Training in progress, step 520, checkpoint

checkpoint-520/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "jeiku/MoEv2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128019,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-520/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128019,
+  "transformers_version": "4.47.0",
+  "use_cache": false
+}

checkpoint-520/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7665f2b189d01fb9fe85ddfb6710fd71bf04ccb60f3baa29f9cdcb9819c84bb4
+size 4991107544

checkpoint-520/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2944367659f3c49147e697009b2e91c7c49a23df5411abb3f93f9ee0242043cb
+size 4945546240

checkpoint-520/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98961bae297e6be4667ccc083eb8b2b2717b8dc1cc84e260f0aea1c819449256
+size 4525495048

checkpoint-520/model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+  "metadata": {
+    "total_size": 14462097408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-520/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089798ee764dd8ed11b231420beb98d776193413fa8f977734e9b438e7cb70f6
+size 14689336226

checkpoint-520/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f50a692634404f2eebb2eab9f456865957578d752987bc52d843ac2a774366
+size 14244

checkpoint-520/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f66861d4ff62f7a73dab7b641047fc393f1908bb3b4adbbda49ed329254254
+size 1064

checkpoint-520/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-520/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884

checkpoint-520/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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-520/trainer_state.json

@@ -0,0 +1,3713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9942418426103647,
+  "eval_steps": 130,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003838771593090211,
+      "grad_norm": 41.942832946777344,
+      "learning_rate": 5e-06,
+      "loss": 29.5342,
+      "step": 1
+    },
+    {
+      "epoch": 0.003838771593090211,
+      "eval_loss": 1.869257926940918,
+      "eval_runtime": 31.5851,
+      "eval_samples_per_second": 9.372,
+      "eval_steps_per_second": 4.686,
+      "step": 1
+    },
+    {
+      "epoch": 0.007677543186180422,
+      "grad_norm": 37.62504577636719,
+      "learning_rate": 1e-05,
+      "loss": 29.602,
+      "step": 2
+    },
+    {
+      "epoch": 0.011516314779270634,
+      "grad_norm": 27.579742431640625,
+      "learning_rate": 1.5e-05,
+      "loss": 28.6884,
+      "step": 3
+    },
+    {
+      "epoch": 0.015355086372360844,
+      "grad_norm": 36.99763870239258,
+      "learning_rate": 2e-05,
+      "loss": 29.9575,
+      "step": 4
+    },
+    {
+      "epoch": 0.019193857965451054,
+      "grad_norm": 37.934635162353516,
+      "learning_rate": 2.5e-05,
+      "loss": 28.0644,
+      "step": 5
+    },
+    {
+      "epoch": 0.023032629558541268,
+      "grad_norm": 45.45661163330078,
+      "learning_rate": 3e-05,
+      "loss": 29.0135,
+      "step": 6
+    },
+    {
+      "epoch": 0.026871401151631478,
+      "grad_norm": 31.74431800842285,
+      "learning_rate": 3.5e-05,
+      "loss": 29.0581,
+      "step": 7
+    },
+    {
+      "epoch": 0.030710172744721688,
+      "grad_norm": 32.59209060668945,
+      "learning_rate": 4e-05,
+      "loss": 28.5253,
+      "step": 8
+    },
+    {
+      "epoch": 0.0345489443378119,
+      "grad_norm": 26.19696617126465,
+      "learning_rate": 4.5e-05,
+      "loss": 27.7504,
+      "step": 9
+    },
+    {
+      "epoch": 0.03838771593090211,
+      "grad_norm": 30.916200637817383,
+      "learning_rate": 5e-05,
+      "loss": 29.3754,
+      "step": 10
+    },
+    {
+      "epoch": 0.04222648752399232,
+      "grad_norm": 25.58551597595215,
+      "learning_rate": 4.9999525683718174e-05,
+      "loss": 29.0332,
+      "step": 11
+    },
+    {
+      "epoch": 0.046065259117082535,
+      "grad_norm": 30.068437576293945,
+      "learning_rate": 4.9998102752870765e-05,
+      "loss": 29.2469,
+      "step": 12
+    },
+    {
+      "epoch": 0.04990403071017274,
+      "grad_norm": 25.17665672302246,
+      "learning_rate": 4.999573126145132e-05,
+      "loss": 28.2097,
+      "step": 13
+    },
+    {
+      "epoch": 0.053742802303262956,
+      "grad_norm": 27.615007400512695,
+      "learning_rate": 4.99924112994468e-05,
+      "loss": 29.7609,
+      "step": 14
+    },
+    {
+      "epoch": 0.05758157389635317,
+      "grad_norm": 26.473073959350586,
+      "learning_rate": 4.998814299283415e-05,
+      "loss": 29.3846,
+      "step": 15
+    },
+    {
+      "epoch": 0.061420345489443376,
+      "grad_norm": 22.732168197631836,
+      "learning_rate": 4.998292650357558e-05,
+      "loss": 28.2741,
+      "step": 16
+    },
+    {
+      "epoch": 0.06525911708253358,
+      "grad_norm": 26.874069213867188,
+      "learning_rate": 4.9976762029612335e-05,
+      "loss": 30.2697,
+      "step": 17
+    },
+    {
+      "epoch": 0.0690978886756238,
+      "grad_norm": 22.940404891967773,
+      "learning_rate": 4.9969649804857257e-05,
+      "loss": 29.0416,
+      "step": 18
+    },
+    {
+      "epoch": 0.07293666026871401,
+      "grad_norm": 22.93003273010254,
+      "learning_rate": 4.996159009918585e-05,
+      "loss": 30.0236,
+      "step": 19
+    },
+    {
+      "epoch": 0.07677543186180422,
+      "grad_norm": 21.159198760986328,
+      "learning_rate": 4.995258321842611e-05,
+      "loss": 29.995,
+      "step": 20
+    },
+    {
+      "epoch": 0.08061420345489444,
+      "grad_norm": 23.158321380615234,
+      "learning_rate": 4.9942629504346827e-05,
+      "loss": 30.1427,
+      "step": 21
+    },
+    {
+      "epoch": 0.08445297504798464,
+      "grad_norm": 22.745277404785156,
+      "learning_rate": 4.993172933464471e-05,
+      "loss": 29.0171,
+      "step": 22
+    },
+    {
+      "epoch": 0.08829174664107485,
+      "grad_norm": 21.473155975341797,
+      "learning_rate": 4.9919883122929976e-05,
+      "loss": 29.1784,
+      "step": 23
+    },
+    {
+      "epoch": 0.09213051823416507,
+      "grad_norm": 21.882991790771484,
+      "learning_rate": 4.990709131871074e-05,
+      "loss": 27.7198,
+      "step": 24
+    },
+    {
+      "epoch": 0.09596928982725528,
+      "grad_norm": 20.5384464263916,
+      "learning_rate": 4.989335440737586e-05,
+      "loss": 29.3608,
+      "step": 25
+    },
+    {
+      "epoch": 0.09980806142034548,
+      "grad_norm": 21.028078079223633,
+      "learning_rate": 4.9878672910176615e-05,
+      "loss": 30.7017,
+      "step": 26
+    },
+    {
+      "epoch": 0.1036468330134357,
