adding model files

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "</headline>": 32008,
+  "</scratchpad>": 32006,
+  "<</SYS>>": 32004,
+  "<<SYS>>": 32003,
+  "<headline>": 32007,
+  "<pad>": 32000,
+  "<scratchpad>": 32005,
+  "[/INST]": 32002,
+  "[INST]": 32001
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006cafbd45d3f484eca7749d880e806261b9ec43f8e6bd2922be9deb0739e3f2
+size 4939116424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550581566336dbaaa7d276f1a1f790725392295867f476d0043466a1698ed044
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9ea6302fbbc48c839c050850bac5940ef6f8f32e686a99f050957d961d9bc6
+size 3590619888

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477093376
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0b510697123150b2963c7b316df0848c000d60d4750d1a1a4035d12c433d1c
+size 1064

special_tokens_map.json

@@ -0,0 +1,82 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,123 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32002": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32003": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32004": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32005": {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32006": {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32007": {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32008": {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[INST]",
+    "[/INST]",
+    "<<SYS>>",
+    "<</SYS>>",
+    "<scratchpad>",
+    "</scratchpad>",
+    "<headline>",
+    "</headline>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,3021 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.400440044004401,
+  "eval_steps": 10,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 32.75,
+      "learning_rate": 8.81057268722467e-07,
+      "loss": 2.0609,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 2.174488067626953,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.779,
+      "eval_steps_per_second": 7.784,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 24.625,
+      "learning_rate": 1.762114537444934e-06,
+      "loss": 2.0653,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.076831579208374,
+      "eval_runtime": 1.0239,
+      "eval_samples_per_second": 152.358,
+      "eval_steps_per_second": 7.813,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 28.75,
+      "learning_rate": 2.643171806167401e-06,
+      "loss": 2.0126,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.833126187324524,
+      "eval_runtime": 1.0293,
+      "eval_samples_per_second": 151.558,
+      "eval_steps_per_second": 7.772,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 25.375,
+      "learning_rate": 3.524229074889868e-06,
+      "loss": 1.6518,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 1.4685035943984985,
+      "eval_runtime": 1.0262,
+      "eval_samples_per_second": 152.014,
+      "eval_steps_per_second": 7.796,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 7.75,
+      "learning_rate": 4.405286343612335e-06,
+      "loss": 1.1979,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.9488865733146667,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.762,
+      "eval_steps_per_second": 7.783,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 11.5,
+      "learning_rate": 5.286343612334802e-06,
+      "loss": 0.783,
+      "step": 60
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.8411845564842224,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 151.685,
+      "eval_steps_per_second": 7.779,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 14.0,
+      "learning_rate": 6.167400881057269e-06,
+      "loss": 0.7714,
+      "step": 70
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.7945773601531982,
+      "eval_runtime": 1.0442,
+      "eval_samples_per_second": 149.402,
+      "eval_steps_per_second": 7.662,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.8125,
+      "learning_rate": 7.048458149779736e-06,
+      "loss": 0.7355,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.7609233856201172,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.785,
+      "eval_steps_per_second": 7.784,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.46875,
+      "learning_rate": 7.929515418502203e-06,
+      "loss": 0.6975,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.7419508695602417,
+      "eval_runtime": 1.0286,
+      "eval_samples_per_second": 151.665,
+      "eval_steps_per_second": 7.778,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.81057268722467e-06,
+      "loss": 0.6724,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.7309817671775818,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.907,
+      "eval_steps_per_second": 7.79,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.484375,
+      "learning_rate": 9.691629955947137e-06,
+      "loss": 0.6828,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.7203356623649597,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 151.696,
+      "eval_steps_per_second": 7.779,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 9.0,
+      "learning_rate": 1.0572687224669605e-05,
+      "loss": 0.7108,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.7119466662406921,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 151.68,
+      "eval_steps_per_second": 7.778,
+      "step": 120
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.1453744493392071e-05,
+      "loss": 0.6326,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.7077727913856506,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.921,
+      "eval_steps_per_second": 7.791,
+      "step": 130
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.78125,
+      "learning_rate": 1.2334801762114539e-05,
+      "loss": 0.6809,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.7020721435546875,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.932,
+      "eval_steps_per_second": 7.791,
+      "step": 140
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.3215859030837006e-05,
+      "loss": 0.6643,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 0.6972720623016357,
+      "eval_runtime": 1.0264,
+      "eval_samples_per_second": 151.992,
+      "eval_steps_per_second": 7.794,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.4096916299559472e-05,
+      "loss": 0.6788,
+      "step": 160
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.6943953633308411,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.927,
+      "eval_steps_per_second": 7.791,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 5.125,
+      "learning_rate": 1.497797356828194e-05,
+      "loss": 0.6691,
+      "step": 170
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.6906076073646545,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 151.679,
+      "eval_steps_per_second": 7.778,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.5859030837004406e-05,
+      "loss": 0.613,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.6878157258033752,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.898,
+      "eval_steps_per_second": 7.79,
+      "step": 180
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.6740088105726872e-05,
+      "loss": 0.5974,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.6908091306686401,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.896,
+      "eval_steps_per_second": 7.79,
+      "step": 190
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.762114537444934e-05,
+      "loss": 0.6832,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.7126217484474182,
+      "eval_runtime": 1.0267,
+      "eval_samples_per_second": 151.946,
+      "eval_steps_per_second": 7.792,
+      "step": 200
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.34375,
+      "learning_rate": 1.8502202643171808e-05,
+      "loss": 0.6832,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 0.6827684044837952,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.747,
+      "eval_steps_per_second": 7.782,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 16.5,
+      "learning_rate": 1.9383259911894274e-05,
+      "loss": 0.6251,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.6819827556610107,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.795,
+      "eval_steps_per_second": 7.784,
+      "step": 220
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 9.875,
+      "learning_rate": 1.9999893591883563e-05,
