Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9982466393921683,
+    "total_flos": 77746305761280.0,
+    "train_loss": 0.8145518043281323,
+    "train_runtime": 5184.5045,
+    "train_samples_per_second": 10.56,
+    "train_steps_per_second": 0.082
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbec9d0e8696c842f201e6eca0df9c5959ac99a1a1be904027b435d570d8fad0
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa388768206e14184e450ff4623eb45fcbcc2e1923657b88e0bf3125d54659f
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35014179bac3831ea0a7f2612d661d4b6b9b4c7fc80b6184dc6d98e2c244262a
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544fa70a574dbd8f170b29940c7893b1ad7ee11f1ecf90c23f583f7b23bcc7e2
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "left"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9982466393921683,
+    "total_flos": 77746305761280.0,
+    "train_loss": 0.8145518043281323,
+    "train_runtime": 5184.5045,
+    "train_samples_per_second": 10.56,
+    "train_steps_per_second": 0.082
+}

trainer_state.json

@@ -0,0 +1,3019 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9982466393921683,
+  "eval_steps": 500,
+  "global_step": 427,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023378141437755697,
+      "grad_norm": 27.288526825189052,
+      "learning_rate": 0.0,
+      "loss": 2.2488,
+      "step": 1
+    },
+    {
+      "epoch": 0.004675628287551139,
+      "grad_norm": 18.402597061645437,
+      "learning_rate": 1.3511907721365987e-06,
+      "loss": 1.7216,
+      "step": 2
+    },
+    {
+      "epoch": 0.0070134424313267095,
+      "grad_norm": 20.827793127279097,
+      "learning_rate": 2.1415867051569737e-06,
+      "loss": 1.8096,
+      "step": 3
+    },
+    {
+      "epoch": 0.009351256575102279,
+      "grad_norm": 17.887138033549412,
+      "learning_rate": 2.7023815442731975e-06,
+      "loss": 1.7273,
+      "step": 4
+    },
+    {
+      "epoch": 0.011689070718877849,
+      "grad_norm": 13.059331628307975,
+      "learning_rate": 3.137367815376517e-06,
+      "loss": 1.3944,
+      "step": 5
+    },
+    {
+      "epoch": 0.014026884862653419,
+      "grad_norm": 12.915220380638836,
+      "learning_rate": 3.4927774772935725e-06,
+      "loss": 1.3309,
+      "step": 6
+    },
+    {
+      "epoch": 0.01636469900642899,
+      "grad_norm": 9.438170554483921,
+      "learning_rate": 3.7932720647964956e-06,
+      "loss": 1.1377,
+      "step": 7
+    },
+    {
+      "epoch": 0.018702513150204558,
+      "grad_norm": 22.34498398581149,
+      "learning_rate": 4.053572316409796e-06,
+      "loss": 1.276,
+      "step": 8
+    },
+    {
+      "epoch": 0.02104032729398013,
+      "grad_norm": 11.688684740044469,
+      "learning_rate": 4.2831734103139475e-06,
+      "loss": 1.1626,
+      "step": 9
+    },
+    {
+      "epoch": 0.023378141437755698,
+      "grad_norm": 7.399035066119634,
+      "learning_rate": 4.488558587513117e-06,
+      "loss": 1.0172,
+      "step": 10
+    },
+    {
+      "epoch": 0.02571595558153127,
+      "grad_norm": 6.844826809549996,
+      "learning_rate": 4.674352079940294e-06,
+      "loss": 1.0159,
+      "step": 11
+    },
+    {
+      "epoch": 0.028053769725306838,
+      "grad_norm": 7.435042287761434,
+      "learning_rate": 4.843968249430172e-06,
+      "loss": 1.0191,
+      "step": 12
+    },
+    {
+      "epoch": 0.030391583869082407,
+      "grad_norm": 8.142142185574825,
+      "learning_rate": 5e-06,
+      "loss": 1.0605,
+      "step": 13
+    },
+    {
+      "epoch": 0.03272939801285798,
+      "grad_norm": 6.515223941306322,
+      "learning_rate": 5e-06,
+      "loss": 0.9758,
+      "step": 14
+    },
+    {
+      "epoch": 0.03506721215663355,
+      "grad_norm": 6.0290403123052965,
+      "learning_rate": 4.98792270531401e-06,
+      "loss": 0.995,
+      "step": 15
+    },
+    {
+      "epoch": 0.037405026300409115,
+      "grad_norm": 5.319952909218166,
+      "learning_rate": 4.97584541062802e-06,
+      "loss": 0.9515,
+      "step": 16
+    },
+    {
+      "epoch": 0.03974284044418469,
+      "grad_norm": 5.748688589731486,
+      "learning_rate": 4.963768115942029e-06,
+      "loss": 1.0102,
+      "step": 17
+    },
+    {
+      "epoch": 0.04208065458796026,
+      "grad_norm": 5.855208805312462,
+      "learning_rate": 4.951690821256039e-06,
+      "loss": 0.9919,
+      "step": 18
+    },
+    {
+      "epoch": 0.04441846873173583,
+      "grad_norm": 5.223174635069425,
+      "learning_rate": 4.939613526570048e-06,
+      "loss": 0.9656,
+      "step": 19
+    },
+    {
+      "epoch": 0.046756282875511396,
+      "grad_norm": 6.065299105647371,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 0.9285,
+      "step": 20
+    },
+    {
+      "epoch": 0.049094097019286964,
+      "grad_norm": 6.07241545277926,
+      "learning_rate": 4.915458937198068e-06,
+      "loss": 1.0017,
+      "step": 21
+    },
+    {
+      "epoch": 0.05143191116306254,
+      "grad_norm": 5.246067572533348,
+      "learning_rate": 4.903381642512078e-06,
+      "loss": 1.0095,
+      "step": 22
+    },
+    {
+      "epoch": 0.05376972530683811,
+      "grad_norm": 5.990327031501364,
+      "learning_rate": 4.891304347826087e-06,
+      "loss": 0.9395,
+      "step": 23
+    },
+    {
+      "epoch": 0.056107539450613676,
+      "grad_norm": 5.165210682799403,
+      "learning_rate": 4.879227053140097e-06,
+      "loss": 0.9407,
+      "step": 24
+    },
+    {
+      "epoch": 0.058445353594389245,
+      "grad_norm": 5.126974516324422,
+      "learning_rate": 4.867149758454107e-06,
+      "loss": 0.949,
+      "step": 25
+    },
+    {
+      "epoch": 0.06078316773816481,
+      "grad_norm": 5.363449994215859,
+      "learning_rate": 4.855072463768117e-06,
+      "loss": 0.9574,
+      "step": 26
+    },
+    {
+      "epoch": 0.06312098188194039,
+      "grad_norm": 5.071572733466881,
+      "learning_rate": 4.8429951690821256e-06,
+      "loss": 0.9008,
+      "step": 27
+    },
+    {
+      "epoch": 0.06545879602571596,
+      "grad_norm": 5.410969697138812,
+      "learning_rate": 4.830917874396135e-06,
+      "loss": 0.9422,
+      "step": 28
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 4.602908185422313,
+      "learning_rate": 4.818840579710145e-06,
+      "loss": 0.8725,
+      "step": 29
+    },
+    {
+      "epoch": 0.0701344243132671,
+      "grad_norm": 4.8619656541333836,
+      "learning_rate": 4.806763285024155e-06,
+      "loss": 0.9414,
+      "step": 30
+    },
+    {
+      "epoch": 0.07247223845704266,
+      "grad_norm": 5.730566605120532,
+      "learning_rate": 4.794685990338165e-06,
+      "loss": 0.9039,
+      "step": 31
+    },
+    {
+      "epoch": 0.07481005260081823,
+      "grad_norm": 5.038586687201418,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.9208,
+      "step": 32
+    },
+    {
+      "epoch": 0.0771478667445938,
+      "grad_norm": 5.0552868730926335,
+      "learning_rate": 4.770531400966184e-06,
+      "loss": 0.8567,
+      "step": 33
+    },
+    {
+      "epoch": 0.07948568088836938,
+      "grad_norm": 4.718130108871858,
+      "learning_rate": 4.758454106280194e-06,
+      "loss": 0.9145,
+      "step": 34
+    },
+    {
+      "epoch": 0.08182349503214495,
+      "grad_norm": 5.492137838168964,
+      "learning_rate": 4.746376811594204e-06,
+      "loss": 0.8846,
+      "step": 35
+    },
+    {
+      "epoch": 0.08416130917592052,
+      "grad_norm": 4.796280317690393,
+      "learning_rate": 4.7342995169082125e-06,
+      "loss": 0.8973,
+      "step": 36
+    },
+    {
+      "epoch": 0.08649912331969609,
+      "grad_norm": 5.097877561946411,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.9225,
+      "step": 37
+    },
+    {
+      "epoch": 0.08883693746347165,
+      "grad_norm": 5.149693059570453,
+      "learning_rate": 4.710144927536232e-06,
+      "loss": 0.9087,
+      "step": 38
+    },
+    {
+      "epoch": 0.09117475160724722,
+      "grad_norm": 4.769756789814799,
+      "learning_rate": 4.698067632850242e-06,
+      "loss": 0.8372,
+      "step": 39
+    },
+    {
+      "epoch": 0.09351256575102279,
+      "grad_norm": 4.303036243240873,
+      "learning_rate": 4.6859903381642516e-06,
+      "loss": 0.899,
+      "step": 40
+    },
+    {
+      "epoch": 0.09585037989479836,
+      "grad_norm": 5.053977102743315,
+      "learning_rate": 4.673913043478261e-06,
+      "loss": 0.8242,
+      "step": 41
+    },
+    {
+      "epoch": 0.09818819403857393,
+      "grad_norm": 4.448509206619331,
+      "learning_rate": 4.661835748792271e-06,
+      "loss": 0.8513,
+      "step": 42
+    },
+    {
+      "epoch": 0.1005260081823495,
+      "grad_norm": 4.8321447335981595,
+      "learning_rate": 4.649758454106281e-06,
+      "loss": 0.8224,
+      "step": 43
+    },
+    {
+      "epoch": 0.10286382232612508,
+      "grad_norm": 5.416510574830531,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 0.9078,
+      "step": 44
+    },
+    {
+      "epoch": 0.10520163646990065,
+      "grad_norm": 5.548877279459332,
+      "learning_rate": 4.6256038647342995e-06,
+      "loss": 0.9292,
+      "step": 45
+    },
+    {
+      "epoch": 0.10753945061367622,
+      "grad_norm": 5.023304416916682,
+      "learning_rate": 4.613526570048309e-06,
+      "loss": 0.8678,
+      "step": 46
+    },
+    {
+      "epoch": 0.10987726475745178,
+      "grad_norm": 5.3492127097713995,
+      "learning_rate": 4.601449275362319e-06,
+      "loss": 0.8999,
+      "step": 47
+    },
+    {
+      "epoch": 0.11221507890122735,
+      "grad_norm": 4.59060914495858,
+      "learning_rate": 4.589371980676329e-06,
+      "loss": 0.8611,
