6200
+    },
+    {
+      "epoch": 2.1587329214167608,
+      "eval_loss": 1.569942831993103,
+      "eval_runtime": 14.0346,
+      "eval_samples_per_second": 71.253,
+      "eval_steps_per_second": 2.28,
+      "step": 6200
+    },
+    {
+      "epoch": 2.176137847010704,
+      "grad_norm": 0.5543365763764092,
+      "learning_rate": 9.001135777398015e-05,
+      "loss": 1.4888,
+      "step": 6250
+    },
+    {
+      "epoch": 2.1935427726046473,
+      "grad_norm": 0.5680832721760428,
+      "learning_rate": 8.985594382715461e-05,
+      "loss": 1.4972,
+      "step": 6300
+    },
+    {
+      "epoch": 2.1935427726046473,
+      "eval_loss": 1.5667256116867065,
+      "eval_runtime": 14.0709,
+      "eval_samples_per_second": 71.069,
+      "eval_steps_per_second": 2.274,
+      "step": 6300
+    },
+    {
+      "epoch": 2.21094769819859,
+      "grad_norm": 0.5247769764374891,
+      "learning_rate": 8.969948357092481e-05,
+      "loss": 1.5106,
+      "step": 6350
+    },
+    {
+      "epoch": 2.2283526237925333,
+      "grad_norm": 0.9601829153693605,
+      "learning_rate": 8.954198170193119e-05,
+      "loss": 1.4849,
+      "step": 6400
+    },
+    {
+      "epoch": 2.2283526237925333,
+      "eval_loss": 1.5672996044158936,
+      "eval_runtime": 14.0285,
+      "eval_samples_per_second": 71.283,
+      "eval_steps_per_second": 2.281,
+      "step": 6400
+    },
+    {
+      "epoch": 2.2457575493864765,
+      "grad_norm": 0.6119058208607214,
+      "learning_rate": 8.938344294808152e-05,
+      "loss": 1.4939,
+      "step": 6450
+    },
+    {
+      "epoch": 2.2631624749804193,
+      "grad_norm": 0.8721578158654933,
+      "learning_rate": 8.922387206840886e-05,
+      "loss": 1.4873,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2631624749804193,
+      "eval_loss": 1.561486840248108,
+      "eval_runtime": 15.6671,
+      "eval_samples_per_second": 63.828,
+      "eval_steps_per_second": 2.042,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2805674005743626,
+      "grad_norm": 0.5628459276663417,
+      "learning_rate": 8.906327385292873e-05,
+      "loss": 1.4936,
+      "step": 6550
+    },
+    {
+      "epoch": 2.297972326168306,
+      "grad_norm": 0.5767623365443796,
+      "learning_rate": 8.890165312249534e-05,
+      "loss": 1.4966,
+      "step": 6600
+    },
+    {
+      "epoch": 2.297972326168306,
+      "eval_loss": 1.5614709854125977,
+      "eval_runtime": 14.0898,
+      "eval_samples_per_second": 70.973,
+      "eval_steps_per_second": 2.271,
+      "step": 6600
+    },
+    {
+      "epoch": 2.3153772517622486,
+      "grad_norm": 0.564692340379062,
+      "learning_rate": 8.873901472865682e-05,
+      "loss": 1.4933,
+      "step": 6650
+    },
+    {
+      "epoch": 2.332782177356192,
+      "grad_norm": 0.5755602053524008,
+      "learning_rate": 8.857536355350971e-05,
+      "loss": 1.4985,
+      "step": 6700
+    },
+    {
+      "epoch": 2.332782177356192,
+      "eval_loss": 1.564212441444397,
+      "eval_runtime": 14.0197,
+      "eval_samples_per_second": 71.328,
+      "eval_steps_per_second": 2.283,
+      "step": 6700
+    },
+    {
+      "epoch": 2.3501871029501347,
+      "grad_norm": 0.5524361278563438,
+      "learning_rate": 8.841070450955225e-05,
+      "loss": 1.4984,
+      "step": 6750
+    },
+    {
+      "epoch": 2.367592028544078,
+      "grad_norm": 0.5237132838370414,
+      "learning_rate": 8.8245042539537e-05,
+      "loss": 1.4865,
+      "step": 6800
+    },
+    {
+      "epoch": 2.367592028544078,
+      "eval_loss": 1.5604348182678223,
+      "eval_runtime": 14.0798,
+      "eval_samples_per_second": 71.024,
+      "eval_steps_per_second": 2.273,