+      "loss": 0.6063,
+      "step": 230
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.6790426969528198,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.754,
+      "eval_steps_per_second": 7.782,
+      "step": 230
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 9.125,
+      "learning_rate": 1.9998001955032094e-05,
+      "loss": 0.6156,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 0.6750704646110535,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.77,
+      "eval_steps_per_second": 7.783,
+      "step": 240
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.9993746208226672e-05,
+      "loss": 0.5974,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.6730541586875916,
+      "eval_runtime": 1.0297,
+      "eval_samples_per_second": 151.504,
+      "eval_steps_per_second": 7.769,
+      "step": 250
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.99871273577737e-05,
+      "loss": 0.6329,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.6770554780960083,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 151.728,
+      "eval_steps_per_second": 7.781,
+      "step": 260
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.375,
+      "learning_rate": 1.997814696875491e-05,
+      "loss": 0.5943,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.6730098128318787,
+      "eval_runtime": 1.0291,
+      "eval_samples_per_second": 151.588,
+      "eval_steps_per_second": 7.774,
+      "step": 270
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.9966807164657295e-05,
+      "loss": 0.6223,
+      "step": 280
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.6706013679504395,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.769,
+      "eval_steps_per_second": 7.783,
+      "step": 280
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.995311062687098e-05,
+      "loss": 0.6637,
+      "step": 290
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.6693400740623474,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.772,
+      "eval_steps_per_second": 7.783,
+      "step": 290
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.9937060594055197e-05,
+      "loss": 0.5988,
+      "step": 300
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.6715561747550964,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.638,
+      "eval_steps_per_second": 7.776,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.9918660861372466e-05,
+      "loss": 0.6432,
+      "step": 310
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.669074535369873,
+      "eval_runtime": 1.0286,
+      "eval_samples_per_second": 151.667,
+      "eval_steps_per_second": 7.778,
+      "step": 310
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.0,
+      "learning_rate": 1.9897915779591217e-05,
+      "loss": 0.5564,
+      "step": 320
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 0.6686736941337585,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 151.727,
+      "eval_steps_per_second": 7.781,
+      "step": 320
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.984375,
+      "learning_rate": 1.9874830254056986e-05,
+      "loss": 0.6206,
+      "step": 330
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.6675607562065125,
+      "eval_runtime": 1.0286,
+      "eval_samples_per_second": 151.669,
+      "eval_steps_per_second": 7.778,
+      "step": 330
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.9849409743532536e-05,
+      "loss": 0.6829,
+      "step": 340
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.6632043719291687,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.816,
+      "eval_steps_per_second": 7.785,
+      "step": 340
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.982166025890706e-05,
+      "loss": 0.6607,
+      "step": 350
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.6611947417259216,
+      "eval_runtime": 1.0301,
+      "eval_samples_per_second": 151.439,
+      "eval_steps_per_second": 7.766,
+      "step": 350
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.979158836177488e-05,
+      "loss": 0.6375,
+      "step": 360
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.6642427444458008,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.636,
+      "eval_steps_per_second": 7.776,
+      "step": 360
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 5.0,
+      "learning_rate": 1.975920116288388e-05,
+      "loss": 0.6545,
+      "step": 370
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.6634836196899414,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.927,
+      "eval_steps_per_second": 7.791,
+      "step": 370
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.9724506320454153e-05,
+      "loss": 0.5904,
+      "step": 380
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.6607149839401245,
+      "eval_runtime": 1.0258,
+      "eval_samples_per_second": 152.077,
+      "eval_steps_per_second": 7.799,
+      "step": 380
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.40625,
+      "learning_rate": 1.9687512038367093e-05,
+      "loss": 0.636,
+      "step": 390
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.6576667428016663,
+      "eval_runtime": 1.0266,
+      "eval_samples_per_second": 151.955,
+      "eval_steps_per_second": 7.793,
+      "step": 390
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.964822706422556e-05,
+      "loss": 0.5867,
+      "step": 400
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.6577550172805786,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.899,
+      "eval_steps_per_second": 7.79,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.960666068728544e-05,
+      "loss": 0.6329,
+      "step": 410
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.6590597629547119,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.839,
+      "eval_steps_per_second": 7.787,
+      "step": 410
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.9562822736259095e-05,
+      "loss": 0.6044,
+      "step": 420
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.6572380065917969,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.933,
+      "eval_steps_per_second": 7.791,
+      "step": 420
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.9516723576991307e-05,
+      "loss": 0.6465,
+      "step": 430
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 0.6611785888671875,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.802,
+      "eval_steps_per_second": 7.785,
+      "step": 430
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.946837411000818e-05,
+      "loss": 0.6072,
+      "step": 440
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.656313955783844,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.836,
+      "eval_steps_per_second": 7.786,
+      "step": 440
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.40625,
+      "learning_rate": 1.9417785767939617e-05,
+      "loss": 0.6511,
+      "step": 450
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.6521472930908203,
+      "eval_runtime": 1.026,
+      "eval_samples_per_second": 152.05,
+      "eval_steps_per_second": 7.797,
+      "step": 450
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 4.125,
+      "learning_rate": 1.9364970512815996e-05,
+      "loss": 0.5406,
+      "step": 460
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 0.6575232744216919,
+      "eval_runtime": 1.0283,
+      "eval_samples_per_second": 151.707,
+      "eval_steps_per_second": 7.78,
+      "step": 460
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.9309940833239628e-05,
+      "loss": 0.4274,
+      "step": 470
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.6672948002815247,
+      "eval_runtime": 1.0266,
+      "eval_samples_per_second": 151.951,
+      "eval_steps_per_second": 7.792,
+      "step": 470
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.9252709741431738e-05,
+      "loss": 0.4328,
+      "step": 480
+    },
+    {
+      "epoch": 1.06,
+      "eval_loss": 0.6646636128425598,
+      "eval_runtime": 1.0272,
+      "eval_samples_per_second": 151.865,
+      "eval_steps_per_second": 7.788,
+      "step": 480
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.9193290770155614e-05,
+      "loss": 0.4823,
+      "step": 490
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.6640533804893494,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.928,