+      "grad_norm": 20.912294387817383,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 29.2454,
+      "step": 27
+    },
+    {
+      "epoch": 0.10748560460652591,
+      "grad_norm": 22.990535736083984,
+      "learning_rate": 4.984647842238185e-05,
+      "loss": 30.5442,
+      "step": 28
+    },
+    {
+      "epoch": 0.11132437619961612,
+      "grad_norm": 20.818967819213867,
+      "learning_rate": 4.982896665341591e-05,
+      "loss": 28.0971,
+      "step": 29
+    },
+    {
+      "epoch": 0.11516314779270634,
+      "grad_norm": 22.41204071044922,
+      "learning_rate": 4.98105127417984e-05,
+      "loss": 30.0213,
+      "step": 30
+    },
+    {
+      "epoch": 0.11900191938579655,
+      "grad_norm": 20.42460823059082,
+      "learning_rate": 4.979111738776857e-05,
+      "loss": 29.0625,
+      "step": 31
+    },
+    {
+      "epoch": 0.12284069097888675,
+      "grad_norm": 23.12067413330078,
+      "learning_rate": 4.977078132728901e-05,
+      "loss": 30.4828,
+      "step": 32
+    },
+    {
+      "epoch": 0.12667946257197696,
+      "grad_norm": 19.101734161376953,
+      "learning_rate": 4.974950533201767e-05,
+      "loss": 27.8432,
+      "step": 33
+    },
+    {
+      "epoch": 0.13051823416506717,
+      "grad_norm": 18.871788024902344,
+      "learning_rate": 4.972729020927865e-05,
+      "loss": 28.2289,
+      "step": 34
+    },
+    {
+      "epoch": 0.1343570057581574,
+      "grad_norm": 19.23995590209961,
+      "learning_rate": 4.9704136802031485e-05,
+      "loss": 28.7979,
+      "step": 35
+    },
+    {
+      "epoch": 0.1381957773512476,
+      "grad_norm": 19.988222122192383,
+      "learning_rate": 4.968004598883923e-05,
+      "loss": 29.0405,
+      "step": 36
+    },
+    {
+      "epoch": 0.1420345489443378,
+      "grad_norm": 17.621200561523438,
+      "learning_rate": 4.965501868383506e-05,
+      "loss": 28.8017,
+      "step": 37
+    },
+    {
+      "epoch": 0.14587332053742802,
+      "grad_norm": 19.57996368408203,
+      "learning_rate": 4.9629055836687665e-05,
+      "loss": 28.5596,
+      "step": 38
+    },
+    {
+      "epoch": 0.14971209213051823,
+      "grad_norm": 19.62120819091797,
+      "learning_rate": 4.960215843256511e-05,
+      "loss": 28.6677,
+      "step": 39
+    },
+    {
+      "epoch": 0.15355086372360843,
+      "grad_norm": 18.79466438293457,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 30.2908,
+      "step": 40
+    },
+    {
+      "epoch": 0.15738963531669867,
+      "grad_norm": 21.75792694091797,
+      "learning_rate": 4.9545564071338426e-05,
+      "loss": 28.7169,
+      "step": 41
+    },
+    {
+      "epoch": 0.16122840690978887,
+      "grad_norm": 21.684478759765625,
+      "learning_rate": 4.9515869261724446e-05,
+      "loss": 28.8571,
+      "step": 42
+    },
+    {
+      "epoch": 0.16506717850287908,
+      "grad_norm": 20.90673065185547,
+      "learning_rate": 4.948524419003415e-05,
+      "loss": 28.5535,
+      "step": 43
+    },
+    {
+      "epoch": 0.1689059500959693,
+      "grad_norm": 20.5564022064209,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 29.5709,
+      "step": 44
+    },
+    {
+      "epoch": 0.1727447216890595,
+      "grad_norm": 21.395124435424805,
+      "learning_rate": 4.942120794399002e-05,
+      "loss": 28.016,
+      "step": 45
+    },
+    {
+      "epoch": 0.1765834932821497,
+      "grad_norm": 18.09257698059082,
+      "learning_rate": 4.938779919951092e-05,
+      "loss": 29.6793,
+      "step": 46
+    },
+    {
+      "epoch": 0.18042226487523993,
+      "grad_norm": 19.043846130371094,
+      "learning_rate": 4.935346505261276e-05,
+      "loss": 30.1972,
+      "step": 47
+    },
+    {
+      "epoch": 0.18426103646833014,
+      "grad_norm": 20.1807804107666,
+      "learning_rate": 4.931820680611512e-05,
+      "loss": 28.7825,
+      "step": 48
+    },
+    {
+      "epoch": 0.18809980806142035,
+      "grad_norm": 18.534324645996094,
+      "learning_rate": 4.928202579790285e-05,
+      "loss": 27.895,
+      "step": 49
+    },
+    {
+      "epoch": 0.19193857965451055,
+      "grad_norm": 19.662391662597656,
+      "learning_rate": 4.9244923400875245e-05,
+      "loss": 30.0118,
+      "step": 50
+    },
+    {
+      "epoch": 0.19577735124760076,
+      "grad_norm": 19.72050666809082,
+      "learning_rate": 4.920690102289397e-05,
+      "loss": 28.6979,
+      "step": 51
+    },
+    {
+      "epoch": 0.19961612284069097,
+      "grad_norm": 20.052833557128906,
+      "learning_rate": 4.916796010672969e-05,
+      "loss": 29.5174,
+      "step": 52
+    },
+    {
+      "epoch": 0.2034548944337812,
+      "grad_norm": 18.85672378540039,
+      "learning_rate": 4.9128102130007225e-05,
+      "loss": 28.3002,
+      "step": 53
+    },
+    {
+      "epoch": 0.2072936660268714,
+      "grad_norm": 18.159709930419922,
+      "learning_rate": 4.908732860514958e-05,
+      "loss": 28.7818,
+      "step": 54
+    },
+    {
+      "epoch": 0.21113243761996162,
+      "grad_norm": 20.378021240234375,
+      "learning_rate": 4.9045641079320484e-05,
+      "loss": 29.458,
+      "step": 55
+    },
+    {
+      "epoch": 0.21497120921305182,
+      "grad_norm": 21.459836959838867,
+      "learning_rate": 4.900304113436571e-05,
+      "loss": 27.3894,
+      "step": 56
+    },
+    {
+      "epoch": 0.21880998080614203,
+      "grad_norm": 19.784387588500977,
+      "learning_rate": 4.895953038675306e-05,
+      "loss": 29.3604,
+      "step": 57
+    },
+    {
+      "epoch": 0.22264875239923224,
+      "grad_norm": 19.705406188964844,
+      "learning_rate": 4.891511048751102e-05,
+      "loss": 27.4372,
+      "step": 58
+    },
+    {
+      "epoch": 0.22648752399232247,
+      "grad_norm": 19.9382381439209,
+      "learning_rate": 4.886978312216611e-05,
+      "loss": 28.2482,
+      "step": 59
+    },
+    {
+      "epoch": 0.23032629558541268,
+      "grad_norm": 19.08539581298828,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 28.4456,
+      "step": 60
+    },
+    {
+      "epoch": 0.23416506717850288,
+      "grad_norm": 18.285186767578125,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 28.745,
+      "step": 61
+    },
+    {
+      "epoch": 0.2380038387715931,
+      "grad_norm": 19.981107711791992,
+      "learning_rate": 4.872837360089754e-05,
+      "loss": 27.6915,
+      "step": 62
+    },
+    {
+      "epoch": 0.2418426103646833,
+      "grad_norm": 18.624874114990234,
+      "learning_rate": 4.8679433914101006e-05,
+      "loss": 28.0039,
+      "step": 63
+    },
+    {
+      "epoch": 0.2456813819577735,
+      "grad_norm": 22.298728942871094,