+      "step": 6800
+    },
+    {
+      "epoch": 2.384996954138021,
+      "grad_norm": 0.6294523267926565,
+      "learning_rate": 8.80783826163225e-05,
+      "loss": 1.4816,
+      "step": 6850
+    },
+    {
+      "epoch": 2.402401879731964,
+      "grad_norm": 0.6439531784449674,
+      "learning_rate": 8.791072974272393e-05,
+      "loss": 1.4774,
+      "step": 6900
+    },
+    {
+      "epoch": 2.402401879731964,
+      "eval_loss": 1.561761736869812,
+      "eval_runtime": 14.1204,
+      "eval_samples_per_second": 70.82,
+      "eval_steps_per_second": 2.266,
+      "step": 6900
+    },
+    {
+      "epoch": 2.419806805325907,
+      "grad_norm": 0.7331282546029708,
+      "learning_rate": 8.774208895136295e-05,
+      "loss": 1.4853,
+      "step": 6950
+    },
+    {
+      "epoch": 2.4372117309198504,
+      "grad_norm": 0.6057172385943509,
+      "learning_rate": 8.757246530451666e-05,
+      "loss": 1.4938,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4372117309198504,
+      "eval_loss": 1.5611796379089355,
+      "eval_runtime": 14.0561,
+      "eval_samples_per_second": 71.143,
+      "eval_steps_per_second": 2.277,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4546166565137932,
+      "grad_norm": 0.5755336572051023,
+      "learning_rate": 8.740186389396561e-05,
+      "loss": 1.4759,
+      "step": 7050
+    },
+    {
+      "epoch": 2.4720215821077365,
+      "grad_norm": 0.5890793091489283,
+      "learning_rate": 8.723028984084096e-05,
+      "loss": 1.4847,
+      "step": 7100
+    },
+    {
+      "epoch": 2.4720215821077365,
+      "eval_loss": 1.555484414100647,
+      "eval_runtime": 14.0449,
+      "eval_samples_per_second": 71.2,
+      "eval_steps_per_second": 2.278,
+      "step": 7100
+    },
+    {
+      "epoch": 2.4894265077016797,
+      "grad_norm": 0.5346651318043478,
+      "learning_rate": 8.705774829547078e-05,
+      "loss": 1.478,
+      "step": 7150
+    },
+    {
+      "epoch": 2.5068314332956225,
+      "grad_norm": 0.5993257736517031,
+      "learning_rate": 8.688424443722541e-05,
+      "loss": 1.4937,
+      "step": 7200
+    },
+    {
+      "epoch": 2.5068314332956225,
+      "eval_loss": 1.5523546934127808,
+      "eval_runtime": 14.1612,
+      "eval_samples_per_second": 70.616,
+      "eval_steps_per_second": 2.26,
+      "step": 7200
+    },
+    {
+      "epoch": 2.5242363588895658,
+      "grad_norm": 0.616236652084947,
+      "learning_rate": 8.670978347436197e-05,
+      "loss": 1.4995,
+      "step": 7250
+    },
+    {
+      "epoch": 2.541641284483509,
+      "grad_norm": 0.6365730699693021,
+      "learning_rate": 8.653437064386809e-05,
+      "loss": 1.4806,
+      "step": 7300
+    },
+    {
+      "epoch": 2.541641284483509,
+      "eval_loss": 1.550804615020752,
+      "eval_runtime": 14.048,
+      "eval_samples_per_second": 71.185,
+      "eval_steps_per_second": 2.278,
+      "step": 7300
+    },
+    {
+      "epoch": 2.559046210077452,
+      "grad_norm": 0.6440606032383255,
+      "learning_rate": 8.635801121130467e-05,
+      "loss": 1.481,
+      "step": 7350
+    },
+    {
+      "epoch": 2.576451135671395,
+      "grad_norm": 0.6891455396803525,
+      "learning_rate": 8.618071047064775e-05,
+      "loss": 1.4847,
+      "step": 7400
+    },
+    {
+      "epoch": 2.576451135671395,
+      "eval_loss": 1.5513026714324951,
+      "eval_runtime": 14.0222,
+      "eval_samples_per_second": 71.316,
+      "eval_steps_per_second": 2.282,
+      "step": 7400
+    },
+    {
+      "epoch": 2.5938560612653383,
+      "grad_norm": 0.4446103623530005,
+      "learning_rate": 8.60024737441297e-05,
+      "loss": 1.4888,
+      "step": 7450
+    },