+      "eval_steps_per_second": 7.791,
+      "step": 490
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.913169796951668e-05,
+      "loss": 0.4958,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.6630443930625916,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.742,
+      "eval_steps_per_second": 7.782,
+      "step": 500
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.9067945903640214e-05,
+      "loss": 0.4515,
+      "step": 510
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.6647157073020935,
+      "eval_runtime": 1.0325,
+      "eval_samples_per_second": 151.083,
+      "eval_steps_per_second": 7.748,
+      "step": 510
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.9002049647227568e-05,
+      "loss": 0.4447,
+      "step": 520
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.667674720287323,
+      "eval_runtime": 1.0332,
+      "eval_samples_per_second": 150.991,
+      "eval_steps_per_second": 7.743,
+      "step": 520
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.893402478199161e-05,
+      "loss": 0.4779,
+      "step": 530
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 0.6629076600074768,
+      "eval_runtime": 1.0311,
+      "eval_samples_per_second": 151.293,
+      "eval_steps_per_second": 7.759,
+      "step": 530
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.88638873929723e-05,
+      "loss": 0.4851,
+      "step": 540
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.663088858127594,
+      "eval_runtime": 1.0334,
+      "eval_samples_per_second": 150.956,
+      "eval_steps_per_second": 7.741,
+      "step": 540
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.8791654064733266e-05,
+      "loss": 0.472,
+      "step": 550
+    },
+    {
+      "epoch": 1.21,
+      "eval_loss": 0.673314094543457,
+      "eval_runtime": 1.032,
+      "eval_samples_per_second": 151.169,
+      "eval_steps_per_second": 7.752,
+      "step": 550
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.5,
+      "learning_rate": 1.8717341877440227e-05,
+      "loss": 0.4784,
+      "step": 560
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 0.6656016111373901,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 151.686,
+      "eval_steps_per_second": 7.779,
+      "step": 560
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.8640968402822265e-05,
+      "loss": 0.4586,
+      "step": 570
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.6733366847038269,
+      "eval_runtime": 1.0309,
+      "eval_samples_per_second": 151.327,
+      "eval_steps_per_second": 7.76,
+      "step": 570
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.8562551700016834e-05,
+      "loss": 0.4249,
+      "step": 580
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.6739068627357483,
+      "eval_runtime": 1.0256,
+      "eval_samples_per_second": 152.103,
+      "eval_steps_per_second": 7.8,
+      "step": 580
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.8482110311299527e-05,
+      "loss": 0.4615,
+      "step": 590
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.6727290153503418,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 151.721,
+      "eval_steps_per_second": 7.781,
+      "step": 590
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.8399663257699608e-05,
+      "loss": 0.5024,
+      "step": 600
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.6658350825309753,
+      "eval_runtime": 1.0302,
+      "eval_samples_per_second": 151.43,
+      "eval_steps_per_second": 7.766,
+      "step": 600
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 5.40625,
+      "learning_rate": 1.8315230034502334e-05,
+      "loss": 0.4866,
+      "step": 610
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 0.6685691475868225,
+      "eval_runtime": 1.0295,
+      "eval_samples_per_second": 151.533,
+      "eval_steps_per_second": 7.771,
+      "step": 610
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.8228830606639128e-05,
+      "loss": 0.4969,
+      "step": 620
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.6662355065345764,
+      "eval_runtime": 1.029,
+      "eval_samples_per_second": 151.606,
+      "eval_steps_per_second": 7.775,
+      "step": 620
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.8140485403966712e-05,
+      "loss": 0.4705,
+      "step": 630
+    },
+    {
+      "epoch": 1.39,
+      "eval_loss": 0.6652340292930603,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 151.717,
+      "eval_steps_per_second": 7.78,
+      "step": 630
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.8050215316436293e-05,
+      "loss": 0.4743,
+      "step": 640
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.6671280264854431,
+      "eval_runtime": 1.0289,
+      "eval_samples_per_second": 151.616,
+      "eval_steps_per_second": 7.775,
+      "step": 640
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.7958041689153963e-05,
+      "loss": 0.4576,
+      "step": 650
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.6608811616897583,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.816,
+      "eval_steps_per_second": 7.785,
+      "step": 650
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.7863986317333483e-05,
+      "loss": 0.4639,
+      "step": 660
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.6664372086524963,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.807,
+      "eval_steps_per_second": 7.785,
+      "step": 660
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.776807144114261e-05,
+      "loss": 0.4691,
+      "step": 670
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.6644898653030396,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.743,
+      "eval_steps_per_second": 7.782,
+      "step": 670
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.767031974044424e-05,
+      "loss": 0.496,
+      "step": 680
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.6639735698699951,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.832,
+      "eval_steps_per_second": 7.786,
+      "step": 680
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.7570754329433555e-05,
+      "loss": 0.4538,
+      "step": 690
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 0.6662041544914246,
+      "eval_runtime": 1.0286,
+      "eval_samples_per_second": 151.662,
+      "eval_steps_per_second": 7.778,
+      "step": 690
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.7469398751172487e-05,
+      "loss": 0.493,
+      "step": 700
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.6623759865760803,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.928,
+      "eval_steps_per_second": 7.791,
+      "step": 700
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.736627697202277e-05,
+      "loss": 0.515,
+      "step": 710
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.6613351106643677,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.757,
+      "eval_steps_per_second": 7.782,
+      "step": 710
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.726141337597889e-05,
+      "loss": 0.4795,
+      "step": 720
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.6653904914855957,
+      "eval_runtime": 1.0295,
+      "eval_samples_per_second": 151.531,
+      "eval_steps_per_second": 7.771,
+      "step": 720
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.7154832758902294e-05,
+      "loss": 0.481,
+      "step": 730
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.6611121892929077,
+      "eval_runtime": 1.0267,
+      "eval_samples_per_second": 151.944,
+      "eval_steps_per_second": 7.792,
+      "step": 730
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.70465603226582e-05,
+      "loss": 0.4487,
+      "step": 740
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 0.6649742126464844,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.925,
+      "eval_steps_per_second": 7.791,
+      "step": 740
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.6936621669156415e-05,
+      "loss": 0.4189,
+      "step": 750
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 0.6644548177719116,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.82,
+      "eval_steps_per_second": 7.786,
+      "step": 750
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.682504279429754e-05,
+      "loss": 0.4934,
+      "step": 760
+    },
+    {
+      "epoch": 1.67,
+      "eval_loss": 0.6619623899459839,