+      "learning_rate": 4.862959570402049e-05,
+      "loss": 28.3383,
+      "step": 64
+    },
+    {
+      "epoch": 0.2495201535508637,
+      "grad_norm": 20.383586883544922,
+      "learning_rate": 4.857886086178194e-05,
+      "loss": 28.918,
+      "step": 65
+    },
+    {
+      "epoch": 0.2533589251439539,
+      "grad_norm": 18.7249755859375,
+      "learning_rate": 4.85272313125343e-05,
+      "loss": 29.0783,
+      "step": 66
+    },
+    {
+      "epoch": 0.2571976967370441,
+      "grad_norm": 18.3210391998291,
+      "learning_rate": 4.8474709015376416e-05,
+      "loss": 27.3239,
+      "step": 67
+    },
+    {
+      "epoch": 0.26103646833013433,
+      "grad_norm": 19.459135055541992,
+      "learning_rate": 4.842129596328277e-05,
+      "loss": 29.2664,
+      "step": 68
+    },
+    {
+      "epoch": 0.2648752399232246,
+      "grad_norm": 18.80237579345703,
+      "learning_rate": 4.836699418302777e-05,
+      "loss": 28.8449,
+      "step": 69
+    },
+    {
+      "epoch": 0.2687140115163148,
+      "grad_norm": 18.05824851989746,
+      "learning_rate": 4.8311805735108894e-05,
+      "loss": 27.5182,
+      "step": 70
+    },
+    {
+      "epoch": 0.272552783109405,
+      "grad_norm": 18.784578323364258,
+      "learning_rate": 4.825573271366851e-05,
+      "loss": 28.4831,
+      "step": 71
+    },
+    {
+      "epoch": 0.2763915547024952,
+      "grad_norm": 18.89769172668457,
+      "learning_rate": 4.8198777246414373e-05,
+      "loss": 27.7881,
+      "step": 72
+    },
+    {
+      "epoch": 0.2802303262955854,
+      "grad_norm": 17.64800453186035,
+      "learning_rate": 4.814094149453891e-05,
+      "loss": 27.7358,
+      "step": 73
+    },
+    {
+      "epoch": 0.2840690978886756,
+      "grad_norm": 19.012086868286133,
+      "learning_rate": 4.808222765263724e-05,
+      "loss": 29.8711,
+      "step": 74
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "grad_norm": 18.49270248413086,
+      "learning_rate": 4.802263794862385e-05,
+      "loss": 28.3761,
+      "step": 75
+    },
+    {
+      "epoch": 0.29174664107485604,
+      "grad_norm": 21.752199172973633,
+      "learning_rate": 4.796217464364808e-05,
+      "loss": 28.3796,
+      "step": 76
+    },
+    {
+      "epoch": 0.29558541266794625,
+      "grad_norm": 19.340524673461914,
+      "learning_rate": 4.790084003200834e-05,
+      "loss": 29.4554,
+      "step": 77
+    },
+    {
+      "epoch": 0.29942418426103645,
+      "grad_norm": 21.60015869140625,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 28.0435,
+      "step": 78
+    },
+    {
+      "epoch": 0.30326295585412666,
+      "grad_norm": 20.29178237915039,
+      "learning_rate": 4.777556623115221e-05,
+      "loss": 27.563,
+      "step": 79
+    },
+    {
+      "epoch": 0.30710172744721687,
+      "grad_norm": 18.13334846496582,
+      "learning_rate": 4.7711631795488096e-05,
+      "loss": 27.4931,
+      "step": 80
+    },
+    {
+      "epoch": 0.31094049904030713,
+      "grad_norm": 18.14622688293457,
+      "learning_rate": 4.764683556008418e-05,
+      "loss": 28.0506,
+      "step": 81
+    },
+    {
+      "epoch": 0.31477927063339733,
+      "grad_norm": 19.75128936767578,
+      "learning_rate": 4.758117998365322e-05,
+      "loss": 27.2963,
+      "step": 82
+    },
+    {
+      "epoch": 0.31861804222648754,
+      "grad_norm": 17.486196517944336,
+      "learning_rate": 4.751466755751594e-05,
+      "loss": 28.7996,
+      "step": 83
+    },
+    {
+      "epoch": 0.32245681381957775,
+      "grad_norm": 19.39826011657715,
+      "learning_rate": 4.7447300805506455e-05,
+      "loss": 27.6073,
+      "step": 84
+    },
+    {
+      "epoch": 0.32629558541266795,
+      "grad_norm": 17.352880477905273,
+      "learning_rate": 4.7379082283876566e-05,
+      "loss": 28.5087,
+      "step": 85
+    },
+    {
+      "epoch": 0.33013435700575816,
+      "grad_norm": 20.071483612060547,
+      "learning_rate": 4.7310014581198695e-05,
+      "loss": 27.1697,
+      "step": 86
+    },
+    {
+      "epoch": 0.33397312859884837,
+      "grad_norm": 19.04390525817871,
+      "learning_rate": 4.7240100318267746e-05,
+      "loss": 27.9563,
+      "step": 87
+    },
+    {
+      "epoch": 0.3378119001919386,
+      "grad_norm": 20.634225845336914,
+      "learning_rate": 4.716934214800155e-05,
+      "loss": 27.6816,
+      "step": 88
+    },
+    {
+      "epoch": 0.3416506717850288,
+      "grad_norm": 19.746788024902344,
+      "learning_rate": 4.70977427553403e-05,
+      "loss": 27.3921,
+      "step": 89
+    },
+    {
+      "epoch": 0.345489443378119,
+      "grad_norm": 19.04279899597168,
+      "learning_rate": 4.702530485714461e-05,
+      "loss": 27.2845,
+      "step": 90
+    },
+    {
+      "epoch": 0.3493282149712092,
+      "grad_norm": 18.288244247436523,
+      "learning_rate": 4.695203120209245e-05,
+      "loss": 28.8947,
+      "step": 91
+    },
+    {
+      "epoch": 0.3531669865642994,
+      "grad_norm": 18.553823471069336,
+      "learning_rate": 4.6877924570574817e-05,
+      "loss": 27.7966,
+      "step": 92
+    },
+    {
+      "epoch": 0.3570057581573896,
+      "grad_norm": 18.615053176879883,
+      "learning_rate": 4.6802987774590275e-05,
+      "loss": 27.8787,
+      "step": 93
+    },
+    {
+      "epoch": 0.36084452975047987,
+      "grad_norm": 18.30453109741211,
+      "learning_rate": 4.672722365763821e-05,
+      "loss": 29.0792,
+      "step": 94
+    },
+    {
+      "epoch": 0.3646833013435701,
+      "grad_norm": 18.134958267211914,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 29.07,
+      "step": 95
+    },
+    {
+      "epoch": 0.3685220729366603,
+      "grad_norm": 19.019006729125977,
+      "learning_rate": 4.6573224991684744e-05,
+      "loss": 27.708,
+      "step": 96
+    },
+    {
+      "epoch": 0.3723608445297505,
+      "grad_norm": 18.863723754882812,
+      "learning_rate": 4.649499628620931e-05,
+      "loss": 27.4551,
+      "step": 97
+    },
+    {
+      "epoch": 0.3761996161228407,
+      "grad_norm": 18.62997055053711,
+      "learning_rate": 4.641595194659657e-05,
+      "loss": 26.7616,
+      "step": 98
+    },
+    {
+      "epoch": 0.3800383877159309,
+      "grad_norm": 18.19691276550293,
+      "learning_rate": 4.63360949722079e-05,
+      "loss": 27.6041,
+      "step": 99
+    },
+    {
+      "epoch": 0.3838771593090211,
+      "grad_norm": 19.37999153137207,
+      "learning_rate": 4.625542839324036e-05,
+      "loss": 26.9613,
+      "step": 100
+    },
+    {
+      "epoch": 0.3877159309021113,
+      "grad_norm": 18.335630416870117,
+      "learning_rate": 4.617395527061168e-05,