+      "step": 48
+    },
+    {
+      "epoch": 0.11455289304500292,
+      "grad_norm": 4.659978410728117,
+      "learning_rate": 4.5772946859903385e-06,
+      "loss": 0.8553,
+      "step": 49
+    },
+    {
+      "epoch": 0.11689070718877849,
+      "grad_norm": 4.869606947497931,
+      "learning_rate": 4.565217391304348e-06,
+      "loss": 0.8353,
+      "step": 50
+    },
+    {
+      "epoch": 0.11922852133255406,
+      "grad_norm": 4.595092369703616,
+      "learning_rate": 4.553140096618358e-06,
+      "loss": 0.8852,
+      "step": 51
+    },
+    {
+      "epoch": 0.12156633547632963,
+      "grad_norm": 4.846379704504629,
+      "learning_rate": 4.541062801932368e-06,
+      "loss": 0.8516,
+      "step": 52
+    },
+    {
+      "epoch": 0.12390414962010521,
+      "grad_norm": 4.762019560202168,
+      "learning_rate": 4.5289855072463775e-06,
+      "loss": 0.8621,
+      "step": 53
+    },
+    {
+      "epoch": 0.12624196376388078,
+      "grad_norm": 4.823419642191392,
+      "learning_rate": 4.516908212560387e-06,
+      "loss": 0.849,
+      "step": 54
+    },
+    {
+      "epoch": 0.12857977790765635,
+      "grad_norm": 4.678982332878243,
+      "learning_rate": 4.504830917874396e-06,
+      "loss": 0.8595,
+      "step": 55
+    },
+    {
+      "epoch": 0.1309175920514319,
+      "grad_norm": 4.695208099270892,
+      "learning_rate": 4.492753623188406e-06,
+      "loss": 0.918,
+      "step": 56
+    },
+    {
+      "epoch": 0.13325540619520748,
+      "grad_norm": 4.692012801651267,
+      "learning_rate": 4.480676328502416e-06,
+      "loss": 0.8879,
+      "step": 57
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 4.459981999724462,
+      "learning_rate": 4.4685990338164255e-06,
+      "loss": 0.8878,
+      "step": 58
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 4.2801494436823,
+      "learning_rate": 4.456521739130435e-06,
+      "loss": 0.8695,
+      "step": 59
+    },
+    {
+      "epoch": 0.1402688486265342,
+      "grad_norm": 4.86123317504702,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.839,
+      "step": 60
+    },
+    {
+      "epoch": 0.14260666277030976,
+      "grad_norm": 4.621713656381368,
+      "learning_rate": 4.432367149758455e-06,
+      "loss": 0.8264,
+      "step": 61
+    },
+    {
+      "epoch": 0.14494447691408532,
+      "grad_norm": 4.437318825045428,
+      "learning_rate": 4.4202898550724645e-06,
+      "loss": 0.8575,
+      "step": 62
+    },
+    {
+      "epoch": 0.1472822910578609,
+      "grad_norm": 4.191896550350781,
+      "learning_rate": 4.408212560386474e-06,
+      "loss": 0.8231,
+      "step": 63
+    },
+    {
+      "epoch": 0.14962010520163646,
+      "grad_norm": 4.934485372283743,
+      "learning_rate": 4.396135265700483e-06,
+      "loss": 0.908,
+      "step": 64
+    },
+    {
+      "epoch": 0.15195791934541203,
+      "grad_norm": 5.164473939972992,
+      "learning_rate": 4.384057971014493e-06,
+      "loss": 0.8157,
+      "step": 65
+    },
+    {
+      "epoch": 0.1542957334891876,
+      "grad_norm": 4.6359554134854655,
+      "learning_rate": 4.371980676328503e-06,
+      "loss": 0.8553,
+      "step": 66
+    },
+    {
+      "epoch": 0.15663354763296317,
+      "grad_norm": 4.586287061115779,
+      "learning_rate": 4.3599033816425124e-06,
+      "loss": 0.8434,
+      "step": 67
+    },
+    {
+      "epoch": 0.15897136177673876,
+      "grad_norm": 4.8424129486531,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.8788,
+      "step": 68
+    },
+    {
+      "epoch": 0.16130917592051433,
+      "grad_norm": 6.155570830239365,
+      "learning_rate": 4.335748792270532e-06,
+      "loss": 0.9687,
+      "step": 69
+    },
+    {
+      "epoch": 0.1636469900642899,
+      "grad_norm": 4.812494847678857,
+      "learning_rate": 4.323671497584541e-06,
+      "loss": 0.9001,
+      "step": 70
+    },
+    {
+      "epoch": 0.16598480420806547,
+      "grad_norm": 4.5207315366098255,
+      "learning_rate": 4.3115942028985515e-06,
+      "loss": 0.8164,
+      "step": 71
+    },
+    {
+      "epoch": 0.16832261835184104,
+      "grad_norm": 4.468118689699742,
+      "learning_rate": 4.299516908212561e-06,
+      "loss": 0.828,
+      "step": 72
+    },
+    {
+      "epoch": 0.1706604324956166,
+      "grad_norm": 4.957803820804726,
+      "learning_rate": 4.28743961352657e-06,
+      "loss": 0.8509,
+      "step": 73
+    },
+    {
+      "epoch": 0.17299824663939217,
+      "grad_norm": 4.994668979616406,
+      "learning_rate": 4.27536231884058e-06,
+      "loss": 0.8264,
+      "step": 74
+    },
+    {
+      "epoch": 0.17533606078316774,
+      "grad_norm": 5.051317651149785,
+      "learning_rate": 4.26328502415459e-06,
+      "loss": 0.8575,
+      "step": 75
+    },
+    {
+      "epoch": 0.1776738749269433,
+      "grad_norm": 4.982871471593161,
+      "learning_rate": 4.251207729468599e-06,
+      "loss": 0.7766,
+      "step": 76
+    },
+    {
+      "epoch": 0.18001168907071888,
+      "grad_norm": 4.812654963388801,
+      "learning_rate": 4.239130434782609e-06,
+      "loss": 0.842,
+      "step": 77
+    },
+    {
+      "epoch": 0.18234950321449445,
+      "grad_norm": 4.849638872368005,
+      "learning_rate": 4.227053140096619e-06,
+      "loss": 0.8493,
+      "step": 78
+    },
+    {
+      "epoch": 0.18468731735827001,
+      "grad_norm": 4.941754403496056,
+      "learning_rate": 4.214975845410628e-06,
+      "loss": 0.8705,
+      "step": 79
+    },
+    {
+      "epoch": 0.18702513150204558,
+      "grad_norm": 4.118521255369774,
+      "learning_rate": 4.202898550724638e-06,
+      "loss": 0.9022,
+      "step": 80
+    },
+    {
+      "epoch": 0.18936294564582115,
+      "grad_norm": 5.048580106033392,
+      "learning_rate": 4.190821256038647e-06,
+      "loss": 0.8431,
+      "step": 81
+    },
+    {
+      "epoch": 0.19170075978959672,
+      "grad_norm": 5.383766123063546,
+      "learning_rate": 4.178743961352658e-06,
+      "loss": 0.8892,
+      "step": 82
+    },
+    {
+      "epoch": 0.1940385739333723,
+      "grad_norm": 4.850111002487489,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9147,
+      "step": 83
+    },
+    {
+      "epoch": 0.19637638807714786,
+      "grad_norm": 4.703827358788699,
+      "learning_rate": 4.154589371980677e-06,
+      "loss": 0.8407,
+      "step": 84
+    },
+    {
+      "epoch": 0.19871420222092342,
+      "grad_norm": 4.5132494951253275,
+      "learning_rate": 4.142512077294686e-06,
+      "loss": 0.859,
+      "step": 85
+    },
+    {
+      "epoch": 0.201052016364699,
+      "grad_norm": 4.425801289741148,
+      "learning_rate": 4.130434782608696e-06,
+      "loss": 0.8643,
+      "step": 86
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 4.6519866473202285,
+      "learning_rate": 4.118357487922706e-06,
+      "loss": 0.8559,
+      "step": 87
+    },
+    {
+      "epoch": 0.20572764465225016,
+      "grad_norm": 4.271767242791549,
+      "learning_rate": 4.106280193236716e-06,
+      "loss": 0.8115,
+      "step": 88
+    },
+    {
+      "epoch": 0.20806545879602573,
+      "grad_norm": 5.056579518750136,
+      "learning_rate": 4.0942028985507246e-06,
+      "loss": 0.8447,
+      "step": 89
+    },
+    {
+      "epoch": 0.2104032729398013,
+      "grad_norm": 4.075100416572746,
+      "learning_rate": 4.082125603864734e-06,
+      "loss": 0.7837,
+      "step": 90
+    },
+    {
+      "epoch": 0.21274108708357686,
+      "grad_norm": 4.393779666632264,
+      "learning_rate": 4.070048309178744e-06,
+      "loss": 0.8368,
+      "step": 91
+    },
+    {
+      "epoch": 0.21507890122735243,
+      "grad_norm": 4.322824034406939,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 0.7942,
+      "step": 92
+    },
+    {
+      "epoch": 0.217416715371128,
+      "grad_norm": 4.691982719838354,
+      "learning_rate": 4.045893719806764e-06,
+      "loss": 0.8384,
+      "step": 93
+    },
+    {
+      "epoch": 0.21975452951490357,
+      "grad_norm": 4.749714290659545,
+      "learning_rate": 4.033816425120773e-06,
+      "loss": 0.86,
+      "step": 94
+    },
+    {
+      "epoch": 0.22209234365867914,
+      "grad_norm": 4.49073749526097,
+      "learning_rate": 4.021739130434783e-06,
+      "loss": 0.8796,
+      "step": 95
+    },
+    {
+      "epoch": 0.2244301578024547,
+      "grad_norm": 4.612026680332374,
+      "learning_rate": 4.009661835748793e-06,
+      "loss": 0.7836,
+      "step": 96
+    },
+    {
+      "epoch": 0.22676797194623027,
+      "grad_norm": 4.5466671401291165,
+      "learning_rate": 3.997584541062803e-06,
+      "loss": 0.8213,
+      "step": 97
+    },
+    {
+      "epoch": 0.22910578609000584,
+      "grad_norm": 4.578959418279228,
+      "learning_rate": 3.9855072463768115e-06,
+      "loss": 0.8302,
+      "step": 98
+    },
+    {
+      "epoch": 0.2314436002337814,
+      "grad_norm": 4.471310182272502,
+      "learning_rate": 3.973429951690821e-06,
+      "loss": 0.8386,
+      "step": 99
+    },
+    {
+      "epoch": 0.23378141437755698,
+      "grad_norm": 4.444066950873127,
+      "learning_rate": 3.961352657004831e-06,
+      "loss": 0.8672,
+      "step": 100
+    },
+    {
+      "epoch": 0.23611922852133255,
+      "grad_norm": 4.08994098536812,
+      "learning_rate": 3.949275362318841e-06,
+      "loss": 0.7914,
+      "step": 101
+    },
+    {
+      "epoch": 0.23845704266510812,
+      "grad_norm": 5.867972858556011,
+      "learning_rate": 3.9371980676328506e-06,
+      "loss": 0.834,
+      "step": 102
+    },
+    {
+      "epoch": 0.24079485680888368,
+      "grad_norm": 4.33178424044995,