+      "eval_runtime": 1.0261,
+      "eval_samples_per_second": 152.033,
+      "eval_steps_per_second": 7.797,
+      "step": 760
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.6711850081826037e-05,
+      "loss": 0.4844,
+      "step": 770
+    },
+    {
+      "epoch": 1.69,
+      "eval_loss": 0.6604421734809875,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.793,
+      "eval_steps_per_second": 7.784,
+      "step": 770
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.659707029709157e-05,
+      "loss": 0.5052,
+      "step": 780
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 0.6578311324119568,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.853,
+      "eval_steps_per_second": 7.787,
+      "step": 780
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.648073058072012e-05,
+      "loss": 0.4886,
+      "step": 790
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.660020649433136,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.738,
+      "eval_steps_per_second": 7.781,
+      "step": 790
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.6362858442196353e-05,
+      "loss": 0.4876,
+      "step": 800
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.6581898331642151,
+      "eval_runtime": 1.0271,
+      "eval_samples_per_second": 151.881,
+      "eval_steps_per_second": 7.789,
+      "step": 800
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.624348175335879e-05,
+      "loss": 0.4712,
+      "step": 810
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.6591123342514038,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.806,
+      "eval_steps_per_second": 7.785,
+      "step": 810
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.78125,
+      "learning_rate": 1.6122628741809267e-05,
+      "loss": 0.4509,
+      "step": 820
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.6636472940444946,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.799,
+      "eval_steps_per_second": 7.785,
+      "step": 820
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.6000327984238292e-05,
+      "loss": 0.4656,
+      "step": 830
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.6625650525093079,
+      "eval_runtime": 1.0266,
+      "eval_samples_per_second": 151.961,
+      "eval_steps_per_second": 7.793,
+      "step": 830
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 2.5,
+      "learning_rate": 1.587660839966785e-05,
+      "loss": 0.4864,
+      "step": 840
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 0.6568517684936523,
+      "eval_runtime": 1.0264,
+      "eval_samples_per_second": 151.99,
+      "eval_steps_per_second": 7.794,
+      "step": 840
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.640625,
+      "learning_rate": 1.575149924261326e-05,
+      "loss": 0.4185,
+      "step": 850
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.6581058502197266,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.838,
+      "eval_steps_per_second": 7.787,
+      "step": 850
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 5.46875,
+      "learning_rate": 1.562503009616571e-05,
+      "loss": 0.4396,
+      "step": 860
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.6597100496292114,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.81,
+      "eval_steps_per_second": 7.785,
+      "step": 860
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.549723086499709e-05,
+      "loss": 0.4812,
+      "step": 870
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.6601681709289551,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.797,
+      "eval_steps_per_second": 7.784,
+      "step": 870
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.5368131768288778e-05,
+      "loss": 0.4405,
+      "step": 880
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.6570097804069519,
+      "eval_runtime": 1.0264,
+      "eval_samples_per_second": 151.987,
+      "eval_steps_per_second": 7.794,
+      "step": 880
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.5237763332586073e-05,
+      "loss": 0.4731,
+      "step": 890
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.6559377908706665,
+      "eval_runtime": 1.0261,
+      "eval_samples_per_second": 152.033,
+      "eval_steps_per_second": 7.797,
+      "step": 890
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.5106156384579942e-05,
+      "loss": 0.476,
+      "step": 900
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.6569525003433228,
+      "eval_runtime": 1.0261,
+      "eval_samples_per_second": 152.036,
+      "eval_steps_per_second": 7.797,
+      "step": 900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.09375,
+      "learning_rate": 1.497334204381778e-05,
+      "loss": 0.4482,
+      "step": 910
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.655533492565155,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.826,
+      "eval_steps_per_second": 7.786,
+      "step": 910
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.4839351715344967e-05,
+      "loss": 0.3162,
+      "step": 920
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.7298592329025269,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.633,
+      "eval_steps_per_second": 7.776,
+      "step": 920
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.4704217082278858e-05,
+      "loss": 0.2976,
+      "step": 930
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 0.711938738822937,
+      "eval_runtime": 1.0294,
+      "eval_samples_per_second": 151.548,
+      "eval_steps_per_second": 7.772,
+      "step": 930
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4567970098317062e-05,
+      "loss": 0.2848,
+      "step": 940
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 0.7092500329017639,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 151.677,
+      "eval_steps_per_second": 7.778,
+      "step": 940
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.4430642980181719e-05,
+      "loss": 0.2898,
+      "step": 950
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 0.719861626625061,
+      "eval_runtime": 1.0289,
+      "eval_samples_per_second": 151.611,
+      "eval_steps_per_second": 7.775,
+      "step": 950
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.4292268200001604e-05,
+      "loss": 0.2754,
+      "step": 960
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 0.7190503478050232,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.924,
+      "eval_steps_per_second": 7.791,
+      "step": 960
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.415287847763381e-05,
+      "loss": 0.2784,
+      "step": 970
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.728531539440155,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.856,
+      "eval_steps_per_second": 7.787,
+      "step": 970
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.4012506772926875e-05,
+      "loss": 0.285,
+      "step": 980
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 0.7191035747528076,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.632,
+      "eval_steps_per_second": 7.776,
+      "step": 980
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.3871186277927152e-05,
+      "loss": 0.2773,
+      "step": 990
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 0.7178661227226257,
+      "eval_runtime": 1.0302,
+      "eval_samples_per_second": 151.42,
+      "eval_steps_per_second": 7.765,
+      "step": 990
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.3728950409030284e-05,
+      "loss": 0.2906,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 0.7206559777259827,
+      "eval_runtime": 1.0321,
+      "eval_samples_per_second": 151.142,
+      "eval_steps_per_second": 7.751,
+      "step": 1000
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.358583279907961e-05,
+      "loss": 0.2793,
+      "step": 1010
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 0.721248209476471,
+      "eval_runtime": 1.0231,
+      "eval_samples_per_second": 152.471,
+      "eval_steps_per_second": 7.819,
+      "step": 1010
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.3441867289413408e-05,
+      "loss": 0.2862,
+      "step": 1020
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.7261033654212952,
+      "eval_runtime": 1.0238,
+      "eval_samples_per_second": 152.38,
+      "eval_steps_per_second": 7.814,
+      "step": 1020
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.329708792186283e-05,