+    {
+      "epoch": 2.611260986859281,
+      "grad_norm": 0.44925002147798715,
+      "learning_rate": 8.582330638207942e-05,
+      "loss": 1.4809,
+      "step": 7500
+    },
+    {
+      "epoch": 2.611260986859281,
+      "eval_loss": 1.5466996431350708,
+      "eval_runtime": 14.0228,
+      "eval_samples_per_second": 71.313,
+      "eval_steps_per_second": 2.282,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6286659124532243,
+      "grad_norm": 0.5311376135998006,
+      "learning_rate": 8.564321376276172e-05,
+      "loss": 1.4829,
+      "step": 7550
+    },
+    {
+      "epoch": 2.6460708380471676,
+      "grad_norm": 0.6263059930294285,
+      "learning_rate": 8.546220129221588e-05,
+      "loss": 1.4888,
+      "step": 7600
+    },
+    {
+      "epoch": 2.6460708380471676,
+      "eval_loss": 1.5447512865066528,
+      "eval_runtime": 14.0345,
+      "eval_samples_per_second": 71.253,
+      "eval_steps_per_second": 2.28,
+      "step": 7600
+    },
+    {
+      "epoch": 2.6634757636411104,
+      "grad_norm": 0.5056520557379114,
+      "learning_rate": 8.528027440409334e-05,
+      "loss": 1.482,
+      "step": 7650
+    },
+    {
+      "epoch": 2.6808806892350536,
+      "grad_norm": 0.689156588626962,
+      "learning_rate": 8.509743855949466e-05,
+      "loss": 1.4829,
+      "step": 7700
+    },
+    {
+      "epoch": 2.6808806892350536,
+      "eval_loss": 1.5431241989135742,
+      "eval_runtime": 14.083,
+      "eval_samples_per_second": 71.007,
+      "eval_steps_per_second": 2.272,
+      "step": 7700
+    },
+    {
+      "epoch": 2.698285614828997,
+      "grad_norm": 0.5268429121635465,
+      "learning_rate": 8.491369924680552e-05,
+      "loss": 1.4769,
+      "step": 7750
+    },
+    {
+      "epoch": 2.7156905404229397,
+      "grad_norm": 0.9679656265410633,
+      "learning_rate": 8.472906198153204e-05,
+      "loss": 1.4902,
+      "step": 7800
+    },
+    {
+      "epoch": 2.7156905404229397,
+      "eval_loss": 1.5384787321090698,
+      "eval_runtime": 14.0677,
+      "eval_samples_per_second": 71.085,
+      "eval_steps_per_second": 2.275,
+      "step": 7800
+    },
+    {
+      "epoch": 2.733095466016883,
+      "grad_norm": 0.7091039157888012,
+      "learning_rate": 8.454353230613517e-05,
+      "loss": 1.4846,
+      "step": 7850
+    },
+    {
+      "epoch": 2.7505003916108257,
+      "grad_norm": 0.6448096725922331,
+      "learning_rate": 8.435711578986429e-05,
+      "loss": 1.4684,
+      "step": 7900
+    },
+    {
+      "epoch": 2.7505003916108257,
+      "eval_loss": 1.5361462831497192,
+      "eval_runtime": 14.0404,
+      "eval_samples_per_second": 71.223,
+      "eval_steps_per_second": 2.279,
+      "step": 7900
+    },
+    {
+      "epoch": 2.767905317204769,
+      "grad_norm": 0.5425910282960384,
+      "learning_rate": 8.416981802859007e-05,
+      "loss": 1.4796,
+      "step": 7950
+    },
+    {
+      "epoch": 2.785310242798712,
+      "grad_norm": 0.5429913334342548,
+      "learning_rate": 8.398164464463652e-05,
+      "loss": 1.4772,
+      "step": 8000
+    },
+    {
+      "epoch": 2.785310242798712,
+      "eval_loss": 1.5346025228500366,
+      "eval_runtime": 14.0528,
+      "eval_samples_per_second": 71.16,
+      "eval_steps_per_second": 2.277,
+      "step": 8000
+    },
+    {
+      "epoch": 2.802715168392655,
+      "grad_norm": 0.6466419466287323,
+      "learning_rate": 8.379260128661213e-05,
+      "loss": 1.4677,
+      "step": 8050
+    },
+    {
+      "epoch": 2.8201200939865982,
+      "grad_norm": 0.48139640132817235,
+      "learning_rate": 8.360269362924042e-05,
+      "loss": 1.4791,
+      "step": 8100
+    },
+    {