+      "learning_rate": 3.92512077294686e-06,
+      "loss": 0.8312,
+      "step": 103
+    },
+    {
+      "epoch": 0.24313267095265925,
+      "grad_norm": 4.422360019571021,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 0.8054,
+      "step": 104
+    },
+    {
+      "epoch": 0.24547048509643482,
+      "grad_norm": 4.540760031449362,
+      "learning_rate": 3.90096618357488e-06,
+      "loss": 0.8011,
+      "step": 105
+    },
+    {
+      "epoch": 0.24780829924021042,
+      "grad_norm": 4.577644817701169,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.7851,
+      "step": 106
+    },
+    {
+      "epoch": 0.25014611338398596,
+      "grad_norm": 4.750903595759052,
+      "learning_rate": 3.8768115942028985e-06,
+      "loss": 0.8496,
+      "step": 107
+    },
+    {
+      "epoch": 0.25248392752776155,
+      "grad_norm": 4.744977001781623,
+      "learning_rate": 3.864734299516908e-06,
+      "loss": 0.8218,
+      "step": 108
+    },
+    {
+      "epoch": 0.2548217416715371,
+      "grad_norm": 4.548950141262851,
+      "learning_rate": 3.852657004830918e-06,
+      "loss": 0.8053,
+      "step": 109
+    },
+    {
+      "epoch": 0.2571595558153127,
+      "grad_norm": 4.44828603075951,
+      "learning_rate": 3.840579710144928e-06,
+      "loss": 0.8231,
+      "step": 110
+    },
+    {
+      "epoch": 0.25949736995908823,
+      "grad_norm": 4.672161591073822,
+      "learning_rate": 3.8285024154589375e-06,
+      "loss": 0.8389,
+      "step": 111
+    },
+    {
+      "epoch": 0.2618351841028638,
+      "grad_norm": 4.526274586937092,
+      "learning_rate": 3.816425120772947e-06,
+      "loss": 0.8683,
+      "step": 112
+    },
+    {
+      "epoch": 0.26417299824663937,
+      "grad_norm": 4.603415978914653,
+      "learning_rate": 3.804347826086957e-06,
+      "loss": 0.8206,
+      "step": 113
+    },
+    {
+      "epoch": 0.26651081239041496,
+      "grad_norm": 4.343843088593362,
+      "learning_rate": 3.792270531400967e-06,
+      "loss": 0.823,
+      "step": 114
+    },
+    {
+      "epoch": 0.2688486265341905,
+      "grad_norm": 4.131180727748698,
+      "learning_rate": 3.780193236714976e-06,
+      "loss": 0.7964,
+      "step": 115
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 5.611563677944062,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 0.8529,
+      "step": 116
+    },
+    {
+      "epoch": 0.2735242548217417,
+      "grad_norm": 4.315382063517201,
+      "learning_rate": 3.7560386473429956e-06,
+      "loss": 0.7849,
+      "step": 117
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 4.3301657812789776,
+      "learning_rate": 3.743961352657005e-06,
+      "loss": 0.8392,
+      "step": 118
+    },
+    {
+      "epoch": 0.27819988310929283,
+      "grad_norm": 4.763659062354643,
+      "learning_rate": 3.7318840579710147e-06,
+      "loss": 0.7846,
+      "step": 119
+    },
+    {
+      "epoch": 0.2805376972530684,
+      "grad_norm": 4.531318611414816,
+      "learning_rate": 3.7198067632850245e-06,
+      "loss": 0.8335,
+      "step": 120
+    },
+    {
+      "epoch": 0.28287551139684397,
+      "grad_norm": 4.4418077648050485,
+      "learning_rate": 3.707729468599034e-06,
+      "loss": 0.7858,
+      "step": 121
+    },
+    {
+      "epoch": 0.2852133255406195,
+      "grad_norm": 4.39068842397474,
+      "learning_rate": 3.6956521739130436e-06,
+      "loss": 0.8408,
+      "step": 122
+    },
+    {
+      "epoch": 0.2875511396843951,
+      "grad_norm": 4.585137838540199,
+      "learning_rate": 3.6835748792270538e-06,
+      "loss": 0.8316,
+      "step": 123
+    },
+    {
+      "epoch": 0.28988895382817065,
+      "grad_norm": 4.319672080062613,
+      "learning_rate": 3.6714975845410635e-06,
+      "loss": 0.8241,
+      "step": 124
+    },
+    {
+      "epoch": 0.29222676797194624,
+      "grad_norm": 4.131090234388279,
+      "learning_rate": 3.659420289855073e-06,
+      "loss": 0.7416,
+      "step": 125
+    },
+    {
+      "epoch": 0.2945645821157218,
+      "grad_norm": 4.081456252490184,
+      "learning_rate": 3.6473429951690826e-06,
+      "loss": 0.7958,
+      "step": 126
+    },
+    {
+      "epoch": 0.2969023962594974,
+      "grad_norm": 4.090503599319394,
+      "learning_rate": 3.635265700483092e-06,
+      "loss": 0.8096,
+      "step": 127
+    },
+    {
+      "epoch": 0.2992402104032729,
+      "grad_norm": 4.129285724564573,
+      "learning_rate": 3.6231884057971017e-06,
+      "loss": 0.7918,
+      "step": 128
+    },
+    {
+      "epoch": 0.3015780245470485,
+      "grad_norm": 4.506022555765926,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.8333,
+      "step": 129
+    },
+    {
+      "epoch": 0.30391583869082406,
+      "grad_norm": 4.151575198600969,
+      "learning_rate": 3.5990338164251208e-06,
+      "loss": 0.7713,
+      "step": 130
+    },
+    {
+      "epoch": 0.30625365283459965,
+      "grad_norm": 4.614683656771631,
+      "learning_rate": 3.5869565217391305e-06,
+      "loss": 0.8298,
+      "step": 131
+    },
+    {
+      "epoch": 0.3085914669783752,
+      "grad_norm": 4.6094981031628075,
+      "learning_rate": 3.5748792270531403e-06,
+      "loss": 0.8217,
+      "step": 132
+    },
+    {
+      "epoch": 0.3109292811221508,
+      "grad_norm": 4.2999582776551675,
+      "learning_rate": 3.5628019323671496e-06,
+      "loss": 0.7968,
+      "step": 133
+    },
+    {
+      "epoch": 0.31326709526592633,
+      "grad_norm": 4.864198700798981,
+      "learning_rate": 3.55072463768116e-06,
+      "loss": 0.8141,
+      "step": 134
+    },
+    {
+      "epoch": 0.31560490940970193,
+      "grad_norm": 4.601546334463328,
+      "learning_rate": 3.5386473429951696e-06,
+      "loss": 0.7925,
+      "step": 135
+    },
+    {
+      "epoch": 0.3179427235534775,
+      "grad_norm": 4.089485101723296,
+      "learning_rate": 3.5265700483091793e-06,
+      "loss": 0.7873,
+      "step": 136
+    },
+    {
+      "epoch": 0.32028053769725306,
+      "grad_norm": 4.0777367885745806,
+      "learning_rate": 3.5144927536231887e-06,
+      "loss": 0.7985,
+      "step": 137
+    },
+    {
+      "epoch": 0.32261835184102866,
+      "grad_norm": 4.832689220436005,
+      "learning_rate": 3.5024154589371984e-06,
+      "loss": 0.8306,
+      "step": 138
+    },
+    {
+      "epoch": 0.3249561659848042,
+      "grad_norm": 4.888417681228503,
+      "learning_rate": 3.490338164251208e-06,
+      "loss": 0.8353,
+      "step": 139
+    },
+    {
+      "epoch": 0.3272939801285798,
+      "grad_norm": 4.28948650105686,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.8057,
+      "step": 140
+    },
+    {
+      "epoch": 0.32963179427235534,
+      "grad_norm": 4.203178774124529,
+      "learning_rate": 3.4661835748792273e-06,
+      "loss": 0.7788,
+      "step": 141
+    },
+    {
+      "epoch": 0.33196960841613093,
+      "grad_norm": 4.637106026831514,
+      "learning_rate": 3.4541062801932366e-06,
+      "loss": 0.8521,
+      "step": 142
+    },
+    {
+      "epoch": 0.3343074225599065,
+      "grad_norm": 4.350395114537057,
+      "learning_rate": 3.4420289855072464e-06,
+      "loss": 0.7968,
+      "step": 143
+    },
+    {
+      "epoch": 0.33664523670368207,
+      "grad_norm": 4.474607456827939,
+      "learning_rate": 3.4299516908212565e-06,
+      "loss": 0.8208,
+      "step": 144
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 4.100288353060924,
+      "learning_rate": 3.4178743961352663e-06,
+      "loss": 0.8165,
+      "step": 145
+    },
+    {
+      "epoch": 0.3413208649912332,
+      "grad_norm": 4.6247997756094845,
+      "learning_rate": 3.4057971014492756e-06,
+      "loss": 0.8294,
+      "step": 146
+    },
+    {
+      "epoch": 0.34365867913500875,
+      "grad_norm": 4.525169765596723,
+      "learning_rate": 3.3937198067632854e-06,
+      "loss": 0.7713,
+      "step": 147
+    },
+    {
+      "epoch": 0.34599649327878435,
+      "grad_norm": 4.442206881786442,
+      "learning_rate": 3.381642512077295e-06,
+      "loss": 0.82,
+      "step": 148
+    },
+    {
+      "epoch": 0.3483343074225599,
+      "grad_norm": 4.225556484795958,
+      "learning_rate": 3.3695652173913045e-06,
+      "loss": 0.7886,
+      "step": 149
+    },
+    {
+      "epoch": 0.3506721215663355,
+      "grad_norm": 4.268743583707888,
+      "learning_rate": 3.3574879227053142e-06,
+      "loss": 0.7762,
+      "step": 150
+    },
+    {
+      "epoch": 0.353009935710111,
+      "grad_norm": 4.338428118785664,
+      "learning_rate": 3.345410628019324e-06,
+      "loss": 0.7719,
+      "step": 151
+    },
+    {
+      "epoch": 0.3553477498538866,
+      "grad_norm": 4.188696391446484,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7745,
+      "step": 152
+    },
+    {
+      "epoch": 0.35768556399766216,
+      "grad_norm": 4.310914121193176,
+      "learning_rate": 3.321256038647343e-06,
+      "loss": 0.8188,
+      "step": 153
+    },
+    {
+      "epoch": 0.36002337814143776,
+      "grad_norm": 4.391656829031555,
+      "learning_rate": 3.3091787439613533e-06,
+      "loss": 0.8148,
+      "step": 154
+    },
+    {
+      "epoch": 0.36236119228521335,
+      "grad_norm": 4.104259018738402,
+      "learning_rate": 3.2971014492753626e-06,
+      "loss": 0.8519,
+      "step": 155
+    },
+    {
+      "epoch": 0.3646990064289889,
+      "grad_norm": 4.25629990334181,
+      "learning_rate": 3.2850241545893724e-06,
+      "loss": 0.7983,
+      "step": 156
+    },
+    {
+      "epoch": 0.3670368205727645,
+      "grad_norm": 4.134990269789036,
+      "learning_rate": 3.272946859903382e-06,
+      "loss": 0.7852,
+      "step": 157
+    },
+    {