+      "loss": 27.4261,
+      "step": 101
+    },
+    {
+      "epoch": 0.3915547024952015,
+      "grad_norm": 19.16864585876465,
+      "learning_rate": 4.6091678695844164e-05,
+      "loss": 28.8591,
+      "step": 102
+    },
+    {
+      "epoch": 0.39539347408829173,
+      "grad_norm": 20.256633758544922,
+      "learning_rate": 4.600860179094732e-05,
+      "loss": 26.8054,
+      "step": 103
+    },
+    {
+      "epoch": 0.39923224568138194,
+      "grad_norm": 18.64192008972168,
+      "learning_rate": 4.5924727708299445e-05,
+      "loss": 27.3249,
+      "step": 104
+    },
+    {
+      "epoch": 0.40307101727447214,
+      "grad_norm": 17.976713180541992,
+      "learning_rate": 4.584005963052799e-05,
+      "loss": 29.1977,
+      "step": 105
+    },
+    {
+      "epoch": 0.4069097888675624,
+      "grad_norm": 17.99713706970215,
+      "learning_rate": 4.575460077038877e-05,
+      "loss": 29.0127,
+      "step": 106
+    },
+    {
+      "epoch": 0.4107485604606526,
+      "grad_norm": 18.080854415893555,
+      "learning_rate": 4.5668354370644086e-05,
+      "loss": 29.716,
+      "step": 107
+    },
+    {
+      "epoch": 0.4145873320537428,
+      "grad_norm": 17.458669662475586,
+      "learning_rate": 4.558132370393968e-05,
+      "loss": 29.7465,
+      "step": 108
+    },
+    {
+      "epoch": 0.418426103646833,
+      "grad_norm": 18.444486618041992,
+      "learning_rate": 4.5493512072680536e-05,
+      "loss": 30.3556,
+      "step": 109
+    },
+    {
+      "epoch": 0.42226487523992323,
+      "grad_norm": 17.931936264038086,
+      "learning_rate": 4.540492280890555e-05,
+      "loss": 27.0296,
+      "step": 110
+    },
+    {
+      "epoch": 0.42610364683301344,
+      "grad_norm": 17.657825469970703,
+      "learning_rate": 4.5315559274161144e-05,
+      "loss": 28.3838,
+      "step": 111
+    },
+    {
+      "epoch": 0.42994241842610365,
+      "grad_norm": 17.2442626953125,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 26.963,
+      "step": 112
+    },
+    {
+      "epoch": 0.43378119001919385,
+      "grad_norm": 16.4385929107666,
+      "learning_rate": 4.5134522984720816e-05,
+      "loss": 28.0953,
+      "step": 113
+    },
+    {
+      "epoch": 0.43761996161228406,
+      "grad_norm": 16.927474975585938,
+      "learning_rate": 4.504285709950167e-05,
+      "loss": 29.0116,
+      "step": 114
+    },
+    {
+      "epoch": 0.44145873320537427,
+      "grad_norm": 18.508386611938477,
+      "learning_rate": 4.4950430682006e-05,
+      "loss": 27.5212,
+      "step": 115
+    },
+    {
+      "epoch": 0.44529750479846447,
+      "grad_norm": 17.00088882446289,
+      "learning_rate": 4.485724723938215e-05,
+      "loss": 27.2209,
+      "step": 116
+    },
+    {
+      "epoch": 0.4491362763915547,
+      "grad_norm": 17.35956573486328,
+      "learning_rate": 4.476331030750408e-05,
+      "loss": 28.9031,
+      "step": 117
+    },
+    {
+      "epoch": 0.45297504798464494,
+      "grad_norm": 17.835237503051758,
+      "learning_rate": 4.4668623450837085e-05,
+      "loss": 25.8466,
+      "step": 118
+    },
+    {
+      "epoch": 0.45681381957773515,
+      "grad_norm": 18.052587509155273,
+      "learning_rate": 4.457319026230257e-05,
+      "loss": 27.7288,
+      "step": 119
+    },
+    {
+      "epoch": 0.46065259117082535,
+      "grad_norm": 21.071945190429688,
+      "learning_rate": 4.447701436314176e-05,
+      "loss": 27.2769,
+      "step": 120
+    },
+    {
+      "epoch": 0.46449136276391556,
+      "grad_norm": 17.07927703857422,
+      "learning_rate": 4.4380099402778244e-05,
+      "loss": 27.3407,
+      "step": 121
+    },
+    {
+      "epoch": 0.46833013435700577,
+      "grad_norm": 17.430988311767578,
+      "learning_rate": 4.428244905867952e-05,
+      "loss": 27.7631,
+      "step": 122
+    },
+    {
+      "epoch": 0.472168905950096,
+      "grad_norm": 18.140281677246094,
+      "learning_rate": 4.418406703621743e-05,
+      "loss": 27.4634,
+      "step": 123
+    },
+    {
+      "epoch": 0.4760076775431862,
+      "grad_norm": 18.464765548706055,
+      "learning_rate": 4.408495706852758e-05,
+      "loss": 27.1883,
+      "step": 124
+    },
+    {
+      "epoch": 0.4798464491362764,
+      "grad_norm": 17.243370056152344,
+      "learning_rate": 4.398512291636768e-05,
+      "loss": 29.4247,
+      "step": 125
+    },
+    {
+      "epoch": 0.4836852207293666,
+      "grad_norm": 18.10504722595215,
+      "learning_rate": 4.3884568367974845e-05,
+      "loss": 27.3026,
+      "step": 126
+    },
+    {
+      "epoch": 0.4875239923224568,
+      "grad_norm": 18.39180564880371,
+      "learning_rate": 4.378329723892184e-05,
+      "loss": 28.0279,
+      "step": 127
+    },
+    {
+      "epoch": 0.491362763915547,
+      "grad_norm": 16.66558265686035,
+      "learning_rate": 4.3681313371972276e-05,
+      "loss": 27.5308,
+      "step": 128
+    },
+    {
+      "epoch": 0.4952015355086372,
+      "grad_norm": 16.756423950195312,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 28.4946,
+      "step": 129
+    },
+    {
+      "epoch": 0.4990403071017274,
+      "grad_norm": 17.056476593017578,
+      "learning_rate": 4.347522293051648e-05,
+      "loss": 27.8562,
+      "step": 130
+    },
+    {
+      "epoch": 0.4990403071017274,
+      "eval_loss": 1.7600558996200562,
+      "eval_runtime": 31.0188,
+      "eval_samples_per_second": 9.543,
+      "eval_steps_per_second": 4.771,
+      "step": 130
+    },
+    {
+      "epoch": 0.5028790786948176,
+      "grad_norm": 17.216785430908203,
+      "learning_rate": 4.337112417617439e-05,
+      "loss": 27.1427,
+      "step": 131
+    },
+    {
+      "epoch": 0.5067178502879078,
+      "grad_norm": 16.08450698852539,
+      "learning_rate": 4.3266328323967333e-05,
+      "loss": 27.4919,
+      "step": 132
+    },
+    {
+      "epoch": 0.510556621880998,
+      "grad_norm": 17.361270904541016,
+      "learning_rate": 4.3160839350405606e-05,
+      "loss": 26.1541,
+      "step": 133
+    },
+    {
+      "epoch": 0.5143953934740882,
+      "grad_norm": 17.303585052490234,
+      "learning_rate": 4.305466125830023e-05,
+      "loss": 26.0347,
+      "step": 134
+    },
+    {
+      "epoch": 0.5182341650671785,
+      "grad_norm": 17.440980911254883,
+      "learning_rate": 4.294779807661105e-05,
+      "loss": 27.2826,
+      "step": 135
+    },
+    {
+      "epoch": 0.5220729366602687,
+      "grad_norm": 19.435768127441406,
+      "learning_rate": 4.284025386029381e-05,
+      "loss": 27.5317,
+      "step": 136
+    },
+    {
+      "epoch": 0.525911708253359,
+      "grad_norm": 17.796663284301758,