+      "epoch": 2.8201200939865982,
+      "eval_loss": 1.528983235359192,
+      "eval_runtime": 14.0868,
+      "eval_samples_per_second": 70.988,
+      "eval_steps_per_second": 2.272,
+      "step": 8100
+    },
+    {
+      "epoch": 2.837525019580541,
+      "grad_norm": 0.5920090390900422,
+      "learning_rate": 8.34119273731895e-05,
+      "loss": 1.4717,
+      "step": 8150
+    },
+    {
+      "epoch": 2.8549299451744843,
+      "grad_norm": 0.47121021893039383,
+      "learning_rate": 8.322030824490102e-05,
+      "loss": 1.4702,
+      "step": 8200
+    },
+    {
+      "epoch": 2.8549299451744843,
+      "eval_loss": 1.5299367904663086,
+      "eval_runtime": 14.0771,
+      "eval_samples_per_second": 71.037,
+      "eval_steps_per_second": 2.273,
+      "step": 8200
+    },
+    {
+      "epoch": 2.8723348707684275,
+      "grad_norm": 0.518097234789271,
+      "learning_rate": 8.302784199641815e-05,
+      "loss": 1.4674,
+      "step": 8250
+    },
+    {
+      "epoch": 2.8897397963623703,
+      "grad_norm": 0.6012732431723707,
+      "learning_rate": 8.283453440521316e-05,
+      "loss": 1.4665,
+      "step": 8300
+    },
+    {
+      "epoch": 2.8897397963623703,
+      "eval_loss": 1.52743661403656,
+      "eval_runtime": 14.0338,
+      "eval_samples_per_second": 71.257,
+      "eval_steps_per_second": 2.28,
+      "step": 8300
+    },
+    {
+      "epoch": 2.9071447219563136,
+      "grad_norm": 0.5403867143777185,
+      "learning_rate": 8.26403912740137e-05,
+      "loss": 1.4727,
+      "step": 8350
+    },
+    {
+      "epoch": 2.924549647550257,
+      "grad_norm": 0.43902817489106005,
+      "learning_rate": 8.244541843062877e-05,
+      "loss": 1.4647,
+      "step": 8400
+    },
+    {
+      "epoch": 2.924549647550257,
+      "eval_loss": 1.5245391130447388,
+      "eval_runtime": 14.0462,
+      "eval_samples_per_second": 71.194,
+      "eval_steps_per_second": 2.278,
+      "step": 8400
+    },
+    {
+      "epoch": 2.9419545731441996,
+      "grad_norm": 0.4748998355550296,
+      "learning_rate": 8.224962172777383e-05,
+      "loss": 1.4642,
+      "step": 8450
+    },
+    {
+      "epoch": 2.959359498738143,
+      "grad_norm": 0.4313453952117379,
+      "learning_rate": 8.205300704289496e-05,
+      "loss": 1.4715,
+      "step": 8500
+    },
+    {
+      "epoch": 2.959359498738143,
+      "eval_loss": 1.5203490257263184,
+      "eval_runtime": 14.0114,
+      "eval_samples_per_second": 71.371,
+      "eval_steps_per_second": 2.284,
+      "step": 8500
+    },
+    {
+      "epoch": 2.976764424332086,
+      "grad_norm": 0.4274467222156833,
+      "learning_rate": 8.185558027799258e-05,
+      "loss": 1.4726,
+      "step": 8550
+    },
+    {
+      "epoch": 2.994169349926029,
+      "grad_norm": 0.6679830853428892,
+      "learning_rate": 8.165734735944413e-05,
+      "loss": 1.4688,
+      "step": 8600
+    },
+    {
+      "epoch": 2.994169349926029,
+      "eval_loss": 1.5217746496200562,
+      "eval_runtime": 14.0739,
+      "eval_samples_per_second": 71.053,
+      "eval_steps_per_second": 2.274,
+      "step": 8600
+    },
+    {
+      "epoch": 3.0118353494038814,
+      "grad_norm": 0.5385154360638814,
+      "learning_rate": 8.145831423782632e-05,
+      "loss": 1.4221,
+      "step": 8650
+    },
+    {
+      "epoch": 3.0292402749978242,
+      "grad_norm": 0.4522644821562811,
+      "learning_rate": 8.125848688773643e-05,
+      "loss": 1.367,
+      "step": 8700
+    },
+    {
+      "epoch": 3.0292402749978242,
+      "eval_loss": 1.528028130531311,
+      "eval_runtime": 14.0484,
+      "eval_samples_per_second": 71.182,
+      "eval_steps_per_second": 2.278,
+      "step": 8700
+    },