+      "epoch": 0.36937463471654003,
+      "grad_norm": 4.0420970622040135,
+      "learning_rate": 3.2608695652173914e-06,
+      "loss": 0.7992,
+      "step": 158
+    },
+    {
+      "epoch": 0.3717124488603156,
+      "grad_norm": 4.341222672754024,
+      "learning_rate": 3.248792270531401e-06,
+      "loss": 0.7704,
+      "step": 159
+    },
+    {
+      "epoch": 0.37405026300409117,
+      "grad_norm": 4.115523347634753,
+      "learning_rate": 3.236714975845411e-06,
+      "loss": 0.791,
+      "step": 160
+    },
+    {
+      "epoch": 0.37638807714786676,
+      "grad_norm": 4.136587110231359,
+      "learning_rate": 3.2246376811594203e-06,
+      "loss": 0.7752,
+      "step": 161
+    },
+    {
+      "epoch": 0.3787258912916423,
+      "grad_norm": 4.504460772929252,
+      "learning_rate": 3.21256038647343e-06,
+      "loss": 0.8176,
+      "step": 162
+    },
+    {
+      "epoch": 0.3810637054354179,
+      "grad_norm": 4.629377407126395,
+      "learning_rate": 3.20048309178744e-06,
+      "loss": 0.8275,
+      "step": 163
+    },
+    {
+      "epoch": 0.38340151957919344,
+      "grad_norm": 4.422477761962599,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 0.7847,
+      "step": 164
+    },
+    {
+      "epoch": 0.38573933372296904,
+      "grad_norm": 3.9888038106102153,
+      "learning_rate": 3.1763285024154593e-06,
+      "loss": 0.7939,
+      "step": 165
+    },
+    {
+      "epoch": 0.3880771478667446,
+      "grad_norm": 4.125918892903183,
+      "learning_rate": 3.164251207729469e-06,
+      "loss": 0.7717,
+      "step": 166
+    },
+    {
+      "epoch": 0.3904149620105202,
+      "grad_norm": 6.885413034719951,
+      "learning_rate": 3.152173913043479e-06,
+      "loss": 0.8514,
+      "step": 167
+    },
+    {
+      "epoch": 0.3927527761542957,
+      "grad_norm": 4.446340003037039,
+      "learning_rate": 3.140096618357488e-06,
+      "loss": 0.813,
+      "step": 168
+    },
+    {
+      "epoch": 0.3950905902980713,
+      "grad_norm": 3.9959566422822346,
+      "learning_rate": 3.128019323671498e-06,
+      "loss": 0.7776,
+      "step": 169
+    },
+    {
+      "epoch": 0.39742840444184685,
+      "grad_norm": 4.627421389612255,
+      "learning_rate": 3.1159420289855073e-06,
+      "loss": 0.8395,
+      "step": 170
+    },
+    {
+      "epoch": 0.39976621858562245,
+      "grad_norm": 4.118715295949323,
+      "learning_rate": 3.103864734299517e-06,
+      "loss": 0.7824,
+      "step": 171
+    },
+    {
+      "epoch": 0.402104032729398,
+      "grad_norm": 4.109354113391549,
+      "learning_rate": 3.0917874396135268e-06,
+      "loss": 0.7961,
+      "step": 172
+    },
+    {
+      "epoch": 0.4044418468731736,
+      "grad_norm": 4.439845150489727,
+      "learning_rate": 3.079710144927536e-06,
+      "loss": 0.8035,
+      "step": 173
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 4.358250626799815,
+      "learning_rate": 3.067632850241546e-06,
+      "loss": 0.7829,
+      "step": 174
+    },
+    {
+      "epoch": 0.4091174751607247,
+      "grad_norm": 4.43053050152037,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.7554,
+      "step": 175
+    },
+    {
+      "epoch": 0.4114552893045003,
+      "grad_norm": 4.324105830729812,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 0.7763,
+      "step": 176
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 4.505708676229393,
+      "learning_rate": 3.031400966183575e-06,
+      "loss": 0.8052,
+      "step": 177
+    },
+    {
+      "epoch": 0.41613091759205145,
+      "grad_norm": 4.198009455233572,
+      "learning_rate": 3.019323671497585e-06,
+      "loss": 0.8036,
+      "step": 178
+    },
+    {
+      "epoch": 0.418468731735827,
+      "grad_norm": 4.255888057785401,
+      "learning_rate": 3.0072463768115946e-06,
+      "loss": 0.8675,
+      "step": 179
+    },
+    {
+      "epoch": 0.4208065458796026,
+      "grad_norm": 4.166498155365259,
+      "learning_rate": 2.995169082125604e-06,
+      "loss": 0.8099,
+      "step": 180
+    },
+    {
+      "epoch": 0.42314436002337813,
+      "grad_norm": 4.471408293419965,
+      "learning_rate": 2.9830917874396137e-06,
+      "loss": 0.8025,
+      "step": 181
+    },
+    {
+      "epoch": 0.4254821741671537,
+      "grad_norm": 4.910816764257679,
+      "learning_rate": 2.9710144927536235e-06,
+      "loss": 0.7702,
+      "step": 182
+    },
+    {
+      "epoch": 0.42781998831092927,
+      "grad_norm": 4.071039233797094,
+      "learning_rate": 2.958937198067633e-06,
+      "loss": 0.8143,
+      "step": 183
+    },
+    {
+      "epoch": 0.43015780245470486,
+      "grad_norm": 4.738565032335615,
+      "learning_rate": 2.9468599033816426e-06,
+      "loss": 0.8158,
+      "step": 184
+    },
+    {
+      "epoch": 0.4324956165984804,
+      "grad_norm": 4.2936029356268195,
+      "learning_rate": 2.9347826086956528e-06,
+      "loss": 0.7874,
+      "step": 185
+    },
+    {
+      "epoch": 0.434833430742256,
+      "grad_norm": 4.206590096270031,
+      "learning_rate": 2.922705314009662e-06,
+      "loss": 0.7997,
+      "step": 186
+    },
+    {
+      "epoch": 0.43717124488603154,
+      "grad_norm": 4.2051171328892085,
+      "learning_rate": 2.910628019323672e-06,
+      "loss": 0.787,
+      "step": 187
+    },
+    {
+      "epoch": 0.43950905902980714,
+      "grad_norm": 4.245918333471198,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 0.7997,
+      "step": 188
+    },
+    {
+      "epoch": 0.4418468731735827,
+      "grad_norm": 4.179370789694772,
+      "learning_rate": 2.886473429951691e-06,
+      "loss": 0.7759,
+      "step": 189
+    },
+    {
+      "epoch": 0.4441846873173583,
+      "grad_norm": 4.41515451612343,
+      "learning_rate": 2.8743961352657007e-06,
+      "loss": 0.7886,
+      "step": 190
+    },
+    {
+      "epoch": 0.4465225014611338,
+      "grad_norm": 4.227222440463386,
+      "learning_rate": 2.8623188405797105e-06,
+      "loss": 0.8294,
+      "step": 191
+    },
+    {
+      "epoch": 0.4488603156049094,
+      "grad_norm": 4.095256731977333,
+      "learning_rate": 2.85024154589372e-06,
+      "loss": 0.7604,
+      "step": 192
+    },
+    {
+      "epoch": 0.451198129748685,
+      "grad_norm": 4.286339845869899,
+      "learning_rate": 2.8381642512077295e-06,
+      "loss": 0.8237,
+      "step": 193
+    },
+    {
+      "epoch": 0.45353594389246055,
+      "grad_norm": 4.141328341649525,
+      "learning_rate": 2.8260869565217393e-06,
+      "loss": 0.7961,
+      "step": 194
+    },
+    {
+      "epoch": 0.45587375803623614,
+      "grad_norm": 4.522982085235291,
+      "learning_rate": 2.8140096618357486e-06,
+      "loss": 0.7918,
+      "step": 195
+    },
+    {
+      "epoch": 0.4582115721800117,
+      "grad_norm": 4.9933547683547745,
+      "learning_rate": 2.801932367149759e-06,
+      "loss": 0.8151,
+      "step": 196
+    },
+    {
+      "epoch": 0.4605493863237873,
+      "grad_norm": 3.8642864404581463,
+      "learning_rate": 2.7898550724637686e-06,
+      "loss": 0.7411,
+      "step": 197
+    },
+    {
+      "epoch": 0.4628872004675628,
+      "grad_norm": 4.304180579272247,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.7975,
+      "step": 198
+    },
+    {
+      "epoch": 0.4652250146113384,
+      "grad_norm": 4.246581554029021,
+      "learning_rate": 2.7657004830917877e-06,
+      "loss": 0.829,
+      "step": 199
+    },
+    {
+      "epoch": 0.46756282875511396,
+      "grad_norm": 4.257923593734172,
+      "learning_rate": 2.7536231884057974e-06,
+      "loss": 0.7475,
+      "step": 200
+    },
+    {
+      "epoch": 0.46990064289888955,
+      "grad_norm": 4.001585884428085,
+      "learning_rate": 2.7415458937198068e-06,
+      "loss": 0.7866,
+      "step": 201
+    },
+    {
+      "epoch": 0.4722384570426651,
+      "grad_norm": 4.064057741085377,
+      "learning_rate": 2.7294685990338165e-06,
+      "loss": 0.7861,
+      "step": 202
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 4.10748108128691,
+      "learning_rate": 2.7173913043478263e-06,
+      "loss": 0.7735,
+      "step": 203
+    },
+    {
+      "epoch": 0.47691408533021623,
+      "grad_norm": 3.9433247912828455,
+      "learning_rate": 2.7053140096618356e-06,
+      "loss": 0.7494,
+      "step": 204
+    },
+    {
+      "epoch": 0.4792518994739918,
+      "grad_norm": 4.368990885761068,
+      "learning_rate": 2.6932367149758454e-06,
+      "loss": 0.7961,
+      "step": 205
+    },
+    {
+      "epoch": 0.48158971361776737,
+      "grad_norm": 4.323297445539955,
+      "learning_rate": 2.6811594202898555e-06,
+      "loss": 0.7498,
+      "step": 206
+    },
+    {
+      "epoch": 0.48392752776154296,
+      "grad_norm": 4.276797241413841,
+      "learning_rate": 2.6690821256038653e-06,
+      "loss": 0.79,
+      "step": 207
+    },
+    {
+      "epoch": 0.4862653419053185,
+      "grad_norm": 4.29615738858519,
+      "learning_rate": 2.6570048309178746e-06,
+      "loss": 0.7762,
+      "step": 208
+    },
+    {
+      "epoch": 0.4886031560490941,
+      "grad_norm": 4.24658335062537,
+      "learning_rate": 2.6449275362318844e-06,
+      "loss": 0.7547,
+      "step": 209
+    },
+    {
+      "epoch": 0.49094097019286964,
+      "grad_norm": 4.140652638469078,
+      "learning_rate": 2.632850241545894e-06,
+      "loss": 0.7568,
+      "step": 210
+    },
+    {
+      "epoch": 0.49327878433664524,
+      "grad_norm": 4.355835930781116,
+      "learning_rate": 2.6207729468599035e-06,
+      "loss": 0.8005,
+      "step": 211
+    },
+    {
+      "epoch": 0.49561659848042083,
+      "grad_norm": 4.1002906789316045,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.7791,