+      "loss": 0.2846,
+      "step": 1030
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.7261976599693298,
+      "eval_runtime": 1.0241,
+      "eval_samples_per_second": 152.334,
+      "eval_steps_per_second": 7.812,
+      "step": 1030
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.315152893070244e-05,
+      "loss": 0.2958,
+      "step": 1040
+    },
+    {
+      "epoch": 2.29,
+      "eval_loss": 0.7268620729446411,
+      "eval_runtime": 1.0256,
+      "eval_samples_per_second": 152.111,
+      "eval_steps_per_second": 7.801,
+      "step": 1040
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.3005224734555215e-05,
+      "loss": 0.2945,
+      "step": 1050
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 0.7208532691001892,
+      "eval_runtime": 1.026,
+      "eval_samples_per_second": 152.051,
+      "eval_steps_per_second": 7.797,
+      "step": 1050
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.2858209928254001e-05,
+      "loss": 0.2882,
+      "step": 1060
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 0.7226111888885498,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.843,
+      "eval_steps_per_second": 7.787,
+      "step": 1060
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.2710519274661275e-05,
+      "loss": 0.2872,
+      "step": 1070
+    },
+    {
+      "epoch": 2.35,
+      "eval_loss": 0.7272056937217712,
+      "eval_runtime": 1.0264,
+      "eval_samples_per_second": 151.989,
+      "eval_steps_per_second": 7.794,
+      "step": 1070
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.75,
+      "learning_rate": 1.2562187696449166e-05,
+      "loss": 0.3138,
+      "step": 1080
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 0.720583975315094,
+      "eval_runtime": 1.0272,
+      "eval_samples_per_second": 151.866,
+      "eval_steps_per_second": 7.788,
+      "step": 1080
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.2413250267841716e-05,
+      "loss": 0.2623,
+      "step": 1090
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.7252639532089233,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.782,
+      "eval_steps_per_second": 7.784,
+      "step": 1090
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 3.25,
+      "learning_rate": 1.2263742206321287e-05,
+      "loss": 0.2881,
+      "step": 1100
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 0.7257930636405945,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.758,
+      "eval_steps_per_second": 7.782,
+      "step": 1100
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.75,
+      "learning_rate": 1.2113698864301091e-05,
+      "loss": 0.2823,
+      "step": 1110
+    },
+    {
+      "epoch": 2.44,
+      "eval_loss": 0.7199146151542664,
+      "eval_runtime": 1.0294,
+      "eval_samples_per_second": 151.544,
+      "eval_steps_per_second": 7.771,
+      "step": 1110
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.1963155720765832e-05,
+      "loss": 0.2934,
+      "step": 1120
+    },
+    {
+      "epoch": 2.46,
+      "eval_loss": 0.7285863757133484,
+      "eval_runtime": 1.0299,
+      "eval_samples_per_second": 151.477,
+      "eval_steps_per_second": 7.768,
+      "step": 1120
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 3.375,
+      "learning_rate": 1.1812148372882389e-05,
+      "loss": 0.2711,
+      "step": 1130
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 0.7325776219367981,
+      "eval_runtime": 1.0283,
+      "eval_samples_per_second": 151.702,
+      "eval_steps_per_second": 7.78,
+      "step": 1130
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.16607125275826e-05,
+      "loss": 0.3202,
+      "step": 1140
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 0.716628909111023,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.934,
+      "eval_steps_per_second": 7.792,
+      "step": 1140
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.1508883993120041e-05,
+      "loss": 0.3144,
+      "step": 1150
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.717096745967865,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.757,
+      "eval_steps_per_second": 7.782,
+      "step": 1150
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.1356698670602873e-05,
+      "loss": 0.2607,
+      "step": 1160
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 0.7311819791793823,
+      "eval_runtime": 1.0307,
+      "eval_samples_per_second": 151.348,
+      "eval_steps_per_second": 7.761,
+      "step": 1160
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.1204192545504737e-05,
+      "loss": 0.2954,
+      "step": 1170
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.7281209230422974,
+      "eval_runtime": 1.0319,
+      "eval_samples_per_second": 151.178,
+      "eval_steps_per_second": 7.753,
+      "step": 1170
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.1051401679155691e-05,
+      "loss": 0.296,
+      "step": 1180
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.7209986448287964,
+      "eval_runtime": 1.029,
+      "eval_samples_per_second": 151.599,
+      "eval_steps_per_second": 7.774,
+      "step": 1180
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.0898362200215199e-05,
+      "loss": 0.2687,
+      "step": 1190
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 0.7288104891777039,
+      "eval_runtime": 1.0323,
+      "eval_samples_per_second": 151.121,
+      "eval_steps_per_second": 7.75,
+      "step": 1190
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.074511029612923e-05,
+      "loss": 0.2952,
+      "step": 1200
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.7337983250617981,
+      "eval_runtime": 1.0329,
+      "eval_samples_per_second": 151.036,
+      "eval_steps_per_second": 7.745,
+      "step": 1200
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.0591682204573425e-05,
+      "loss": 0.2755,
+      "step": 1210
+    },
+    {
+      "epoch": 2.66,
+      "eval_loss": 0.7264887690544128,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.734,
+      "eval_steps_per_second": 7.781,
+      "step": 1210
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.0438114204884404e-05,
+      "loss": 0.2768,
+      "step": 1220
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 0.729884684085846,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.769,
+      "eval_steps_per_second": 7.783,
+      "step": 1220
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.0284442609481225e-05,
+      "loss": 0.2846,
+      "step": 1230
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 0.733102023601532,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.758,
+      "eval_steps_per_second": 7.782,
+      "step": 1230
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 3.140625,
+      "learning_rate": 1.0130703755278992e-05,
+      "loss": 0.2763,
+      "step": 1240
+    },
+    {
+      "epoch": 2.73,
+      "eval_loss": 0.7278034090995789,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.732,
+      "eval_steps_per_second": 7.781,
+      "step": 1240
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.625,
+      "learning_rate": 9.976933995096717e-06,
+      "loss": 0.2728,
+      "step": 1250
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 0.7328708171844482,
+      "eval_runtime": 1.0293,
+      "eval_samples_per_second": 151.555,
+      "eval_steps_per_second": 7.772,
+      "step": 1250
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 3.09375,
+      "learning_rate": 9.823169689061384e-06,
+      "loss": 0.2928,
+      "step": 1260
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 0.732266366481781,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.917,
+      "eval_steps_per_second": 7.791,
+      "step": 1260
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.640625,
+      "learning_rate": 9.669447196010295e-06,
+      "loss": 0.2868,
+      "step": 1270
+    },
+    {
+      "epoch": 2.79,
+      "eval_loss": 0.7313841581344604,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.741,
+      "eval_steps_per_second": 7.782,
+      "step": 1270
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 3.21875,
+      "learning_rate": 9.51580286489374e-06,
+      "loss": 0.2911,
+      "step": 1280
+    },
+    {
+      "epoch": 2.82,
+      "eval_loss": 0.730948269367218,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.76,