+    {
+      "epoch": 3.0466452005917675,
+      "grad_norm": 0.5423484195953633,
+      "learning_rate": 8.105787130761297e-05,
+      "loss": 1.365,
+      "step": 8750
+    },
+    {
+      "epoch": 3.0640501261857107,
+      "grad_norm": 0.5739682275817762,
+      "learning_rate": 8.08564735195556e-05,
+      "loss": 1.3722,
+      "step": 8800
+    },
+    {
+      "epoch": 3.0640501261857107,
+      "eval_loss": 1.5242141485214233,
+      "eval_runtime": 14.0838,
+      "eval_samples_per_second": 71.003,
+      "eval_steps_per_second": 2.272,
+      "step": 8800
+    },
+    {
+      "epoch": 3.0814550517796535,
+      "grad_norm": 0.4693165515239932,
+      "learning_rate": 8.06542995691444e-05,
+      "loss": 1.372,
+      "step": 8850
+    },
+    {
+      "epoch": 3.0988599773735968,
+      "grad_norm": 0.8181124317276868,
+      "learning_rate": 8.04513555252584e-05,
+      "loss": 1.3786,
+      "step": 8900
+    },
+    {
+      "epoch": 3.0988599773735968,
+      "eval_loss": 1.5413788557052612,
+      "eval_runtime": 14.0509,
+      "eval_samples_per_second": 71.17,
+      "eval_steps_per_second": 2.277,
+      "step": 8900
+    },
+    {
+      "epoch": 3.11626490296754,
+      "grad_norm": 0.4557422607086103,
+      "learning_rate": 8.024764747989332e-05,
+      "loss": 1.3787,
+      "step": 8950
+    },
+    {
+      "epoch": 3.133669828561483,
+      "grad_norm": 0.5469507008985239,
+      "learning_rate": 8.00431815479788e-05,
+      "loss": 1.3723,
+      "step": 9000
+    },
+    {
+      "epoch": 3.133669828561483,
+      "eval_loss": 1.5236259698867798,
+      "eval_runtime": 14.0373,
+      "eval_samples_per_second": 71.239,
+      "eval_steps_per_second": 2.28,
+      "step": 9000
+    },
+    {
+      "epoch": 3.151074754155426,
+      "grad_norm": 0.4960756983190434,
+      "learning_rate": 7.983796386719481e-05,
+      "loss": 1.3639,
+      "step": 9050
+    },
+    {
+      "epoch": 3.1684796797493693,
+      "grad_norm": 0.5129111765247095,
+      "learning_rate": 7.963200059778732e-05,
+      "loss": 1.3905,
+      "step": 9100
+    },
+    {
+      "epoch": 3.1684796797493693,
+      "eval_loss": 1.5138270854949951,
+      "eval_runtime": 14.1186,
+      "eval_samples_per_second": 70.829,
+      "eval_steps_per_second": 2.267,
+      "step": 9100
+    },
+    {
+      "epoch": 3.185884605343312,
+      "grad_norm": 0.42247230971649347,
+      "learning_rate": 7.942529792238357e-05,
+      "loss": 1.3742,
+      "step": 9150
+    },
+    {
+      "epoch": 3.2032895309372553,
+      "grad_norm": 0.49904682272530276,
+      "learning_rate": 7.921786204580626e-05,
+      "loss": 1.3722,
+      "step": 9200
+    },
+    {
+      "epoch": 3.2032895309372553,
+      "eval_loss": 1.516204595565796,
+      "eval_runtime": 14.1219,
+      "eval_samples_per_second": 70.812,
+      "eval_steps_per_second": 2.266,
+      "step": 9200
+    },
+    {
+      "epoch": 3.220694456531198,
+      "grad_norm": 0.7397633131463133,
+      "learning_rate": 7.900969919488747e-05,
+      "loss": 1.3762,
+      "step": 9250
+    },
+    {
+      "epoch": 3.2380993821251414,
+      "grad_norm": 0.4582585234648608,
+      "learning_rate": 7.880081561828164e-05,
+      "loss": 1.3707,
+      "step": 9300
+    },
+    {
+      "epoch": 3.2380993821251414,
+      "eval_loss": 1.510941505432129,
+      "eval_runtime": 14.0773,
+      "eval_samples_per_second": 71.036,
+      "eval_steps_per_second": 2.273,
+      "step": 9300
+    },
+    {
+      "epoch": 3.2555043077190846,
+      "grad_norm": 0.7597768772603912,
+      "learning_rate": 7.859121758627805e-05,
+      "loss": 1.3644,
+      "step": 9350
+    },
+    {
+      "epoch": 3.2729092333130274,