+      "step": 212
+    },
+    {
+      "epoch": 0.4979544126241964,
+      "grad_norm": 4.210038749172179,
+      "learning_rate": 2.596618357487923e-06,
+      "loss": 0.7777,
+      "step": 213
+    },
+    {
+      "epoch": 0.5002922267679719,
+      "grad_norm": 4.1435757469488985,
+      "learning_rate": 2.5845410628019323e-06,
+      "loss": 0.7824,
+      "step": 214
+    },
+    {
+      "epoch": 0.5026300409117476,
+      "grad_norm": 4.309944612009968,
+      "learning_rate": 2.572463768115942e-06,
+      "loss": 0.7625,
+      "step": 215
+    },
+    {
+      "epoch": 0.5049678550555231,
+      "grad_norm": 4.662526042139382,
+      "learning_rate": 2.5603864734299523e-06,
+      "loss": 0.7873,
+      "step": 216
+    },
+    {
+      "epoch": 0.5073056691992986,
+      "grad_norm": 4.473614799031895,
+      "learning_rate": 2.5483091787439616e-06,
+      "loss": 0.7737,
+      "step": 217
+    },
+    {
+      "epoch": 0.5096434833430742,
+      "grad_norm": 4.54082051832202,
+      "learning_rate": 2.5362318840579714e-06,
+      "loss": 0.782,
+      "step": 218
+    },
+    {
+      "epoch": 0.5119812974868498,
+      "grad_norm": 3.9808775866846817,
+      "learning_rate": 2.524154589371981e-06,
+      "loss": 0.7592,
+      "step": 219
+    },
+    {
+      "epoch": 0.5143191116306254,
+      "grad_norm": 4.233088111283031,
+      "learning_rate": 2.5120772946859904e-06,
+      "loss": 0.774,
+      "step": 220
+    },
+    {
+      "epoch": 0.5166569257744009,
+      "grad_norm": 4.179314655537464,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7936,
+      "step": 221
+    },
+    {
+      "epoch": 0.5189947399181765,
+      "grad_norm": 4.808766886416466,
+      "learning_rate": 2.48792270531401e-06,
+      "loss": 0.7961,
+      "step": 222
+    },
+    {
+      "epoch": 0.5213325540619521,
+      "grad_norm": 4.088801764052967,
+      "learning_rate": 2.4758454106280193e-06,
+      "loss": 0.7693,
+      "step": 223
+    },
+    {
+      "epoch": 0.5236703682057277,
+      "grad_norm": 4.1844548782576005,
+      "learning_rate": 2.4637681159420295e-06,
+      "loss": 0.7961,
+      "step": 224
+    },
+    {
+      "epoch": 0.5260081823495032,
+      "grad_norm": 3.909844659514703,
+      "learning_rate": 2.451690821256039e-06,
+      "loss": 0.7304,
+      "step": 225
+    },
+    {
+      "epoch": 0.5283459964932787,
+      "grad_norm": 3.7096435860994346,
+      "learning_rate": 2.4396135265700486e-06,
+      "loss": 0.7712,
+      "step": 226
+    },
+    {
+      "epoch": 0.5306838106370544,
+      "grad_norm": 4.0389484559123305,
+      "learning_rate": 2.4275362318840583e-06,
+      "loss": 0.7711,
+      "step": 227
+    },
+    {
+      "epoch": 0.5330216247808299,
+      "grad_norm": 4.171802534409844,
+      "learning_rate": 2.4154589371980677e-06,
+      "loss": 0.7768,
+      "step": 228
+    },
+    {
+      "epoch": 0.5353594389246055,
+      "grad_norm": 4.636520882862149,
+      "learning_rate": 2.4033816425120774e-06,
+      "loss": 0.7832,
+      "step": 229
+    },
+    {
+      "epoch": 0.537697253068381,
+      "grad_norm": 4.2073440647978675,
+      "learning_rate": 2.391304347826087e-06,
+      "loss": 0.7816,
+      "step": 230
+    },
+    {
+      "epoch": 0.5400350672121567,
+      "grad_norm": 4.115009346971059,
+      "learning_rate": 2.379227053140097e-06,
+      "loss": 0.7152,
+      "step": 231
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 4.47134068227285,
+      "learning_rate": 2.3671497584541063e-06,
+      "loss": 0.7898,
+      "step": 232
+    },
+    {
+      "epoch": 0.5447106954997077,
+      "grad_norm": 4.78251740854767,
+      "learning_rate": 2.355072463768116e-06,
+      "loss": 0.8101,
+      "step": 233
+    },
+    {
+      "epoch": 0.5470485096434834,
+      "grad_norm": 4.735288223469208,
+      "learning_rate": 2.3429951690821258e-06,
+      "loss": 0.7864,
+      "step": 234
+    },
+    {
+      "epoch": 0.5493863237872589,
+      "grad_norm": 4.445520808429391,
+      "learning_rate": 2.3309178743961355e-06,
+      "loss": 0.7986,
+      "step": 235
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 4.83504723163877,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 0.8231,
+      "step": 236
+    },
+    {
+      "epoch": 0.55406195207481,
+      "grad_norm": 3.9498177063802897,
+      "learning_rate": 2.3067632850241546e-06,
+      "loss": 0.7834,
+      "step": 237
+    },
+    {
+      "epoch": 0.5563997662185857,
+      "grad_norm": 4.190234074575243,
+      "learning_rate": 2.2946859903381644e-06,
+      "loss": 0.7839,
+      "step": 238
+    },
+    {
+      "epoch": 0.5587375803623612,
+      "grad_norm": 4.76462271734834,
+      "learning_rate": 2.282608695652174e-06,
+      "loss": 0.8258,
+      "step": 239
+    },
+    {
+      "epoch": 0.5610753945061367,
+      "grad_norm": 4.369965626736373,
+      "learning_rate": 2.270531400966184e-06,
+      "loss": 0.7927,
+      "step": 240
+    },
+    {
+      "epoch": 0.5634132086499123,
+      "grad_norm": 4.423067504974851,
+      "learning_rate": 2.2584541062801937e-06,
+      "loss": 0.8181,
+      "step": 241
+    },
+    {
+      "epoch": 0.5657510227936879,
+      "grad_norm": 4.117514088831818,
+      "learning_rate": 2.246376811594203e-06,
+      "loss": 0.7471,
+      "step": 242
+    },
+    {
+      "epoch": 0.5680888369374635,
+      "grad_norm": 4.208191494707427,
+      "learning_rate": 2.2342995169082127e-06,
+      "loss": 0.7936,
+      "step": 243
+    },
+    {
+      "epoch": 0.570426651081239,
+      "grad_norm": 4.30348767627021,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.8087,
+      "step": 244
+    },
+    {
+      "epoch": 0.5727644652250146,
+      "grad_norm": 4.08781387103947,
+      "learning_rate": 2.2101449275362323e-06,
+      "loss": 0.7712,
+      "step": 245
+    },
+    {
+      "epoch": 0.5751022793687902,
+      "grad_norm": 4.255214633571236,
+      "learning_rate": 2.1980676328502416e-06,
+      "loss": 0.7327,
+      "step": 246
+    },
+    {
+      "epoch": 0.5774400935125658,
+      "grad_norm": 4.249395888532918,
+      "learning_rate": 2.1859903381642513e-06,
+      "loss": 0.8115,
+      "step": 247
+    },
+    {
+      "epoch": 0.5797779076563413,
+      "grad_norm": 4.048350886158577,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 0.7629,
+      "step": 248
+    },
+    {
+      "epoch": 0.5821157218001168,
+      "grad_norm": 4.286991029118236,
+      "learning_rate": 2.1618357487922704e-06,
+      "loss": 0.7748,
+      "step": 249
+    },
+    {
+      "epoch": 0.5844535359438925,
+      "grad_norm": 4.473519294462659,
+      "learning_rate": 2.1497584541062806e-06,
+      "loss": 0.7786,
+      "step": 250
+    },
+    {
+      "epoch": 0.586791350087668,
+      "grad_norm": 4.511510327301669,
+      "learning_rate": 2.13768115942029e-06,
+      "loss": 0.8125,
+      "step": 251
+    },
+    {
+      "epoch": 0.5891291642314436,
+      "grad_norm": 4.198745204040387,
+      "learning_rate": 2.1256038647342997e-06,
+      "loss": 0.7843,
+      "step": 252
+    },
+    {
+      "epoch": 0.5914669783752192,
+      "grad_norm": 4.3568648354588655,
+      "learning_rate": 2.1135265700483095e-06,
+      "loss": 0.7346,
+      "step": 253
+    },
+    {
+      "epoch": 0.5938047925189948,
+      "grad_norm": 3.8942460823301412,
+      "learning_rate": 2.101449275362319e-06,
+      "loss": 0.7879,
+      "step": 254
+    },
+    {
+      "epoch": 0.5961426066627703,
+      "grad_norm": 4.221148903821956,
+      "learning_rate": 2.089371980676329e-06,
+      "loss": 0.799,
+      "step": 255
+    },
+    {
+      "epoch": 0.5984804208065458,
+      "grad_norm": 4.041691704636457,
+      "learning_rate": 2.0772946859903383e-06,
+      "loss": 0.767,
+      "step": 256
+    },
+    {
+      "epoch": 0.6008182349503215,
+      "grad_norm": 4.03197715174544,
+      "learning_rate": 2.065217391304348e-06,
+      "loss": 0.7487,
+      "step": 257
+    },
+    {
+      "epoch": 0.603156049094097,
+      "grad_norm": 4.082902353599498,
+      "learning_rate": 2.053140096618358e-06,
+      "loss": 0.7874,
+      "step": 258
+    },
+    {
+      "epoch": 0.6054938632378726,
+      "grad_norm": 3.7781639431570557,
+      "learning_rate": 2.041062801932367e-06,
+      "loss": 0.7721,
+      "step": 259
+    },
+    {
+      "epoch": 0.6078316773816481,
+      "grad_norm": 4.280421267303715,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 0.783,
+      "step": 260
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 4.073869260462684,
+      "learning_rate": 2.0169082125603867e-06,
+      "loss": 0.7759,
+      "step": 261
+    },
+    {
+      "epoch": 0.6125073056691993,
+      "grad_norm": 3.935130784068012,
+      "learning_rate": 2.0048309178743964e-06,
+      "loss": 0.7669,
+      "step": 262
+    },
+    {
+      "epoch": 0.6148451198129748,
+      "grad_norm": 4.40643829592683,
+      "learning_rate": 1.9927536231884058e-06,
+      "loss": 0.7572,
+      "step": 263
+    },
+    {
+      "epoch": 0.6171829339567504,
+      "grad_norm": 4.337844456783807,
+      "learning_rate": 1.9806763285024155e-06,
+      "loss": 0.7605,
+      "step": 264
+    },
+    {
+      "epoch": 0.619520748100526,
+      "grad_norm": 4.281102087431204,
+      "learning_rate": 1.9685990338164253e-06,
+      "loss": 0.7393,
+      "step": 265
+    },
+    {
+      "epoch": 0.6218585622443016,
+      "grad_norm": 4.23207914041172,
+      "learning_rate": 1.956521739130435e-06,
+      "loss": 0.7794,
+      "step": 266
+    },
+    {
+      "epoch": 0.6241963763880771,