+      "eval_steps_per_second": 7.783,
+      "step": 1280
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 3.53125,
+      "learning_rate": 9.362273026179958e-06,
+      "loss": 0.2918,
+      "step": 1290
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 0.7271366715431213,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.892,
+      "eval_steps_per_second": 7.789,
+      "step": 1290
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.208893983264522e-06,
+      "loss": 0.2759,
+      "step": 1300
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.7273522615432739,
+      "eval_runtime": 1.0297,
+      "eval_samples_per_second": 151.505,
+      "eval_steps_per_second": 7.77,
+      "step": 1300
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.828125,
+      "learning_rate": 9.055702003886107e-06,
+      "loss": 0.2849,
+      "step": 1310
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 0.725708544254303,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.796,
+      "eval_steps_per_second": 7.784,
+      "step": 1310
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 2.421875,
+      "learning_rate": 8.902733311550658e-06,
+      "loss": 0.2843,
+      "step": 1320
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 0.7219725847244263,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.773,
+      "eval_steps_per_second": 7.783,
+      "step": 1320
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.046875,
+      "learning_rate": 8.750024076966059e-06,
+      "loss": 0.2957,
+      "step": 1330
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.7244921326637268,
+      "eval_runtime": 1.0295,
+      "eval_samples_per_second": 151.524,
+      "eval_steps_per_second": 7.77,
+      "step": 1330
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 2.765625,
+      "learning_rate": 8.597610409489287e-06,
+      "loss": 0.2913,
+      "step": 1340
+    },
+    {
+      "epoch": 2.95,
+      "eval_loss": 0.7283746004104614,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 151.695,
+      "eval_steps_per_second": 7.779,
+      "step": 1340
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 3.34375,
+      "learning_rate": 8.445528348588026e-06,
+      "loss": 0.3032,
+      "step": 1350
+    },
+    {
+      "epoch": 2.97,
+      "eval_loss": 0.7312036156654358,
+      "eval_runtime": 1.0271,
+      "eval_samples_per_second": 151.883,
+      "eval_steps_per_second": 7.789,
+      "step": 1350
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 2.546875,
+      "learning_rate": 8.293813855318851e-06,
+      "loss": 0.272,
+      "step": 1360
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 0.7295395135879517,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.627,
+      "eval_steps_per_second": 7.776,
+      "step": 1360
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 2.328125,
+      "learning_rate": 8.142502803823954e-06,
+      "loss": 0.2311,
+      "step": 1370
+    },
+    {
+      "epoch": 3.01,
+      "eval_loss": 0.7461617588996887,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 151.64,
+      "eval_steps_per_second": 7.776,
+      "step": 1370
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 3.265625,
+      "learning_rate": 7.991630972848384e-06,
+      "loss": 0.2038,
+      "step": 1380
+    },
+    {
+      "epoch": 3.04,
+      "eval_loss": 0.8119441866874695,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 151.671,
+      "eval_steps_per_second": 7.778,
+      "step": 1380
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 3.046875,
+      "learning_rate": 7.841234037279878e-06,
+      "loss": 0.1993,
+      "step": 1390
+    },
+    {
+      "epoch": 3.06,
+      "eval_loss": 0.8213101625442505,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.838,
+      "eval_steps_per_second": 7.787,
+      "step": 1390
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 2.8125,
+      "learning_rate": 7.691347559713251e-06,
+      "loss": 0.1882,
+      "step": 1400
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 0.8104899525642395,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 151.685,
+      "eval_steps_per_second": 7.779,
+      "step": 1400
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 2.9375,
+      "learning_rate": 7.54200698204131e-06,
+      "loss": 0.1919,
+      "step": 1410
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 0.8027247190475464,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.856,
+      "eval_steps_per_second": 7.788,
+      "step": 1410
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 2.765625,
+      "learning_rate": 7.39324761707433e-06,
+      "loss": 0.1934,
+      "step": 1420
+    },
+    {
+      "epoch": 3.12,
+      "eval_loss": 0.8067971467971802,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.917,
+      "eval_steps_per_second": 7.791,
+      "step": 1420
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 3.0,
+      "learning_rate": 7.245104640190052e-06,
+      "loss": 0.1876,
+      "step": 1430
+    },
+    {
+      "epoch": 3.15,
+      "eval_loss": 0.8202968835830688,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.829,
+      "eval_steps_per_second": 7.786,
+      "step": 1430
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 2.375,
+      "learning_rate": 7.097613081016191e-06,
+      "loss": 0.2005,
+      "step": 1440
+    },
+    {
+      "epoch": 3.17,
+      "eval_loss": 0.8179227709770203,
+      "eval_runtime": 1.0272,
+      "eval_samples_per_second": 151.868,
+      "eval_steps_per_second": 7.788,
+      "step": 1440
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.950807815147358e-06,
+      "loss": 0.1932,
+      "step": 1450
+    },
+    {
+      "epoch": 3.19,
+      "eval_loss": 0.8141485452651978,
+      "eval_runtime": 1.0265,
+      "eval_samples_per_second": 151.97,
+      "eval_steps_per_second": 7.793,
+      "step": 1450
+    },
+    {
+      "epoch": 3.21,
+      "grad_norm": 2.75,
+      "learning_rate": 6.804723555898458e-06,
+      "loss": 0.1868,
+      "step": 1460
+    },
+    {
+      "epoch": 3.21,
+      "eval_loss": 0.8194668889045715,
+      "eval_runtime": 1.0302,
+      "eval_samples_per_second": 151.427,
+      "eval_steps_per_second": 7.765,
+      "step": 1460
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 2.484375,
+      "learning_rate": 6.659394846096452e-06,
+      "loss": 0.196,
+      "step": 1470
+    },
+    {
+      "epoch": 3.23,
+      "eval_loss": 0.8170936703681946,
+      "eval_runtime": 1.0279,
+      "eval_samples_per_second": 151.758,
+      "eval_steps_per_second": 7.782,
+      "step": 1470
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 2.234375,
+      "learning_rate": 6.514856049912397e-06,
+      "loss": 0.1894,
+      "step": 1480
+    },
+    {
+      "epoch": 3.26,
+      "eval_loss": 0.8142940998077393,
+      "eval_runtime": 1.0289,
+      "eval_samples_per_second": 151.625,
+      "eval_steps_per_second": 7.776,
+      "step": 1480
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 2.109375,
+      "learning_rate": 6.371141344735764e-06,
+      "loss": 0.1852,
+      "step": 1490
+    },
+    {
+      "epoch": 3.28,
+      "eval_loss": 0.8115652203559875,
+      "eval_runtime": 1.0304,
+      "eval_samples_per_second": 151.393,
+      "eval_steps_per_second": 7.764,
+      "step": 1490
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 2.78125,
+      "learning_rate": 6.228284713092922e-06,
+      "loss": 0.186,
+      "step": 1500
+    },
+    {
+      "epoch": 3.3,
+      "eval_loss": 0.8131534457206726,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.899,
+      "eval_steps_per_second": 7.79,
+      "step": 1500
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 1.9296875,
+      "learning_rate": 6.086319934611682e-06,
+      "loss": 0.1904,
+      "step": 1510
+    },
+    {
+      "epoch": 3.32,
+      "eval_loss": 0.8167653679847717,
+      "eval_runtime": 1.0295,
+      "eval_samples_per_second": 151.535,
+      "eval_steps_per_second": 7.771,
+      "step": 1510
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 2.8125,
+      "learning_rate": 5.945280578033813e-06,
+      "loss": 0.1995,
+      "step": 1520
+    },
+    {
+      "epoch": 3.34,
+      "eval_loss": 0.8196493983268738,
+      "eval_runtime": 1.0286,
+      "eval_samples_per_second": 151.66,
+      "eval_steps_per_second": 7.777,
+      "step": 1520