+      "learning_rate": 4.273203269014634e-05,
+      "loss": 27.8947,
+      "step": 137
+    },
+    {
+      "epoch": 0.5297504798464492,
+      "grad_norm": 17.049524307250977,
+      "learning_rate": 4.2623138672653684e-05,
+      "loss": 29.3983,
+      "step": 138
+    },
+    {
+      "epoch": 0.5335892514395394,
+      "grad_norm": 17.124839782714844,
+      "learning_rate": 4.2513575939832275e-05,
+      "loss": 28.4112,
+      "step": 139
+    },
+    {
+      "epoch": 0.5374280230326296,
+      "grad_norm": 17.724750518798828,
+      "learning_rate": 4.2403348649073174e-05,
+      "loss": 29.1517,
+      "step": 140
+    },
+    {
+      "epoch": 0.5412667946257198,
+      "grad_norm": 17.679073333740234,
+      "learning_rate": 4.2292460982984255e-05,
+      "loss": 27.1786,
+      "step": 141
+    },
+    {
+      "epoch": 0.54510556621881,
+      "grad_norm": 18.939489364624023,
+      "learning_rate": 4.218091714923157e-05,
+      "loss": 28.6373,
+      "step": 142
+    },
+    {
+      "epoch": 0.5489443378119002,
+      "grad_norm": 17.122732162475586,
+      "learning_rate": 4.206872138037964e-05,
+      "loss": 27.252,
+      "step": 143
+    },
+    {
+      "epoch": 0.5527831094049904,
+      "grad_norm": 18.2526912689209,
+      "learning_rate": 4.1955877933730855e-05,
+      "loss": 29.9347,
+      "step": 144
+    },
+    {
+      "epoch": 0.5566218809980806,
+      "grad_norm": 18.54884147644043,
+      "learning_rate": 4.184239109116393e-05,
+      "loss": 27.988,
+      "step": 145
+    },
+    {
+      "epoch": 0.5604606525911708,
+      "grad_norm": 18.026559829711914,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 28.1473,
+      "step": 146
+    },
+    {
+      "epoch": 0.564299424184261,
+      "grad_norm": 17.47412109375,
+      "learning_rate": 4.161350446769645e-05,
+      "loss": 26.7597,
+      "step": 147
+    },
+    {
+      "epoch": 0.5681381957773513,
+      "grad_norm": 19.019777297973633,
+      "learning_rate": 4.149811337196807e-05,
+      "loss": 27.5097,
+      "step": 148
+    },
+    {
+      "epoch": 0.5719769673704415,
+      "grad_norm": 18.873889923095703,
+      "learning_rate": 4.1382096250336346e-05,
+      "loss": 26.3739,
+      "step": 149
+    },
+    {
+      "epoch": 0.5758157389635317,
+      "grad_norm": 17.524677276611328,
+      "learning_rate": 4.126545750510605e-05,
+      "loss": 26.7282,
+      "step": 150
+    },
+    {
+      "epoch": 0.5796545105566219,
+      "grad_norm": 17.283926010131836,
+      "learning_rate": 4.1148201562169685e-05,
+      "loss": 26.9749,
+      "step": 151
+    },
+    {
+      "epoch": 0.5834932821497121,
+      "grad_norm": 17.261751174926758,
+      "learning_rate": 4.103033287083946e-05,
+      "loss": 27.2926,
+      "step": 152
+    },
+    {
+      "epoch": 0.5873320537428023,
+      "grad_norm": 16.952129364013672,
+      "learning_rate": 4.0911855903678534e-05,
+      "loss": 29.1231,
+      "step": 153
+    },
+    {
+      "epoch": 0.5911708253358925,
+      "grad_norm": 16.523609161376953,
+      "learning_rate": 4.079277515633127e-05,
+      "loss": 27.9168,
+      "step": 154
+    },
+    {
+      "epoch": 0.5950095969289827,
+      "grad_norm": 17.648927688598633,
+      "learning_rate": 4.067309514735267e-05,
+      "loss": 26.9956,
+      "step": 155
+    },
+    {
+      "epoch": 0.5988483685220729,
+      "grad_norm": 18.750659942626953,
+      "learning_rate": 4.055282041803685e-05,
+      "loss": 27.5584,
+      "step": 156
+    },
+    {
+      "epoch": 0.6026871401151631,
+      "grad_norm": 17.183300018310547,
+      "learning_rate": 4.0431955532244827e-05,
+      "loss": 27.9265,
+      "step": 157
+    },
+    {
+      "epoch": 0.6065259117082533,
+      "grad_norm": 17.270681381225586,
+      "learning_rate": 4.031050507623125e-05,
+      "loss": 28.9735,
+      "step": 158
+    },
+    {
+      "epoch": 0.6103646833013435,
+      "grad_norm": 19.801315307617188,
+      "learning_rate": 4.0188473658470426e-05,
+      "loss": 26.7811,
+      "step": 159
+    },
+    {
+      "epoch": 0.6142034548944337,
+      "grad_norm": 16.823190689086914,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 26.9071,
+      "step": 160
+    },
+    {
+      "epoch": 0.6180422264875239,
+      "grad_norm": 17.074491500854492,
+      "learning_rate": 3.9942686481652344e-05,
+      "loss": 27.9241,
+      "step": 161
+    },
+    {
+      "epoch": 0.6218809980806143,
+      "grad_norm": 18.242040634155273,
+      "learning_rate": 3.981894004906388e-05,
+      "loss": 28.2823,
+      "step": 162
+    },
+    {
+      "epoch": 0.6257197696737045,
+      "grad_norm": 16.200469970703125,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 27.2651,
+      "step": 163
+    },
+    {
+      "epoch": 0.6295585412667947,
+      "grad_norm": 17.807695388793945,
+      "learning_rate": 3.9569764973329026e-05,
+      "loss": 28.572,
+      "step": 164
+    },
+    {
+      "epoch": 0.6333973128598849,
+      "grad_norm": 16.356901168823242,
+      "learning_rate": 3.9444345785206285e-05,
+      "loss": 27.4942,
+      "step": 165
+    },
+    {
+      "epoch": 0.6372360844529751,
+      "grad_norm": 18.459415435791016,
+      "learning_rate": 3.931837850201263e-05,
+      "loss": 27.4934,
+      "step": 166
+    },
+    {
+      "epoch": 0.6410748560460653,
+      "grad_norm": 18.079626083374023,
+      "learning_rate": 3.919186790361475e-05,
+      "loss": 28.0261,
+      "step": 167
+    },
+    {
+      "epoch": 0.6449136276391555,
+      "grad_norm": 18.058738708496094,
+      "learning_rate": 3.906481879049558e-05,
+      "loss": 27.2611,
+      "step": 168
+    },
+    {
+      "epoch": 0.6487523992322457,
+      "grad_norm": 17.553970336914062,
+      "learning_rate": 3.893723598357214e-05,
+      "loss": 27.5768,
+      "step": 169
+    },
+    {
+      "epoch": 0.6525911708253359,
+      "grad_norm": 18.69593620300293,
+      "learning_rate": 3.880912432401265e-05,
+      "loss": 27.5784,
+      "step": 170
+    },
+    {
+      "epoch": 0.6564299424184261,
+      "grad_norm": 17.491533279418945,
+      "learning_rate": 3.8680488673052784e-05,
+      "loss": 29.1586,
+      "step": 171
+    },
+    {
+      "epoch": 0.6602687140115163,
+      "grad_norm": 18.12783432006836,
+      "learning_rate": 3.855133391181124e-05,
+      "loss": 27.3099,
+      "step": 172
+    },
+    {
+      "epoch": 0.6641074856046065,
+      "grad_norm": 18.322479248046875,
+      "learning_rate": 3.842166494110451e-05,
+      "loss": 29.5131,
+      "step": 173
+    },
+    {
+      "epoch": 0.6679462571976967,