+      "grad_norm": 3.9282868393703896,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 0.7782,
+      "step": 267
+    },
+    {
+      "epoch": 0.6265341905318527,
+      "grad_norm": 4.098138917146235,
+      "learning_rate": 1.932367149758454e-06,
+      "loss": 0.7725,
+      "step": 268
+    },
+    {
+      "epoch": 0.6288720046756283,
+      "grad_norm": 4.141313603560724,
+      "learning_rate": 1.920289855072464e-06,
+      "loss": 0.7785,
+      "step": 269
+    },
+    {
+      "epoch": 0.6312098188194039,
+      "grad_norm": 4.611198038918517,
+      "learning_rate": 1.9082125603864736e-06,
+      "loss": 0.8185,
+      "step": 270
+    },
+    {
+      "epoch": 0.6335476329631794,
+      "grad_norm": 4.452172749748544,
+      "learning_rate": 1.8961352657004834e-06,
+      "loss": 0.7703,
+      "step": 271
+    },
+    {
+      "epoch": 0.635885447106955,
+      "grad_norm": 4.454099100217199,
+      "learning_rate": 1.884057971014493e-06,
+      "loss": 0.7756,
+      "step": 272
+    },
+    {
+      "epoch": 0.6382232612507306,
+      "grad_norm": 4.159216947583455,
+      "learning_rate": 1.8719806763285025e-06,
+      "loss": 0.7358,
+      "step": 273
+    },
+    {
+      "epoch": 0.6405610753945061,
+      "grad_norm": 4.0088196320012885,
+      "learning_rate": 1.8599033816425122e-06,
+      "loss": 0.8002,
+      "step": 274
+    },
+    {
+      "epoch": 0.6428988895382817,
+      "grad_norm": 4.197686175636046,
+      "learning_rate": 1.8478260869565218e-06,
+      "loss": 0.7998,
+      "step": 275
+    },
+    {
+      "epoch": 0.6452367036820573,
+      "grad_norm": 4.373828840174765,
+      "learning_rate": 1.8357487922705318e-06,
+      "loss": 0.742,
+      "step": 276
+    },
+    {
+      "epoch": 0.6475745178258329,
+      "grad_norm": 4.212073348085054,
+      "learning_rate": 1.8236714975845413e-06,
+      "loss": 0.7678,
+      "step": 277
+    },
+    {
+      "epoch": 0.6499123319696084,
+      "grad_norm": 3.972532257275605,
+      "learning_rate": 1.8115942028985508e-06,
+      "loss": 0.7757,
+      "step": 278
+    },
+    {
+      "epoch": 0.6522501461133839,
+      "grad_norm": 4.141324887414669,
+      "learning_rate": 1.7995169082125604e-06,
+      "loss": 0.7447,
+      "step": 279
+    },
+    {
+      "epoch": 0.6545879602571596,
+      "grad_norm": 4.319306461683,
+      "learning_rate": 1.7874396135265702e-06,
+      "loss": 0.7669,
+      "step": 280
+    },
+    {
+      "epoch": 0.6569257744009351,
+      "grad_norm": 4.13159761798667,
+      "learning_rate": 1.77536231884058e-06,
+      "loss": 0.753,
+      "step": 281
+    },
+    {
+      "epoch": 0.6592635885447107,
+      "grad_norm": 4.261205598617194,
+      "learning_rate": 1.7632850241545897e-06,
+      "loss": 0.7867,
+      "step": 282
+    },
+    {
+      "epoch": 0.6616014026884862,
+      "grad_norm": 4.043224440888056,
+      "learning_rate": 1.7512077294685992e-06,
+      "loss": 0.7634,
+      "step": 283
+    },
+    {
+      "epoch": 0.6639392168322619,
+      "grad_norm": 4.221366014724788,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8032,
+      "step": 284
+    },
+    {
+      "epoch": 0.6662770309760374,
+      "grad_norm": 4.2120362159497935,
+      "learning_rate": 1.7270531400966183e-06,
+      "loss": 0.7449,
+      "step": 285
+    },
+    {
+      "epoch": 0.668614845119813,
+      "grad_norm": 4.330019099169185,
+      "learning_rate": 1.7149758454106283e-06,
+      "loss": 0.7641,
+      "step": 286
+    },
+    {
+      "epoch": 0.6709526592635885,
+      "grad_norm": 4.234551345137344,
+      "learning_rate": 1.7028985507246378e-06,
+      "loss": 0.7785,
+      "step": 287
+    },
+    {
+      "epoch": 0.6732904734073641,
+      "grad_norm": 4.789360597178873,
+      "learning_rate": 1.6908212560386476e-06,
+      "loss": 0.7517,
+      "step": 288
+    },
+    {
+      "epoch": 0.6756282875511397,
+      "grad_norm": 4.087545337483895,
+      "learning_rate": 1.6787439613526571e-06,
+      "loss": 0.7398,
+      "step": 289
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 4.048928229662754,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7759,
+      "step": 290
+    },
+    {
+      "epoch": 0.6803039158386909,
+      "grad_norm": 4.258228190717208,
+      "learning_rate": 1.6545893719806766e-06,
+      "loss": 0.7816,
+      "step": 291
+    },
+    {
+      "epoch": 0.6826417299824664,
+      "grad_norm": 4.207730290983508,
+      "learning_rate": 1.6425120772946862e-06,
+      "loss": 0.7492,
+      "step": 292
+    },
+    {
+      "epoch": 0.684979544126242,
+      "grad_norm": 4.211632269620855,
+      "learning_rate": 1.6304347826086957e-06,
+      "loss": 0.8045,
+      "step": 293
+    },
+    {
+      "epoch": 0.6873173582700175,
+      "grad_norm": 4.2791266083196575,
+      "learning_rate": 1.6183574879227055e-06,
+      "loss": 0.7686,
+      "step": 294
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 4.400251918863611,
+      "learning_rate": 1.606280193236715e-06,
+      "loss": 0.7346,
+      "step": 295
+    },
+    {
+      "epoch": 0.6919929865575687,
+      "grad_norm": 3.8930859729711,
+      "learning_rate": 1.5942028985507246e-06,
+      "loss": 0.7476,
+      "step": 296
+    },
+    {
+      "epoch": 0.6943308007013442,
+      "grad_norm": 4.179140087181349,
+      "learning_rate": 1.5821256038647345e-06,
+      "loss": 0.7758,
+      "step": 297
+    },
+    {
+      "epoch": 0.6966686148451198,
+      "grad_norm": 4.1025982230247005,
+      "learning_rate": 1.570048309178744e-06,
+      "loss": 0.764,
+      "step": 298
+    },
+    {
+      "epoch": 0.6990064289888954,
+      "grad_norm": 4.54359763623282,
+      "learning_rate": 1.5579710144927536e-06,
+      "loss": 0.813,
+      "step": 299
+    },
+    {
+      "epoch": 0.701344243132671,
+      "grad_norm": 3.8868646182191333,
+      "learning_rate": 1.5458937198067634e-06,
+      "loss": 0.7809,
+      "step": 300
+    },
+    {
+      "epoch": 0.7036820572764465,
+      "grad_norm": 4.027087287618028,
+      "learning_rate": 1.533816425120773e-06,
+      "loss": 0.7421,
+      "step": 301
+    },
+    {
+      "epoch": 0.706019871420222,
+      "grad_norm": 4.221180533576584,
+      "learning_rate": 1.521739130434783e-06,
+      "loss": 0.7437,
+      "step": 302
+    },
+    {
+      "epoch": 0.7083576855639977,
+      "grad_norm": 4.025585601097397,
+      "learning_rate": 1.5096618357487924e-06,
+      "loss": 0.7587,
+      "step": 303
+    },
+    {
+      "epoch": 0.7106954997077732,
+      "grad_norm": 4.082415548970675,
+      "learning_rate": 1.497584541062802e-06,
+      "loss": 0.7437,
+      "step": 304
+    },
+    {
+      "epoch": 0.7130333138515488,
+      "grad_norm": 3.9885030268207764,
+      "learning_rate": 1.4855072463768117e-06,
+      "loss": 0.7342,
+      "step": 305
+    },
+    {
+      "epoch": 0.7153711279953243,
+      "grad_norm": 4.110847006439374,
+      "learning_rate": 1.4734299516908213e-06,
+      "loss": 0.7643,
+      "step": 306
+    },
+    {
+      "epoch": 0.7177089421391,
+      "grad_norm": 4.018479338411149,
+      "learning_rate": 1.461352657004831e-06,
+      "loss": 0.7524,
+      "step": 307
+    },
+    {
+      "epoch": 0.7200467562828755,
+      "grad_norm": 3.8679633701250835,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 0.7854,
+      "step": 308
+    },
+    {
+      "epoch": 0.722384570426651,
+      "grad_norm": 4.308222321507237,
+      "learning_rate": 1.4371980676328504e-06,
+      "loss": 0.7805,
+      "step": 309
+    },
+    {
+      "epoch": 0.7247223845704267,
+      "grad_norm": 3.8916559653506018,
+      "learning_rate": 1.42512077294686e-06,
+      "loss": 0.6789,
+      "step": 310
+    },
+    {
+      "epoch": 0.7270601987142022,
+      "grad_norm": 4.208472724847014,
+      "learning_rate": 1.4130434782608697e-06,
+      "loss": 0.7624,
+      "step": 311
+    },
+    {
+      "epoch": 0.7293980128579778,
+      "grad_norm": 4.541098999570629,
+      "learning_rate": 1.4009661835748794e-06,
+      "loss": 0.7754,
+      "step": 312
+    },
+    {
+      "epoch": 0.7317358270017533,
+      "grad_norm": 3.894542881557041,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 0.7327,
+      "step": 313
+    },
+    {
+      "epoch": 0.734073641145529,
+      "grad_norm": 4.316419064602019,
+      "learning_rate": 1.3768115942028987e-06,
+      "loss": 0.7785,
+      "step": 314
+    },
+    {
+      "epoch": 0.7364114552893045,
+      "grad_norm": 3.840444616763943,
+      "learning_rate": 1.3647342995169083e-06,
+      "loss": 0.7296,
+      "step": 315
+    },
+    {
+      "epoch": 0.7387492694330801,
+      "grad_norm": 4.0101608921412835,
+      "learning_rate": 1.3526570048309178e-06,
+      "loss": 0.7199,
+      "step": 316
+    },
+    {
+      "epoch": 0.7410870835768556,
+      "grad_norm": 4.02178577481216,
+      "learning_rate": 1.3405797101449278e-06,
+      "loss": 0.7662,
+      "step": 317
+    },
+    {
+      "epoch": 0.7434248977206313,
+      "grad_norm": 3.955088131738884,
+      "learning_rate": 1.3285024154589373e-06,
+      "loss": 0.7196,
+      "step": 318
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 4.130879922008592,
+      "learning_rate": 1.316425120772947e-06,
+      "loss": 0.787,
+      "step": 319
+    },
+    {
+      "epoch": 0.7481005260081823,
+      "grad_norm": 4.0739088224040705,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 0.7509,
+      "step": 320
+    },
+    {
+      "epoch": 0.7504383401519579,
+      "grad_norm": 4.2499948389358595,
+      "learning_rate": 1.2922705314009662e-06,
+      "loss": 0.7373,