+      "grad_norm": 0.4671394975402726,
+      "learning_rate": 7.838091139061257e-05,
+      "loss": 1.377,
+      "step": 9400
+    },
+    {
+      "epoch": 3.2729092333130274,
+      "eval_loss": 1.5095287561416626,
+      "eval_runtime": 14.08,
+      "eval_samples_per_second": 71.023,
+      "eval_steps_per_second": 2.273,
+      "step": 9400
+    },
+    {
+      "epoch": 3.2903141589069707,
+      "grad_norm": 0.6488585559041425,
+      "learning_rate": 7.81699033442788e-05,
+      "loss": 1.3814,
+      "step": 9450
+    },
+    {
+      "epoch": 3.307719084500914,
+      "grad_norm": 0.60047167590259,
+      "learning_rate": 7.795819978133857e-05,
+      "loss": 1.3933,
+      "step": 9500
+    },
+    {
+      "epoch": 3.307719084500914,
+      "eval_loss": 1.5094648599624634,
+      "eval_runtime": 14.0657,
+      "eval_samples_per_second": 71.095,
+      "eval_steps_per_second": 2.275,
+      "step": 9500
+    },
+    {
+      "epoch": 3.3251240100948567,
+      "grad_norm": 0.5120665387653157,
+      "learning_rate": 7.774580705673178e-05,
+      "loss": 1.3791,
+      "step": 9550
+    },
+    {
+      "epoch": 3.3425289356888,
+      "grad_norm": 0.4897005552721969,
+      "learning_rate": 7.75327315460857e-05,
+      "loss": 1.3799,
+      "step": 9600
+    },
+    {
+      "epoch": 3.3425289356888,
+      "eval_loss": 1.506594181060791,
+      "eval_runtime": 14.0207,
+      "eval_samples_per_second": 71.323,
+      "eval_steps_per_second": 2.282,
+      "step": 9600
+    },
+    {
+      "epoch": 3.359933861282743,
+      "grad_norm": 0.6114201210671623,
+      "learning_rate": 7.73189796455235e-05,
+      "loss": 1.3693,
+      "step": 9650
+    },
+    {
+      "epoch": 3.377338786876686,
+      "grad_norm": 0.48276642492539806,
+      "learning_rate": 7.710455777147235e-05,
+      "loss": 1.3666,
+      "step": 9700
+    },
+    {
+      "epoch": 3.377338786876686,
+      "eval_loss": 1.503042221069336,
+      "eval_runtime": 14.1057,
+      "eval_samples_per_second": 70.893,
+      "eval_steps_per_second": 2.269,
+      "step": 9700
+    },
+    {
+      "epoch": 3.3947437124706292,
+      "grad_norm": 0.41168106873603116,
+      "learning_rate": 7.688947236047066e-05,
+      "loss": 1.379,
+      "step": 9750
+    },
+    {
+      "epoch": 3.412148638064572,
+      "grad_norm": 0.8870199328897735,
+      "learning_rate": 7.667372986897506e-05,
+      "loss": 1.3824,
+      "step": 9800
+    },
+    {
+      "epoch": 3.412148638064572,
+      "eval_loss": 1.5050235986709595,
+      "eval_runtime": 14.0443,
+      "eval_samples_per_second": 71.203,
+      "eval_steps_per_second": 2.279,
+      "step": 9800
+    },
+    {
+      "epoch": 3.4295535636585153,
+      "grad_norm": 0.43715464592108627,
+      "learning_rate": 7.645733677316645e-05,
+      "loss": 1.3783,
+      "step": 9850
+    },
+    {
+      "epoch": 3.4469584892524585,
+      "grad_norm": 0.468234113819773,
+      "learning_rate": 7.624029956875564e-05,
+      "loss": 1.3758,
+      "step": 9900
+    },
+    {
+      "epoch": 3.4469584892524585,
+      "eval_loss": 1.4960707426071167,
+      "eval_runtime": 14.0681,
+      "eval_samples_per_second": 71.083,
+      "eval_steps_per_second": 2.275,
+      "step": 9900
+    },
+    {
+      "epoch": 3.4643634148464013,
+      "grad_norm": 0.43920113071992883,
+      "learning_rate": 7.602262477078834e-05,
+      "loss": 1.3781,
+      "step": 9950
+    },
+    {
+      "epoch": 3.4817683404403446,
+      "grad_norm": 0.5400880842727124,
+      "learning_rate": 7.580431891344967e-05,
+      "loss": 1.3661,
+      "step": 10000
+    },
+    {
+      "epoch": 3.4817683404403446,