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.805199993277462e-06,
+      "loss": 0.1965,
+      "step": 1530
+    },
+    {
+      "epoch": 3.37,
+      "eval_loss": 0.8189469575881958,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.739,
+      "eval_steps_per_second": 7.781,
+      "step": 1530
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 2.234375,
+      "learning_rate": 5.666111303551276e-06,
+      "loss": 0.1936,
+      "step": 1540
+    },
+    {
+      "epoch": 3.39,
+      "eval_loss": 0.8187676668167114,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.801,
+      "eval_steps_per_second": 7.785,
+      "step": 1540
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 2.453125,
+      "learning_rate": 5.5280473975221324e-06,
+      "loss": 0.2206,
+      "step": 1550
+    },
+    {
+      "epoch": 3.41,
+      "eval_loss": 0.817896842956543,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.825,
+      "eval_steps_per_second": 7.786,
+      "step": 1550
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 2.890625,
+      "learning_rate": 5.391040921538389e-06,
+      "loss": 0.2094,
+      "step": 1560
+    },
+    {
+      "epoch": 3.43,
+      "eval_loss": 0.8177632093429565,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.75,
+      "eval_steps_per_second": 7.782,
+      "step": 1560
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 2.53125,
+      "learning_rate": 5.255124271910323e-06,
+      "loss": 0.2109,
+      "step": 1570
+    },
+    {
+      "epoch": 3.45,
+      "eval_loss": 0.8160055875778198,
+      "eval_runtime": 1.0263,
+      "eval_samples_per_second": 152.002,
+      "eval_steps_per_second": 7.795,
+      "step": 1570
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 2.34375,
+      "learning_rate": 5.120329587249807e-06,
+      "loss": 0.1942,
+      "step": 1580
+    },
+    {
+      "epoch": 3.48,
+      "eval_loss": 0.8156926035881042,
+      "eval_runtime": 1.0281,
+      "eval_samples_per_second": 151.73,
+      "eval_steps_per_second": 7.781,
+      "step": 1580
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 2.875,
+      "learning_rate": 4.9866887408708535e-06,
+      "loss": 0.1809,
+      "step": 1590
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.8169762492179871,
+      "eval_runtime": 1.0263,
+      "eval_samples_per_second": 152.002,
+      "eval_steps_per_second": 7.795,
+      "step": 1590
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.8542333332528865e-06,
+      "loss": 0.194,
+      "step": 1600
+    },
+    {
+      "epoch": 3.52,
+      "eval_loss": 0.8198422193527222,
+      "eval_runtime": 1.0268,
+      "eval_samples_per_second": 151.933,
+      "eval_steps_per_second": 7.791,
+      "step": 1600
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 3.9375,
+      "learning_rate": 4.722994684568586e-06,
+      "loss": 0.1982,
+      "step": 1610
+    },
+    {
+      "epoch": 3.54,
+      "eval_loss": 0.8185614347457886,
+      "eval_runtime": 1.0299,
+      "eval_samples_per_second": 151.474,
+      "eval_steps_per_second": 7.768,
+      "step": 1610
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 2.90625,
+      "learning_rate": 4.593003827277944e-06,
+      "loss": 0.2056,
+      "step": 1620
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 0.8191636204719543,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.787,
+      "eval_steps_per_second": 7.784,
+      "step": 1620
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.464291498790402e-06,
+      "loss": 0.194,
+      "step": 1630
+    },
+    {
+      "epoch": 3.59,
+      "eval_loss": 0.8186812400817871,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.897,
+      "eval_steps_per_second": 7.79,
+      "step": 1630
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 3.359375,
+      "learning_rate": 4.3368881341967135e-06,
+      "loss": 0.1938,
+      "step": 1640
+    },
+    {
+      "epoch": 3.61,
+      "eval_loss": 0.8184131979942322,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.845,
+      "eval_steps_per_second": 7.787,
+      "step": 1640
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 2.6875,
+      "learning_rate": 4.210823859072362e-06,
+      "loss": 0.2154,
+      "step": 1650
+    },
+    {
+      "epoch": 3.63,
+      "eval_loss": 0.8162879943847656,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.918,
+      "eval_steps_per_second": 7.791,
+      "step": 1650
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 2.328125,
+      "learning_rate": 4.086128482354058e-06,
+      "loss": 0.1851,
+      "step": 1660
+    },
+    {
+      "epoch": 3.65,
+      "eval_loss": 0.8180512189865112,
+      "eval_runtime": 1.0265,
+      "eval_samples_per_second": 151.973,
+      "eval_steps_per_second": 7.793,
+      "step": 1660
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 2.578125,
+      "learning_rate": 3.962831489291223e-06,
+      "loss": 0.1848,
+      "step": 1670
+    },
+    {
+      "epoch": 3.67,
+      "eval_loss": 0.8209714889526367,
+      "eval_runtime": 1.0274,
+      "eval_samples_per_second": 151.841,
+      "eval_steps_per_second": 7.787,
+      "step": 1670
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 2.375,
+      "learning_rate": 3.840962034473936e-06,
+      "loss": 0.1876,
+      "step": 1680
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 0.8223714828491211,
+      "eval_runtime": 1.0265,
+      "eval_samples_per_second": 151.975,
+      "eval_steps_per_second": 7.794,
+      "step": 1680
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 2.546875,
+      "learning_rate": 3.7205489349390953e-06,
+      "loss": 0.193,
+      "step": 1690
+    },
+    {
+      "epoch": 3.72,
+      "eval_loss": 0.8224756121635437,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.781,
+      "eval_steps_per_second": 7.784,
+      "step": 1690
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 3.03125,
+      "learning_rate": 3.60162066335638e-06,
+      "loss": 0.1943,
+      "step": 1700
+    },
+    {
+      "epoch": 3.74,
+      "eval_loss": 0.8223010301589966,
+      "eval_runtime": 1.0266,
+      "eval_samples_per_second": 151.961,
+      "eval_steps_per_second": 7.793,
+      "step": 1700
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 2.5,
+      "learning_rate": 3.4842053412956757e-06,
+      "loss": 0.1995,
+      "step": 1710
+    },
+    {
+      "epoch": 3.76,
+      "eval_loss": 0.8211143612861633,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.897,
+      "eval_steps_per_second": 7.79,
+      "step": 1710
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 2.59375,
+      "learning_rate": 3.3683307325774818e-06,
+      "loss": 0.2074,
+      "step": 1720
+    },
+    {
+      "epoch": 3.78,
+      "eval_loss": 0.8206495642662048,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 151.819,
+      "eval_steps_per_second": 7.786,
+      "step": 1720
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 2.28125,
+      "learning_rate": 3.25402423670793e-06,
+      "loss": 0.1968,
+      "step": 1730
+    },
+    {
+      "epoch": 3.81,
+      "eval_loss": 0.8195406198501587,
+      "eval_runtime": 1.0267,
+      "eval_samples_per_second": 151.942,
+      "eval_steps_per_second": 7.792,
+      "step": 1730
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 3.171875,
+      "learning_rate": 3.141312882399952e-06,
+      "loss": 0.2056,
+      "step": 1740
+    },
+    {
+      "epoch": 3.83,
+      "eval_loss": 0.8185840249061584,
+      "eval_runtime": 1.0251,
+      "eval_samples_per_second": 152.183,
+      "eval_steps_per_second": 7.804,
+      "step": 1740
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 2.8125,
+      "learning_rate": 3.0302233211821e-06,
+      "loss": 0.1936,
+      "step": 1750
+    },
+    {
+      "epoch": 3.85,
+      "eval_loss": 0.8186120390892029,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.86,
+      "eval_steps_per_second": 7.788,
+      "step": 1750
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 2.421875,
+      "learning_rate": 2.9207818210965987e-06,
+      "loss": 0.1805,
+      "step": 1760
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 0.8195428848266602,
+      "eval_runtime": 1.0283,
+      "eval_samples_per_second": 151.71,
+      "eval_steps_per_second": 7.78,
+      "step": 1760
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 2.765625,
+      "learning_rate": 2.8130142604880228e-06,