+      "step": 321
+    },
+    {
+      "epoch": 0.7527761542957335,
+      "grad_norm": 4.048557241149405,
+      "learning_rate": 1.2801932367149761e-06,
+      "loss": 0.781,
+      "step": 322
+    },
+    {
+      "epoch": 0.7551139684395091,
+      "grad_norm": 4.2499198906024205,
+      "learning_rate": 1.2681159420289857e-06,
+      "loss": 0.7674,
+      "step": 323
+    },
+    {
+      "epoch": 0.7574517825832846,
+      "grad_norm": 4.1878094914635255,
+      "learning_rate": 1.2560386473429952e-06,
+      "loss": 0.726,
+      "step": 324
+    },
+    {
+      "epoch": 0.7597895967270601,
+      "grad_norm": 4.531895242987001,
+      "learning_rate": 1.243961352657005e-06,
+      "loss": 0.7849,
+      "step": 325
+    },
+    {
+      "epoch": 0.7621274108708358,
+      "grad_norm": 4.042779330179229,
+      "learning_rate": 1.2318840579710147e-06,
+      "loss": 0.7532,
+      "step": 326
+    },
+    {
+      "epoch": 0.7644652250146113,
+      "grad_norm": 3.9930786810311254,
+      "learning_rate": 1.2198067632850243e-06,
+      "loss": 0.7286,
+      "step": 327
+    },
+    {
+      "epoch": 0.7668030391583869,
+      "grad_norm": 5.948998810978814,
+      "learning_rate": 1.2077294685990338e-06,
+      "loss": 0.8127,
+      "step": 328
+    },
+    {
+      "epoch": 0.7691408533021625,
+      "grad_norm": 4.144487299852383,
+      "learning_rate": 1.1956521739130436e-06,
+      "loss": 0.7691,
+      "step": 329
+    },
+    {
+      "epoch": 0.7714786674459381,
+      "grad_norm": 4.128733708034505,
+      "learning_rate": 1.1835748792270531e-06,
+      "loss": 0.768,
+      "step": 330
+    },
+    {
+      "epoch": 0.7738164815897136,
+      "grad_norm": 4.530767375631303,
+      "learning_rate": 1.1714975845410629e-06,
+      "loss": 0.7798,
+      "step": 331
+    },
+    {
+      "epoch": 0.7761542957334892,
+      "grad_norm": 3.9238729668993835,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 0.7642,
+      "step": 332
+    },
+    {
+      "epoch": 0.7784921098772648,
+      "grad_norm": 4.111531783109019,
+      "learning_rate": 1.1473429951690822e-06,
+      "loss": 0.7616,
+      "step": 333
+    },
+    {
+      "epoch": 0.7808299240210403,
+      "grad_norm": 4.140234356572554,
+      "learning_rate": 1.135265700483092e-06,
+      "loss": 0.8308,
+      "step": 334
+    },
+    {
+      "epoch": 0.7831677381648159,
+      "grad_norm": 4.5225578335616845,
+      "learning_rate": 1.1231884057971015e-06,
+      "loss": 0.7688,
+      "step": 335
+    },
+    {
+      "epoch": 0.7855055523085914,
+      "grad_norm": 4.253055596048113,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.7823,
+      "step": 336
+    },
+    {
+      "epoch": 0.7878433664523671,
+      "grad_norm": 4.214973850734774,
+      "learning_rate": 1.0990338164251208e-06,
+      "loss": 0.7015,
+      "step": 337
+    },
+    {
+      "epoch": 0.7901811805961426,
+      "grad_norm": 4.242093529547378,
+      "learning_rate": 1.0869565217391306e-06,
+      "loss": 0.7902,
+      "step": 338
+    },
+    {
+      "epoch": 0.7925189947399182,
+      "grad_norm": 4.27860016507252,
+      "learning_rate": 1.0748792270531403e-06,
+      "loss": 0.7893,
+      "step": 339
+    },
+    {
+      "epoch": 0.7948568088836937,
+      "grad_norm": 4.193517659739712,
+      "learning_rate": 1.0628019323671499e-06,
+      "loss": 0.7932,
+      "step": 340
+    },
+    {
+      "epoch": 0.7971946230274694,
+      "grad_norm": 3.861888360541971,
+      "learning_rate": 1.0507246376811594e-06,
+      "loss": 0.7271,
+      "step": 341
+    },
+    {
+      "epoch": 0.7995324371712449,
+      "grad_norm": 4.044324859369637,
+      "learning_rate": 1.0386473429951692e-06,
+      "loss": 0.7651,
+      "step": 342
+    },
+    {
+      "epoch": 0.8018702513150204,
+      "grad_norm": 4.143848474405527,
+      "learning_rate": 1.026570048309179e-06,
+      "loss": 0.7991,
+      "step": 343
+    },
+    {
+      "epoch": 0.804208065458796,
+      "grad_norm": 4.543740361976109,
+      "learning_rate": 1.0144927536231885e-06,
+      "loss": 0.7871,
+      "step": 344
+    },
+    {
+      "epoch": 0.8065458796025716,
+      "grad_norm": 4.053324740509495,
+      "learning_rate": 1.0024154589371982e-06,
+      "loss": 0.7181,
+      "step": 345
+    },
+    {
+      "epoch": 0.8088836937463472,
+      "grad_norm": 3.91170761323185,
+      "learning_rate": 9.903381642512078e-07,
+      "loss": 0.7167,
+      "step": 346
+    },
+    {
+      "epoch": 0.8112215078901227,
+      "grad_norm": 3.9769619064751174,
+      "learning_rate": 9.782608695652175e-07,
+      "loss": 0.7152,
+      "step": 347
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 4.141477101296879,
+      "learning_rate": 9.66183574879227e-07,
+      "loss": 0.806,
+      "step": 348
+    },
+    {
+      "epoch": 0.8158971361776739,
+      "grad_norm": 3.9266793661338566,
+      "learning_rate": 9.541062801932368e-07,
+      "loss": 0.74,
+      "step": 349
+    },
+    {
+      "epoch": 0.8182349503214494,
+      "grad_norm": 3.905819434278297,
+      "learning_rate": 9.420289855072465e-07,
+      "loss": 0.7621,
+      "step": 350
+    },
+    {
+      "epoch": 0.820572764465225,
+      "grad_norm": 4.271457136544383,
+      "learning_rate": 9.299516908212561e-07,
+      "loss": 0.7108,
+      "step": 351
+    },
+    {
+      "epoch": 0.8229105786090006,
+      "grad_norm": 3.9018935668444907,
+      "learning_rate": 9.178743961352659e-07,
+      "loss": 0.7326,
+      "step": 352
+    },
+    {
+      "epoch": 0.8252483927527762,
+      "grad_norm": 3.842764627332658,
+      "learning_rate": 9.057971014492754e-07,
+      "loss": 0.769,
+      "step": 353
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 4.12270406926976,
+      "learning_rate": 8.937198067632851e-07,
+      "loss": 0.7462,
+      "step": 354
+    },
+    {
+      "epoch": 0.8299240210403273,
+      "grad_norm": 4.25238665717318,
+      "learning_rate": 8.816425120772948e-07,
+      "loss": 0.7417,
+      "step": 355
+    },
+    {
+      "epoch": 0.8322618351841029,
+      "grad_norm": 4.10405871770544,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.7769,
+      "step": 356
+    },
+    {
+      "epoch": 0.8345996493278784,
+      "grad_norm": 4.132898802117579,
+      "learning_rate": 8.574879227053141e-07,
+      "loss": 0.7334,
+      "step": 357
+    },
+    {
+      "epoch": 0.836937463471654,
+      "grad_norm": 3.9812833871444573,
+      "learning_rate": 8.454106280193238e-07,
+      "loss": 0.7437,
+      "step": 358
+    },
+    {
+      "epoch": 0.8392752776154295,
+      "grad_norm": 4.819360178352156,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.7594,
+      "step": 359
+    },
+    {
+      "epoch": 0.8416130917592052,
+      "grad_norm": 4.27077723520544,
+      "learning_rate": 8.212560386473431e-07,
+      "loss": 0.7282,
+      "step": 360
+    },
+    {
+      "epoch": 0.8439509059029807,
+      "grad_norm": 4.234704486935872,
+      "learning_rate": 8.091787439613527e-07,
+      "loss": 0.7844,
+      "step": 361
+    },
+    {
+      "epoch": 0.8462887200467563,
+      "grad_norm": 3.660518143878683,
+      "learning_rate": 7.971014492753623e-07,
+      "loss": 0.6846,
+      "step": 362
+    },
+    {
+      "epoch": 0.8486265341905318,
+      "grad_norm": 4.382898231252646,
+      "learning_rate": 7.85024154589372e-07,
+      "loss": 0.7378,
+      "step": 363
+    },
+    {
+      "epoch": 0.8509643483343075,
+      "grad_norm": 4.03693007471031,
+      "learning_rate": 7.729468599033817e-07,
+      "loss": 0.7321,
+      "step": 364
+    },
+    {
+      "epoch": 0.853302162478083,
+      "grad_norm": 4.061417655548705,
+      "learning_rate": 7.608695652173914e-07,
+      "loss": 0.7427,
+      "step": 365
+    },
+    {
+      "epoch": 0.8556399766218585,
+      "grad_norm": 4.033537459659518,
+      "learning_rate": 7.48792270531401e-07,
+      "loss": 0.7631,
+      "step": 366
+    },
+    {
+      "epoch": 0.8579777907656342,
+      "grad_norm": 3.8672964986217377,
+      "learning_rate": 7.367149758454106e-07,
+      "loss": 0.7277,
+      "step": 367
+    },
+    {
+      "epoch": 0.8603156049094097,
+      "grad_norm": 4.1614750880483795,
+      "learning_rate": 7.246376811594204e-07,
+      "loss": 0.7821,
+      "step": 368
+    },
+    {
+      "epoch": 0.8626534190531853,
+      "grad_norm": 4.0347237221296846,
+      "learning_rate": 7.1256038647343e-07,
+      "loss": 0.7229,
+      "step": 369
+    },
+    {
+      "epoch": 0.8649912331969608,
+      "grad_norm": 4.419235250329394,
+      "learning_rate": 7.004830917874397e-07,
+      "loss": 0.7912,
+      "step": 370
+    },
+    {
+      "epoch": 0.8673290473407365,
+      "grad_norm": 4.0395927745176925,
+      "learning_rate": 6.884057971014494e-07,
+      "loss": 0.7781,
+      "step": 371
+    },
+    {
+      "epoch": 0.869666861484512,
+      "grad_norm": 4.323154501136669,
+      "learning_rate": 6.763285024154589e-07,
+      "loss": 0.7489,
+      "step": 372
+    },
+    {
+      "epoch": 0.8720046756282875,
+      "grad_norm": 4.0036925914792,
+      "learning_rate": 6.642512077294687e-07,
+      "loss": 0.7488,
+      "step": 373
+    },
+    {
+      "epoch": 0.8743424897720631,
+      "grad_norm": 4.081792943103691,
+      "learning_rate": 6.521739130434783e-07,
+      "loss": 0.7506,
+      "step": 374
+    },
+    {
+      "epoch": 0.8766803039158387,
+      "grad_norm": 3.961593904598705,
+      "learning_rate": 6.400966183574881e-07,
+      "loss": 0.7365,
+      "step": 375
+    },
+    {
+      "epoch": 0.8790181180596143,