+      "eval_loss": 1.4914283752441406,
+      "eval_runtime": 14.0434,
+      "eval_samples_per_second": 71.208,
+      "eval_steps_per_second": 2.279,
+      "step": 10000
+    },
+    {
+      "epoch": 3.499173266034288,
+      "grad_norm": 0.5988472397522009,
+      "learning_rate": 7.558538854986791e-05,
+      "loss": 1.3764,
+      "step": 10050
+    },
+    {
+      "epoch": 3.5165781916282306,
+      "grad_norm": 0.8444574285812011,
+      "learning_rate": 7.536584025191782e-05,
+      "loss": 1.3737,
+      "step": 10100
+    },
+    {
+      "epoch": 3.5165781916282306,
+      "eval_loss": 1.4899932146072388,
+      "eval_runtime": 14.0384,
+      "eval_samples_per_second": 71.233,
+      "eval_steps_per_second": 2.279,
+      "step": 10100
+    },
+    {
+      "epoch": 3.533983117222174,
+      "grad_norm": 0.46208976459931617,
+      "learning_rate": 7.514568061002343e-05,
+      "loss": 1.3748,
+      "step": 10150
+    },
+    {
+      "epoch": 3.551388042816117,
+      "grad_norm": 0.48277184847168264,
+      "learning_rate": 7.492491623296011e-05,
+      "loss": 1.3851,
+      "step": 10200
+    },
+    {
+      "epoch": 3.551388042816117,
+      "eval_loss": 1.487738013267517,
+      "eval_runtime": 14.035,
+      "eval_samples_per_second": 71.25,
+      "eval_steps_per_second": 2.28,
+      "step": 10200
+    },
+    {
+      "epoch": 3.56879296841006,
+      "grad_norm": 0.5878106590021267,
+      "learning_rate": 7.470355374765626e-05,
+      "loss": 1.3792,
+      "step": 10250
+    },
+    {
+      "epoch": 3.586197894004003,
+      "grad_norm": 0.6218481065209976,
+      "learning_rate": 7.448159979899435e-05,
+      "loss": 1.3614,
+      "step": 10300
+    },
+    {
+      "epoch": 3.586197894004003,
+      "eval_loss": 1.4880549907684326,
+      "eval_runtime": 14.0575,
+      "eval_samples_per_second": 71.136,
+      "eval_steps_per_second": 2.276,
+      "step": 10300
+    },
+    {
+      "epoch": 3.6036028195979464,
+      "grad_norm": 0.43014733880077827,
+      "learning_rate": 7.425906104961146e-05,
+      "loss": 1.3529,
+      "step": 10350
+    },
+    {
+      "epoch": 3.621007745191889,
+      "grad_norm": 0.38180996387086397,
+      "learning_rate": 7.403594417969929e-05,
+      "loss": 1.3708,
+      "step": 10400
+    },
+    {
+      "epoch": 3.621007745191889,
+      "eval_loss": 1.485776424407959,
+      "eval_runtime": 14.0127,
+      "eval_samples_per_second": 71.364,
+      "eval_steps_per_second": 2.284,
+      "step": 10400
+    },
+    {
+      "epoch": 3.6384126707858324,
+      "grad_norm": 0.640922818316427,
+      "learning_rate": 7.38122558868036e-05,
+      "loss": 1.3768,
+      "step": 10450
+    },
+    {
+      "epoch": 3.6558175963797757,
+      "grad_norm": 0.5101843138500863,
+      "learning_rate": 7.358800288562322e-05,
+      "loss": 1.3778,
+      "step": 10500
+    },
+    {
+      "epoch": 3.6558175963797757,
+      "eval_loss": 1.482886791229248,
+      "eval_runtime": 14.0734,
+      "eval_samples_per_second": 71.056,
+      "eval_steps_per_second": 2.274,
+      "step": 10500
+    },
+    {
+      "epoch": 3.6732225219737185,
+      "grad_norm": 0.4741527452791268,
+      "learning_rate": 7.33631919078084e-05,
+      "loss": 1.3838,
+      "step": 10550
+    },
+    {
+      "epoch": 3.6906274475676617,
+      "grad_norm": 0.5102702944909827,
+      "learning_rate": 7.313782970175884e-05,
+      "loss": 1.3759,
+      "step": 10600
+    },
+    {
+      "epoch": 3.6906274475676617,
+      "eval_loss": 1.4799257516860962,
+      "eval_runtime": 14.007,
+      "eval_samples_per_second": 71.393,
+      "eval_steps_per_second": 2.285,
+      "step": 10600
+    },
+    {