+      "grad_norm": 17.041065216064453,
+      "learning_rate": 3.82914866812609e-05,
+      "loss": 28.5525,
+      "step": 174
+    },
+    {
+      "epoch": 0.6717850287907869,
+      "grad_norm": 17.609098434448242,
+      "learning_rate": 3.81608040719339e-05,
+      "loss": 28.8543,
+      "step": 175
+    },
+    {
+      "epoch": 0.6756238003838771,
+      "grad_norm": 17.111724853515625,
+      "learning_rate": 3.802962207191463e-05,
+      "loss": 25.6639,
+      "step": 176
+    },
+    {
+      "epoch": 0.6794625719769674,
+      "grad_norm": 17.328916549682617,
+      "learning_rate": 3.789794565894378e-05,
+      "loss": 26.0536,
+      "step": 177
+    },
+    {
+      "epoch": 0.6833013435700576,
+      "grad_norm": 17.837627410888672,
+      "learning_rate": 3.7765779829522675e-05,
+      "loss": 27.5278,
+      "step": 178
+    },
+    {
+      "epoch": 0.6871401151631478,
+      "grad_norm": 15.394762992858887,
+      "learning_rate": 3.7633129598723704e-05,
+      "loss": 27.7244,
+      "step": 179
+    },
+    {
+      "epoch": 0.690978886756238,
+      "grad_norm": 19.647441864013672,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 25.729,
+      "step": 180
+    },
+    {
+      "epoch": 0.6948176583493282,
+      "grad_norm": 17.077699661254883,
+      "learning_rate": 3.7366396084994475e-05,
+      "loss": 26.2709,
+      "step": 181
+    },
+    {
+      "epoch": 0.6986564299424184,
+      "grad_norm": 16.858604431152344,
+      "learning_rate": 3.723232292334809e-05,
+      "loss": 27.8621,
+      "step": 182
+    },
+    {
+      "epoch": 0.7024952015355086,
+      "grad_norm": 17.455453872680664,
+      "learning_rate": 3.709778560250754e-05,
+      "loss": 27.0243,
+      "step": 183
+    },
+    {
+      "epoch": 0.7063339731285988,
+      "grad_norm": 16.5456600189209,
+      "learning_rate": 3.696278922753216e-05,
+      "loss": 27.6667,
+      "step": 184
+    },
+    {
+      "epoch": 0.710172744721689,
+      "grad_norm": 17.52065086364746,
+      "learning_rate": 3.6827338920900254e-05,
+      "loss": 27.4649,
+      "step": 185
+    },
+    {
+      "epoch": 0.7140115163147792,
+      "grad_norm": 15.55224323272705,
+      "learning_rate": 3.669143982231467e-05,
+      "loss": 26.4226,
+      "step": 186
+    },
+    {
+      "epoch": 0.7178502879078695,
+      "grad_norm": 16.189666748046875,
+      "learning_rate": 3.655509708850783e-05,
+      "loss": 26.3024,
+      "step": 187
+    },
+    {
+      "epoch": 0.7216890595009597,
+      "grad_norm": 17.70796775817871,
+      "learning_rate": 3.641831589304602e-05,
+      "loss": 27.1759,
+      "step": 188
+    },
+    {
+      "epoch": 0.72552783109405,
+      "grad_norm": 16.10495376586914,
+      "learning_rate": 3.628110142613308e-05,
+      "loss": 26.5754,
+      "step": 189
+    },
+    {
+      "epoch": 0.7293666026871402,
+      "grad_norm": 17.34556007385254,
+      "learning_rate": 3.6143458894413465e-05,
+      "loss": 27.8653,
+      "step": 190
+    },
+    {
+      "epoch": 0.7332053742802304,
+      "grad_norm": 18.321557998657227,
+      "learning_rate": 3.600539352077469e-05,
+      "loss": 27.7326,
+      "step": 191
+    },
+    {
+      "epoch": 0.7370441458733206,
+      "grad_norm": 15.874064445495605,
+      "learning_rate": 3.586691054414913e-05,
+      "loss": 26.683,
+      "step": 192
+    },
+    {
+      "epoch": 0.7408829174664108,
+      "grad_norm": 16.701417922973633,
+      "learning_rate": 3.572801521931522e-05,
+      "loss": 25.815,
+      "step": 193
+    },
+    {
+      "epoch": 0.744721689059501,
+      "grad_norm": 17.957345962524414,
+      "learning_rate": 3.558871281669811e-05,
+      "loss": 26.726,
+      "step": 194
+    },
+    {
+      "epoch": 0.7485604606525912,
+      "grad_norm": 17.00701141357422,
+      "learning_rate": 3.544900862216959e-05,
+      "loss": 26.8739,
+      "step": 195
+    },
+    {
+      "epoch": 0.7523992322456814,
+      "grad_norm": 19.22977638244629,
+      "learning_rate": 3.5308907936847594e-05,
+      "loss": 26.1091,
+      "step": 196
+    },
+    {
+      "epoch": 0.7562380038387716,
+      "grad_norm": 18.498205184936523,
+      "learning_rate": 3.516841607689501e-05,
+      "loss": 25.4755,
+      "step": 197
+    },
+    {
+      "epoch": 0.7600767754318618,
+      "grad_norm": 18.955081939697266,
+      "learning_rate": 3.502753837331797e-05,
+      "loss": 26.3684,
+      "step": 198
+    },
+    {
+      "epoch": 0.763915547024952,
+      "grad_norm": 18.34401512145996,
+      "learning_rate": 3.488628017176356e-05,
+      "loss": 28.767,
+      "step": 199
+    },
+    {
+      "epoch": 0.7677543186180422,
+      "grad_norm": 18.423044204711914,
+      "learning_rate": 3.474464683231698e-05,
+      "loss": 27.2117,
+      "step": 200
+    },
+    {
+      "epoch": 0.7715930902111324,
+      "grad_norm": 18.909847259521484,
+      "learning_rate": 3.460264372929815e-05,
+      "loss": 26.408,
+      "step": 201
+    },
+    {
+      "epoch": 0.7754318618042226,
+      "grad_norm": 16.31786346435547,
+      "learning_rate": 3.446027625105776e-05,
+      "loss": 26.7065,
+      "step": 202
+    },
+    {
+      "epoch": 0.7792706333973128,
+      "grad_norm": 18.030500411987305,
+      "learning_rate": 3.431754979977285e-05,
+      "loss": 27.028,
+      "step": 203
+    },
+    {
+      "epoch": 0.783109404990403,
+      "grad_norm": 16.70123863220215,
+      "learning_rate": 3.4174469791241806e-05,
+      "loss": 27.5544,
+      "step": 204
+    },
+    {
+      "epoch": 0.7869481765834933,
+      "grad_norm": 16.9814453125,
+      "learning_rate": 3.403104165467883e-05,
+      "loss": 27.5372,
+      "step": 205
+    },
+    {
+      "epoch": 0.7907869481765835,
+      "grad_norm": 17.28445053100586,
+      "learning_rate": 3.388727083250795e-05,
+      "loss": 27.4625,
+      "step": 206
+    },
+    {
+      "epoch": 0.7946257197696737,
+      "grad_norm": 17.412431716918945,
+      "learning_rate": 3.374316278015653e-05,
+      "loss": 27.897,
+      "step": 207
+    },
+    {
+      "epoch": 0.7984644913627639,
+      "grad_norm": 16.263408660888672,
+      "learning_rate": 3.3598722965848204e-05,
+      "loss": 27.2817,
+      "step": 208
+    },
+    {
+      "epoch": 0.8023032629558541,
+      "grad_norm": 16.9997615814209,
+      "learning_rate": 3.345395687039543e-05,
+      "loss": 26.4631,
+      "step": 209
+    },
+    {
+      "epoch": 0.8061420345489443,
+      "grad_norm": 17.816619873046875,
+      "learning_rate": 3.330886998699149e-05,
+      "loss": 25.6059,
+      "step": 210
+    },
+    {
+      "epoch": 0.8099808061420346,