+      "grad_norm": 5.343637922572841,
+      "learning_rate": 6.280193236714976e-07,
+      "loss": 0.8142,
+      "step": 376
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 4.234613953777181,
+      "learning_rate": 6.159420289855074e-07,
+      "loss": 0.7685,
+      "step": 377
+    },
+    {
+      "epoch": 0.8836937463471654,
+      "grad_norm": 3.914888154011919,
+      "learning_rate": 6.038647342995169e-07,
+      "loss": 0.7442,
+      "step": 378
+    },
+    {
+      "epoch": 0.886031560490941,
+      "grad_norm": 3.998960956090034,
+      "learning_rate": 5.917874396135266e-07,
+      "loss": 0.7724,
+      "step": 379
+    },
+    {
+      "epoch": 0.8883693746347165,
+      "grad_norm": 3.7467228875291885,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 0.7157,
+      "step": 380
+    },
+    {
+      "epoch": 0.8907071887784921,
+      "grad_norm": 3.921411494491602,
+      "learning_rate": 5.67632850241546e-07,
+      "loss": 0.7604,
+      "step": 381
+    },
+    {
+      "epoch": 0.8930450029222676,
+      "grad_norm": 4.171395377831423,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.7498,
+      "step": 382
+    },
+    {
+      "epoch": 0.8953828170660433,
+      "grad_norm": 4.1347642411133725,
+      "learning_rate": 5.434782608695653e-07,
+      "loss": 0.7472,
+      "step": 383
+    },
+    {
+      "epoch": 0.8977206312098188,
+      "grad_norm": 4.092973708302494,
+      "learning_rate": 5.314009661835749e-07,
+      "loss": 0.7237,
+      "step": 384
+    },
+    {
+      "epoch": 0.9000584453535944,
+      "grad_norm": 3.9933326706118875,
+      "learning_rate": 5.193236714975846e-07,
+      "loss": 0.7389,
+      "step": 385
+    },
+    {
+      "epoch": 0.90239625949737,
+      "grad_norm": 3.8068860103615174,
+      "learning_rate": 5.072463768115942e-07,
+      "loss": 0.7177,
+      "step": 386
+    },
+    {
+      "epoch": 0.9047340736411456,
+      "grad_norm": 4.25980749026596,
+      "learning_rate": 4.951690821256039e-07,
+      "loss": 0.758,
+      "step": 387
+    },
+    {
+      "epoch": 0.9070718877849211,
+      "grad_norm": 3.8688206778681278,
+      "learning_rate": 4.830917874396135e-07,
+      "loss": 0.7577,
+      "step": 388
+    },
+    {
+      "epoch": 0.9094097019286966,
+      "grad_norm": 4.072604714599362,
+      "learning_rate": 4.7101449275362324e-07,
+      "loss": 0.7655,
+      "step": 389
+    },
+    {
+      "epoch": 0.9117475160724723,
+      "grad_norm": 4.216731514011164,
+      "learning_rate": 4.5893719806763294e-07,
+      "loss": 0.7572,
+      "step": 390
+    },
+    {
+      "epoch": 0.9140853302162478,
+      "grad_norm": 4.204400645393741,
+      "learning_rate": 4.4685990338164254e-07,
+      "loss": 0.7595,
+      "step": 391
+    },
+    {
+      "epoch": 0.9164231443600234,
+      "grad_norm": 4.327014987328045,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 0.7347,
+      "step": 392
+    },
+    {
+      "epoch": 0.9187609585037989,
+      "grad_norm": 4.381847799007514,
+      "learning_rate": 4.227053140096619e-07,
+      "loss": 0.7505,
+      "step": 393
+    },
+    {
+      "epoch": 0.9210987726475746,
+      "grad_norm": 4.019350453750999,
+      "learning_rate": 4.1062801932367154e-07,
+      "loss": 0.7488,
+      "step": 394
+    },
+    {
+      "epoch": 0.9234365867913501,
+      "grad_norm": 3.958102022071496,
+      "learning_rate": 3.9855072463768114e-07,
+      "loss": 0.7436,
+      "step": 395
+    },
+    {
+      "epoch": 0.9257744009351256,
+      "grad_norm": 4.3569068621437745,
+      "learning_rate": 3.8647342995169085e-07,
+      "loss": 0.7323,
+      "step": 396
+    },
+    {
+      "epoch": 0.9281122150789012,
+      "grad_norm": 3.9242746982918777,
+      "learning_rate": 3.743961352657005e-07,
+      "loss": 0.7255,
+      "step": 397
+    },
+    {
+      "epoch": 0.9304500292226768,
+      "grad_norm": 3.91121815410949,
+      "learning_rate": 3.623188405797102e-07,
+      "loss": 0.7471,
+      "step": 398
+    },
+    {
+      "epoch": 0.9327878433664524,
+      "grad_norm": 3.973005041304068,
+      "learning_rate": 3.5024154589371985e-07,
+      "loss": 0.6823,
+      "step": 399
+    },
+    {
+      "epoch": 0.9351256575102279,
+      "grad_norm": 3.988161090830406,
+      "learning_rate": 3.3816425120772945e-07,
+      "loss": 0.6871,
+      "step": 400
+    },
+    {
+      "epoch": 0.9374634716540035,
+      "grad_norm": 4.296337191130102,
+      "learning_rate": 3.2608695652173915e-07,
+      "loss": 0.7236,
+      "step": 401
+    },
+    {
+      "epoch": 0.9398012857977791,
+      "grad_norm": 4.3179225277967515,
+      "learning_rate": 3.140096618357488e-07,
+      "loss": 0.7582,
+      "step": 402
+    },
+    {
+      "epoch": 0.9421390999415546,
+      "grad_norm": 4.191674727829652,
+      "learning_rate": 3.0193236714975846e-07,
+      "loss": 0.7238,
+      "step": 403
+    },
+    {
+      "epoch": 0.9444769140853302,
+      "grad_norm": 3.8257966103380765,
+      "learning_rate": 2.8985507246376816e-07,
+      "loss": 0.7475,
+      "step": 404
+    },
+    {
+      "epoch": 0.9468147282291058,
+      "grad_norm": 4.06630469936539,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.7109,
+      "step": 405
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 4.583718694034358,
+      "learning_rate": 2.6570048309178746e-07,
+      "loss": 0.7623,
+      "step": 406
+    },
+    {
+      "epoch": 0.9514903565166569,
+      "grad_norm": 3.9553370864295694,
+      "learning_rate": 2.536231884057971e-07,
+      "loss": 0.7911,
+      "step": 407
+    },
+    {
+      "epoch": 0.9538281706604325,
+      "grad_norm": 4.221184826167876,
+      "learning_rate": 2.4154589371980677e-07,
+      "loss": 0.7322,
+      "step": 408
+    },
+    {
+      "epoch": 0.9561659848042081,
+      "grad_norm": 4.196761181297048,
+      "learning_rate": 2.2946859903381647e-07,
+      "loss": 0.7476,
+      "step": 409
+    },
+    {
+      "epoch": 0.9585037989479837,
+      "grad_norm": 4.185489684411542,
+      "learning_rate": 2.173913043478261e-07,
+      "loss": 0.7548,
+      "step": 410
+    },
+    {
+      "epoch": 0.9608416130917592,
+      "grad_norm": 4.371686498083367,
+      "learning_rate": 2.0531400966183577e-07,
+      "loss": 0.7328,
+      "step": 411
+    },
+    {
+      "epoch": 0.9631794272355347,
+      "grad_norm": 4.314986686818614,
+      "learning_rate": 1.9323671497584542e-07,
+      "loss": 0.7304,
+      "step": 412
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 3.9822912414587806,
+      "learning_rate": 1.811594202898551e-07,
+      "loss": 0.7395,
+      "step": 413
+    },
+    {
+      "epoch": 0.9678550555230859,
+      "grad_norm": 4.218523033535868,
+      "learning_rate": 1.6908212560386473e-07,
+      "loss": 0.7302,
+      "step": 414
+    },
+    {
+      "epoch": 0.9701928696668615,
+      "grad_norm": 4.092187481356195,
+      "learning_rate": 1.570048309178744e-07,
+      "loss": 0.7351,
+      "step": 415
+    },
+    {
+      "epoch": 0.972530683810637,
+      "grad_norm": 4.184125537002853,
+      "learning_rate": 1.4492753623188408e-07,
+      "loss": 0.7413,
+      "step": 416
+    },
+    {
+      "epoch": 0.9748684979544127,
+      "grad_norm": 3.889649663413063,
+      "learning_rate": 1.3285024154589373e-07,
+      "loss": 0.7365,
+      "step": 417
+    },
+    {
+      "epoch": 0.9772063120981882,
+      "grad_norm": 4.139378543594781,
+      "learning_rate": 1.2077294685990338e-07,
+      "loss": 0.7626,
+      "step": 418
+    },
+    {
+      "epoch": 0.9795441262419637,
+      "grad_norm": 4.016007817051792,
+      "learning_rate": 1.0869565217391305e-07,
+      "loss": 0.7428,
+      "step": 419
+    },
+    {
+      "epoch": 0.9818819403857393,
+      "grad_norm": 4.31935746465498,
+      "learning_rate": 9.661835748792271e-08,
+      "loss": 0.7886,
+      "step": 420
+    },
+    {
+      "epoch": 0.9842197545295149,
+      "grad_norm": 4.305755648868578,
+      "learning_rate": 8.454106280193236e-08,
+      "loss": 0.7552,
+      "step": 421
+    },
+    {
+      "epoch": 0.9865575686732905,
+      "grad_norm": 4.324910095691635,
+      "learning_rate": 7.246376811594204e-08,
+      "loss": 0.7465,
+      "step": 422
+    },
+    {
+      "epoch": 0.988895382817066,
+      "grad_norm": 3.694300442393254,
+      "learning_rate": 6.038647342995169e-08,
+      "loss": 0.7093,
+      "step": 423
+    },
+    {
+      "epoch": 0.9912331969608417,
+      "grad_norm": 3.829444377626212,
+      "learning_rate": 4.8309178743961356e-08,
+      "loss": 0.7241,
+      "step": 424
+    },
+    {
+      "epoch": 0.9935710111046172,
+      "grad_norm": 4.179549227414933,
+      "learning_rate": 3.623188405797102e-08,
+      "loss": 0.7663,
+      "step": 425
+    },
+    {
+      "epoch": 0.9959088252483927,
+      "grad_norm": 3.832323286806212,
+      "learning_rate": 2.4154589371980678e-08,
+      "loss": 0.7859,
+      "step": 426
+    },
+    {
+      "epoch": 0.9982466393921683,
+      "grad_norm": 4.123264294362188,
+      "learning_rate": 1.2077294685990339e-08,
+      "loss": 0.7678,
+      "step": 427
+    },
+    {
+      "epoch": 0.9982466393921683,
+      "step": 427,
+      "total_flos": 77746305761280.0,
+      "train_loss": 0.8145518043281323,
+      "train_runtime": 5184.5045,
+      "train_samples_per_second": 10.56,
+      "train_steps_per_second": 0.082
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 427,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 77746305761280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8ce2d5b5c98b4f1d5ec5391f325f087b05052b4ea8949ed0bdebf2f573c337
+size 8504