+      "epoch": 3.708032373161605,
+      "grad_norm": 0.48024693782242006,
+      "learning_rate": 7.291192303242105e-05,
+      "loss": 1.3643,
+      "step": 10650
+    },
+    {
+      "epoch": 3.7254372987555477,
+      "grad_norm": 0.7062059015983605,
+      "learning_rate": 7.26854786810853e-05,
+      "loss": 1.3799,
+      "step": 10700
+    },
+    {
+      "epoch": 3.7254372987555477,
+      "eval_loss": 1.4801214933395386,
+      "eval_runtime": 14.1078,
+      "eval_samples_per_second": 70.883,
+      "eval_steps_per_second": 2.268,
+      "step": 10700
+    },
+    {
+      "epoch": 3.742842224349491,
+      "grad_norm": 0.46375178262944156,
+      "learning_rate": 7.245850344518204e-05,
+      "loss": 1.3732,
+      "step": 10750
+    },
+    {
+      "epoch": 3.7602471499434342,
+      "grad_norm": 0.4169945821614371,
+      "learning_rate": 7.223100413807791e-05,
+      "loss": 1.3724,
+      "step": 10800
+    },
+    {
+      "epoch": 3.7602471499434342,
+      "eval_loss": 1.473942518234253,
+      "eval_runtime": 14.1259,
+      "eval_samples_per_second": 70.792,
+      "eval_steps_per_second": 2.265,
+      "step": 10800
+    },
+    {
+      "epoch": 3.777652075537377,
+      "grad_norm": 0.4786950005537502,
+      "learning_rate": 7.200298758887112e-05,
+      "loss": 1.3591,
+      "step": 10850
+    },
+    {
+      "epoch": 3.7950570011313203,
+      "grad_norm": 0.45323468154555957,
+      "learning_rate": 7.177446064218653e-05,
+      "loss": 1.3746,
+      "step": 10900
+    },
+    {
+      "epoch": 3.7950570011313203,
+      "eval_loss": 1.4767768383026123,
+      "eval_runtime": 14.103,
+      "eval_samples_per_second": 70.907,
+      "eval_steps_per_second": 2.269,
+      "step": 10900
+    },
+    {
+      "epoch": 3.8124619267252635,
+      "grad_norm": 0.5072239832224601,
+      "learning_rate": 7.154543015797018e-05,
+      "loss": 1.3633,
+      "step": 10950
+    },
+    {
+      "epoch": 3.8298668523192063,
+      "grad_norm": 0.45536613779948765,
+      "learning_rate": 7.131590301128332e-05,
+      "loss": 1.3738,
+      "step": 11000
+    },
+    {
+      "epoch": 3.8298668523192063,
+      "eval_loss": 1.4675488471984863,
+      "eval_runtime": 14.0469,
+      "eval_samples_per_second": 71.19,
+      "eval_steps_per_second": 2.278,
+      "step": 11000
+    },
+    {
+      "epoch": 3.8472717779131496,
+      "grad_norm": 0.4924988003169001,
+      "learning_rate": 7.108588609209616e-05,
+      "loss": 1.3654,
+      "step": 11050
+    },
+    {
+      "epoch": 3.8646767035070924,
+      "grad_norm": 0.5502823179480381,
+      "learning_rate": 7.085538630508079e-05,
+      "loss": 1.3748,
+      "step": 11100
+    },
+    {
+      "epoch": 3.8646767035070924,
+      "eval_loss": 1.4667439460754395,
+      "eval_runtime": 14.0612,
+      "eval_samples_per_second": 71.117,
+      "eval_steps_per_second": 2.276,
+      "step": 11100
+    },
+    {
+      "epoch": 3.8820816291010356,
+      "grad_norm": 0.4005236928047556,
+      "learning_rate": 7.06244105694042e-05,
+      "loss": 1.3632,
+      "step": 11150
+    },
+    {
+      "epoch": 3.8994865546949784,
+      "grad_norm": 0.3994617195202627,
+      "learning_rate": 7.039296581852047e-05,
+      "loss": 1.3638,
+      "step": 11200
+    },
+    {
+      "epoch": 3.8994865546949784,
+      "eval_loss": 1.4673991203308105,
+      "eval_runtime": 14.0586,
+      "eval_samples_per_second": 71.131,
+      "eval_steps_per_second": 2.276,
+      "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": 1.0865424153444352e+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 sha256:330a1382d8f36c1f829ec415c7a7e4c25ca7af7af5864965b537dd4b791f5ab3
+size 7416