+      "loss": 0.1926,
+      "step": 1770
+    },
+    {
+      "epoch": 3.89,
+      "eval_loss": 0.8200863003730774,
+      "eval_runtime": 1.0258,
+      "eval_samples_per_second": 152.076,
+      "eval_steps_per_second": 7.799,
+      "step": 1770
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 2.28125,
+      "learning_rate": 2.7069461218841806e-06,
+      "loss": 0.1945,
+      "step": 1780
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 0.8192042112350464,
+      "eval_runtime": 1.0259,
+      "eval_samples_per_second": 152.062,
+      "eval_steps_per_second": 7.798,
+      "step": 1780
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 3.28125,
+      "learning_rate": 2.6026024859705256e-06,
+      "loss": 0.2178,
+      "step": 1790
+    },
+    {
+      "epoch": 3.94,
+      "eval_loss": 0.8187469244003296,
+      "eval_runtime": 1.0262,
+      "eval_samples_per_second": 152.013,
+      "eval_steps_per_second": 7.796,
+      "step": 1790
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.53125,
+      "learning_rate": 2.500008025659648e-06,
+      "loss": 0.184,
+      "step": 1800
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 0.8194283246994019,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.921,
+      "eval_steps_per_second": 7.791,
+      "step": 1800
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 2.265625,
+      "learning_rate": 2.3991870002571517e-06,
+      "loss": 0.2091,
+      "step": 1810
+    },
+    {
+      "epoch": 3.98,
+      "eval_loss": 0.8195890784263611,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 151.806,
+      "eval_steps_per_second": 7.785,
+      "step": 1810
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.625,
+      "learning_rate": 2.3001632497253423e-06,
+      "loss": 0.2221,
+      "step": 1820
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8198089599609375,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 151.903,
+      "eval_steps_per_second": 7.79,
+      "step": 1820
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 2.21875,
+      "learning_rate": 2.202960189046062e-06,
+      "loss": 0.173,
+      "step": 1830
+    },
+    {
+      "epoch": 4.03,
+      "eval_loss": 0.8222331404685974,
+      "eval_runtime": 1.026,
+      "eval_samples_per_second": 152.049,
+      "eval_steps_per_second": 7.797,
+      "step": 1830
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 2.5625,
+      "learning_rate": 2.10760080268405e-06,
+      "loss": 0.1837,
+      "step": 1840
+    },
+    {
+      "epoch": 4.05,
+      "eval_loss": 0.8266891837120056,
+      "eval_runtime": 1.026,
+      "eval_samples_per_second": 152.045,
+      "eval_steps_per_second": 7.797,
+      "step": 1840
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 2.328125,
+      "learning_rate": 2.0141076391520443e-06,
+      "loss": 0.179,
+      "step": 1850
+    },
+    {
+      "epoch": 4.07,
+      "eval_loss": 0.8306039571762085,
+      "eval_runtime": 1.0254,
+      "eval_samples_per_second": 152.137,
+      "eval_steps_per_second": 7.802,
+      "step": 1850
+    },
+    {
+      "epoch": 4.09,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.922502805679025e-06,
+      "loss": 0.1526,
+      "step": 1860
+    },
+    {
+      "epoch": 4.09,
+      "eval_loss": 0.8337188363075256,
+      "eval_runtime": 1.0271,
+      "eval_samples_per_second": 151.878,
+      "eval_steps_per_second": 7.789,
+      "step": 1860
+    },
+    {
+      "epoch": 4.11,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.8328079629827667e-06,
+      "loss": 0.1774,
+      "step": 1870
+    },
+    {
+      "epoch": 4.11,
+      "eval_loss": 0.8363264203071594,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.847,
+      "eval_steps_per_second": 7.787,
+      "step": 1870
+    },
+    {
+      "epoch": 4.14,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.7450443201479771e-06,
+      "loss": 0.1855,
+      "step": 1880
+    },
+    {
+      "epoch": 4.14,
+      "eval_loss": 0.8378145098686218,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 151.683,
+      "eval_steps_per_second": 7.779,
+      "step": 1880
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.6592326296112548e-06,
+      "loss": 0.1778,
+      "step": 1890
+    },
+    {
+      "epoch": 4.16,
+      "eval_loss": 0.8393206596374512,
+      "eval_runtime": 1.0278,
+      "eval_samples_per_second": 151.784,
+      "eval_steps_per_second": 7.784,
+      "step": 1890
+    },
+    {
+      "epoch": 4.18,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.5753931822539824e-06,
+      "loss": 0.1877,
+      "step": 1900
+    },
+    {
+      "epoch": 4.18,
+      "eval_loss": 0.8407032489776611,
+      "eval_runtime": 1.0251,
+      "eval_samples_per_second": 152.173,
+      "eval_steps_per_second": 7.804,
+      "step": 1900
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 2.875,
+      "learning_rate": 1.4935458026043958e-06,
+      "loss": 0.1836,
+      "step": 1910
+    },
+    {
+      "epoch": 4.2,
+      "eval_loss": 0.8414338231086731,
+      "eval_runtime": 1.028,
+      "eval_samples_per_second": 151.755,
+      "eval_steps_per_second": 7.782,
+      "step": 1910
+    },
+    {
+      "epoch": 4.22,
+      "grad_norm": 3.375,
+      "learning_rate": 1.4137098441498965e-06,
+      "loss": 0.1817,
+      "step": 1920
+    },
+    {
+      "epoch": 4.22,
+      "eval_loss": 0.8417092561721802,
+      "eval_runtime": 1.0273,
+      "eval_samples_per_second": 151.854,
+      "eval_steps_per_second": 7.787,
+      "step": 1920
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.3359041847607823e-06,
+      "loss": 0.1859,
+      "step": 1930
+    },
+    {
+      "epoch": 4.25,
+      "eval_loss": 0.8419297933578491,
+      "eval_runtime": 1.0249,
+      "eval_samples_per_second": 152.214,
+      "eval_steps_per_second": 7.806,
+      "step": 1930
+    },
+    {
+      "epoch": 4.27,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.2601472222263912e-06,
+      "loss": 0.1817,
+      "step": 1940
+    },
+    {
+      "epoch": 4.27,
+      "eval_loss": 0.8424677848815918,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.915,
+      "eval_steps_per_second": 7.79,
+      "step": 1940
+    },
+    {
+      "epoch": 4.29,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.1864568699048162e-06,
+      "loss": 0.1717,
+      "step": 1950
+    },
+    {
+      "epoch": 4.29,
+      "eval_loss": 0.8427534103393555,
+      "eval_runtime": 1.0277,
+      "eval_samples_per_second": 151.803,
+      "eval_steps_per_second": 7.785,
+      "step": 1950
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.1148505524871334e-06,
+      "loss": 0.172,
+      "step": 1960
+    },
+    {
+      "epoch": 4.31,
+      "eval_loss": 0.8427566885948181,
+      "eval_runtime": 1.0257,
+      "eval_samples_per_second": 152.094,
+      "eval_steps_per_second": 7.8,
+      "step": 1960
+    },
+    {
+      "epoch": 4.33,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.0453452018771904e-06,
+      "loss": 0.1709,
+      "step": 1970
+    },
+    {
+      "epoch": 4.33,
+      "eval_loss": 0.8430888652801514,
+      "eval_runtime": 1.0257,
+      "eval_samples_per_second": 152.098,
+      "eval_steps_per_second": 7.8,
+      "step": 1970
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.779572531879166e-07,
+      "loss": 0.1756,
+      "step": 1980
+    },
+    {
+      "epoch": 4.36,
+      "eval_loss": 0.8433722257614136,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 151.917,
+      "eval_steps_per_second": 7.791,
+      "step": 1980
+    },
+    {
+      "epoch": 4.38,
+      "grad_norm": 2.921875,
+      "learning_rate": 9.127026408551143e-07,
+      "loss": 0.1839,
+      "step": 1990
+    },
+    {
+      "epoch": 4.38,
+      "eval_loss": 0.8435284495353699,
+      "eval_runtime": 1.0266,
+      "eval_samples_per_second": 151.964,
+      "eval_steps_per_second": 7.793,
+      "step": 1990
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.171875,
+      "learning_rate": 8.495967948696193e-07,
+      "loss": 0.1821,
+      "step": 2000
+    },
+    {
+      "epoch": 4.4,
+      "eval_loss": 0.8436821103096008,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 151.723,
+      "eval_steps_per_second": 7.781,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "total_flos": 9.266133733054874e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}