+      "grad_norm": 17.235605239868164,
+      "learning_rate": 3.316346782100208e-05,
+      "loss": 27.4531,
+      "step": 211
+    },
+    {
+      "epoch": 0.8138195777351248,
+      "grad_norm": 15.711729049682617,
+      "learning_rate": 3.301775588975638e-05,
+      "loss": 27.0936,
+      "step": 212
+    },
+    {
+      "epoch": 0.817658349328215,
+      "grad_norm": 16.274784088134766,
+      "learning_rate": 3.28717397223377e-05,
+      "loss": 25.6661,
+      "step": 213
+    },
+    {
+      "epoch": 0.8214971209213052,
+      "grad_norm": 15.97848129272461,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 26.772,
+      "step": 214
+    },
+    {
+      "epoch": 0.8253358925143954,
+      "grad_norm": 16.191444396972656,
+      "learning_rate": 3.257881685282609e-05,
+      "loss": 25.8711,
+      "step": 215
+    },
+    {
+      "epoch": 0.8291746641074856,
+      "grad_norm": 16.814664840698242,
+      "learning_rate": 3.243192126578007e-05,
+      "loss": 25.5683,
+      "step": 216
+    },
+    {
+      "epoch": 0.8330134357005758,
+      "grad_norm": 15.929566383361816,
+      "learning_rate": 3.228474367223312e-05,
+      "loss": 27.5315,
+      "step": 217
+    },
+    {
+      "epoch": 0.836852207293666,
+      "grad_norm": 16.453189849853516,
+      "learning_rate": 3.2137289656883556e-05,
+      "loss": 27.1406,
+      "step": 218
+    },
+    {
+      "epoch": 0.8406909788867563,
+      "grad_norm": 15.205329895019531,
+      "learning_rate": 3.19895648149186e-05,
+      "loss": 26.2816,
+      "step": 219
+    },
+    {
+      "epoch": 0.8445297504798465,
+      "grad_norm": 16.378446578979492,
+      "learning_rate": 3.1841574751802076e-05,
+      "loss": 26.6438,
+      "step": 220
+    },
+    {
+      "epoch": 0.8483685220729367,
+      "grad_norm": 16.06751251220703,
+      "learning_rate": 3.16933250830617e-05,
+      "loss": 27.0177,
+      "step": 221
+    },
+    {
+      "epoch": 0.8522072936660269,
+      "grad_norm": 15.032289505004883,
+      "learning_rate": 3.1544821434076014e-05,
+      "loss": 27.5912,
+      "step": 222
+    },
+    {
+      "epoch": 0.8560460652591171,
+      "grad_norm": 16.624408721923828,
+      "learning_rate": 3.1396069439860894e-05,
+      "loss": 28.211,
+      "step": 223
+    },
+    {
+      "epoch": 0.8598848368522073,
+      "grad_norm": 17.585723876953125,
+      "learning_rate": 3.124707474485577e-05,
+      "loss": 26.8424,
+      "step": 224
+    },
+    {
+      "epoch": 0.8637236084452975,
+      "grad_norm": 15.791353225708008,
+      "learning_rate": 3.109784300270943e-05,
+      "loss": 26.7544,
+      "step": 225
+    },
+    {
+      "epoch": 0.8675623800383877,
+      "grad_norm": 16.265228271484375,
+      "learning_rate": 3.094837987606547e-05,
+      "loss": 26.9071,
+      "step": 226
+    },
+    {
+      "epoch": 0.8714011516314779,
+      "grad_norm": 15.219544410705566,
+      "learning_rate": 3.0798691036347453e-05,
+      "loss": 25.127,
+      "step": 227
+    },
+    {
+      "epoch": 0.8752399232245681,
+      "grad_norm": 16.0206241607666,
+      "learning_rate": 3.064878216354369e-05,
+      "loss": 27.3355,
+      "step": 228
+    },
+    {
+      "epoch": 0.8790786948176583,
+      "grad_norm": 15.717583656311035,
+      "learning_rate": 3.049865894599172e-05,
+      "loss": 27.7224,
+      "step": 229
+    },
+    {
+      "epoch": 0.8829174664107485,
+      "grad_norm": 16.433361053466797,
+      "learning_rate": 3.0348327080162435e-05,
+      "loss": 27.4405,
+      "step": 230
+    },
+    {
+      "epoch": 0.8867562380038387,
+      "grad_norm": 16.457277297973633,
+      "learning_rate": 3.0197792270443982e-05,
+      "loss": 26.5396,
+      "step": 231
+    },
+    {
+      "epoch": 0.8905950095969289,
+      "grad_norm": 15.61976146697998,
+      "learning_rate": 3.0047060228925256e-05,
+      "loss": 27.3457,
+      "step": 232
+    },
+    {
+      "epoch": 0.8944337811900192,
+      "grad_norm": 16.303308486938477,
+      "learning_rate": 2.9896136675179176e-05,
+      "loss": 26.2405,
+      "step": 233
+    },
+    {
+      "epoch": 0.8982725527831094,
+      "grad_norm": 15.62144660949707,
+      "learning_rate": 2.974502733604565e-05,
+      "loss": 26.1536,
+      "step": 234
+    },
+    {
+      "epoch": 0.9021113243761996,
+      "grad_norm": 16.30591583251953,
+      "learning_rate": 2.9593737945414264e-05,
+      "loss": 26.1949,
+      "step": 235
+    },
+    {
+      "epoch": 0.9059500959692899,
+      "grad_norm": 16.510095596313477,
+      "learning_rate": 2.9442274244006722e-05,
+      "loss": 26.6893,
+      "step": 236
+    },
+    {
+      "epoch": 0.9097888675623801,
+      "grad_norm": 16.378929138183594,
+      "learning_rate": 2.9290641979158993e-05,
+      "loss": 28.0321,
+      "step": 237
+    },
+    {
+      "epoch": 0.9136276391554703,
+      "grad_norm": 15.976604461669922,
+      "learning_rate": 2.913884690460325e-05,
+      "loss": 27.17,
+      "step": 238
+    },
+    {
+      "epoch": 0.9174664107485605,
+      "grad_norm": 16.334959030151367,
+      "learning_rate": 2.8986894780249524e-05,
+      "loss": 26.3522,
+      "step": 239
+    },
+    {
+      "epoch": 0.9213051823416507,
+      "grad_norm": 16.02887725830078,
+      "learning_rate": 2.8834791371967142e-05,
+      "loss": 28.4084,
+      "step": 240
+    },
+    {
+      "epoch": 0.9251439539347409,
+      "grad_norm": 17.058687210083008,
+      "learning_rate": 2.868254245136594e-05,
+      "loss": 26.801,
+      "step": 241
+    },
+    {
+      "epoch": 0.9289827255278311,
+      "grad_norm": 15.894112586975098,
+      "learning_rate": 2.8530153795577286e-05,
+      "loss": 25.7278,
+      "step": 242
+    },
+    {
+      "epoch": 0.9328214971209213,
+      "grad_norm": 16.269180297851562,
+      "learning_rate": 2.8377631187034825e-05,
+      "loss": 26.3214,
+      "step": 243
+    },
+    {
+      "epoch": 0.9366602687140115,
+      "grad_norm": 15.76980209350586,
+      "learning_rate": 2.8224980413255086e-05,
+      "loss": 27.0605,
+      "step": 244
+    },
+    {
+      "epoch": 0.9404990403071017,
+      "grad_norm": 15.396162986755371,
+      "learning_rate": 2.8072207266617855e-05,
+      "loss": 26.77,
+      "step": 245
+    },
+    {
+      "epoch": 0.944337811900192,
+      "grad_norm": 16.089946746826172,
+      "learning_rate": 2.7919317544146405e-05,
+      "loss": 26.3307,
+      "step": 246
+    },
+    {
+      "epoch": 0.9481765834932822,
+      "grad_norm": 15.087519645690918,
+      "learning_rate": 2.776631704728752e-05,
+      "loss": 25.4705,
+      "step": 247
+    },
+    {
+      "epoch": 0.9520153550863724,
+      "grad_norm": 16.0484619140625,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 25.8905,
+      "step": 248
+    },
+    {
+      "epoch": 0.9558541266794626,
+      "grad_norm": 16.0047607421875,
+      "learning_rate": 2.746000695699107e-05,
+      "loss": 26.0246,
+      "step": 249
+    },
+    {
+      "epoch": 0.9596928982725528,
+      "grad_norm": 16.781606674194336,
+      "learning_rate": 2.7306708986582553e-05,
+      "loss": 25.6385,
+      "step": 250
+    },
+    {
+      "epoch": 0.963531669865643,
+      "grad_norm": 15.778640747070312,
+      "learning_rate": 2.7153323487403655e-05,
+      "loss": 26.7195,
+      "step": 251
+    },
+    {
+      "epoch": 0.9673704414587332,
+      "grad_norm": 17.09006118774414,
+      "learning_rate": 2.6999856279713544e-05,
+      "loss": 25.475,
+      "step": 252
+    },
+    {
+      "epoch": 0.9712092130518234,
+      "grad_norm": 16.174684524536133,
+      "learning_rate": 2.6846313186871853e-05,
+      "loss": 24.9302,
+      "step": 253
+    },
+    {
+      "epoch": 0.9750479846449136,
+      "grad_norm": 15.83430290222168,
+      "learning_rate": 2.669270003511769e-05,
+      "loss": 25.4569,
+      "step": 254
+    },
+    {
+      "epoch": 0.9788867562380038,
+      "grad_norm": 16.559917449951172,
+      "learning_rate": 2.653902265334858e-05,
+      "loss": 26.9698,
+      "step": 255
+    },
+    {
+      "epoch": 0.982725527831094,
+      "grad_norm": 15.691744804382324,
+      "learning_rate": 2.638528687289925e-05,
+      "loss": 25.7697,
+      "step": 256
+    },
+    {
+      "epoch": 0.9865642994241842,
+      "grad_norm": 15.908937454223633,
+      "learning_rate": 2.6231498527320425e-05,
+      "loss": 26.0816,
+      "step": 257
+    },
+    {
+      "epoch": 0.9904030710172744,
+      "grad_norm": 15.256813049316406,
+      "learning_rate": 2.6077663452157397e-05,
+      "loss": 27.2372,
+      "step": 258
+    },
+    {
+      "epoch": 0.9942418426103646,
+      "grad_norm": 16.329204559326172,
+      "learning_rate": 2.592378748472863e-05,
+      "loss": 26.6932,
+      "step": 259
+    },
+    {
+      "epoch": 0.9980806142034548,
+      "grad_norm": 15.60101318359375,
+      "learning_rate": 2.5769876463904265e-05,
+      "loss": 26.632,
+      "step": 260
+    },
+    {
+      "epoch": 0.9980806142034548,
+      "eval_loss": 1.698987364768982,
+      "eval_runtime": 31.0703,
+      "eval_samples_per_second": 9.527,
+      "eval_steps_per_second": 4.763,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.983232498168945,
+      "learning_rate": 2.5615936229884557e-05,
+      "loss": 12.2146,
+      "step": 261
+    },
+    {
+      "epoch": 1.0038387715930903,
+      "grad_norm": 31.90011978149414,
+      "learning_rate": 2.5461972623978247e-05,
+      "loss": 20.352,
+      "step": 262
+    },
+    {
+      "epoch": 1.0076775431861804,
+      "grad_norm": 28.391979217529297,
+      "learning_rate": 2.530799148838096e-05,
+      "loss": 21.9385,
+      "step": 263
+    },
+    {
+      "epoch": 1.0115163147792707,
+      "grad_norm": 23.981868743896484,
+      "learning_rate": 2.5153998665953473e-05,
+      "loss": 21.5485,
+      "step": 264
+    },
+    {
+      "epoch": 1.0153550863723608,
+      "grad_norm": 35.79429244995117,
+      "learning_rate": 2.5e-05,
+      "loss": 21.8402,
+      "step": 265
+    },
+    {
+      "epoch": 1.0191938579654511,
+      "grad_norm": 38.60832214355469,
+      "learning_rate": 2.4846001334046537e-05,
+      "loss": 22.1631,
+      "step": 266
+    },
+    {
+      "epoch": 1.0230326295585412,
+      "grad_norm": 28.950275421142578,
+      "learning_rate": 2.4692008511619042e-05,
+      "loss": 22.083,
+      "step": 267
+    },
+    {
+      "epoch": 1.0268714011516316,
+      "grad_norm": 24.666053771972656,
+      "learning_rate": 2.453802737602176e-05,
+      "loss": 22.934,
+      "step": 268
+    },
+    {
+      "epoch": 1.0307101727447217,
+      "grad_norm": 27.369165420532227,
+      "learning_rate": 2.4384063770115455e-05,
+      "loss": 20.742,
+      "step": 269
+    },
+    {
+      "epoch": 1.034548944337812,
+      "grad_norm": 22.31073570251465,
+      "learning_rate": 2.4230123536095748e-05,
+      "loss": 20.5333,
+      "step": 270
+    },
+    {
+      "epoch": 1.038387715930902,
+      "grad_norm": 21.734153747558594,
+      "learning_rate": 2.4076212515271383e-05,
+      "loss": 20.3299,
+      "step": 271
+    },
+    {
+      "epoch": 1.0422264875239924,
+      "grad_norm": 22.82332992553711,
+      "learning_rate": 2.3922336547842616e-05,
+      "loss": 20.2011,
+      "step": 272
+    },
+    {
+      "epoch": 1.0460652591170825,
+      "grad_norm": 21.255210876464844,
+      "learning_rate": 2.376850147267958e-05,
+      "loss": 21.1856,
+      "step": 273
+    },
+    {
+      "epoch": 1.0499040307101728,
+      "grad_norm": 19.702167510986328,
+      "learning_rate": 2.361471312710075e-05,
+      "loss": 21.5977,
+      "step": 274
+    },
+    {
+      "epoch": 1.053742802303263,
+      "grad_norm": 19.20767593383789,
+      "learning_rate": 2.346097734665143e-05,
+      "loss": 20.1011,
+      "step": 275
+    },
+    {
+      "epoch": 1.0575815738963532,
+      "grad_norm": 21.382646560668945,
+      "learning_rate": 2.3307299964882315e-05,
+      "loss": 20.8318,
+      "step": 276
+    },
+    {
+      "epoch": 1.0614203454894433,
+      "grad_norm": 20.11638641357422,
+      "learning_rate": 2.3153686813128153e-05,
+      "loss": 23.0071,
+      "step": 277
+    },
+    {
+      "epoch": 1.0652591170825336,
+      "grad_norm": 17.689075469970703,
+      "learning_rate": 2.3000143720286462e-05,
+      "loss": 21.3526,
+      "step": 278
+    },
+    {
+      "epoch": 1.0690978886756237,
+      "grad_norm": 19.41102409362793,
+      "learning_rate": 2.2846676512596354e-05,
+      "loss": 20.1244,
+      "step": 279
+    },
+    {
+      "epoch": 1.072936660268714,
+      "grad_norm": 19.403839111328125,
+      "learning_rate": 2.2693291013417453e-05,
+      "loss": 21.4532,
+      "step": 280
+    },
+    {
+      "epoch": 1.0767754318618041,
+      "grad_norm": 17.783912658691406,
+      "learning_rate": 2.2539993043008937e-05,
+      "loss": 20.0096,
+      "step": 281
+    },
+    {
+      "epoch": 1.0806142034548945,
+      "grad_norm": 18.40188980102539,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 21.923,
+      "step": 282
+    },
+    {
+      "epoch": 1.0844529750479845,
+      "grad_norm": 16.70290756225586,
+      "learning_rate": 2.2233682952712485e-05,
+      "loss": 22.0604,
+      "step": 283
+    },
+    {
+      "epoch": 1.0882917466410749,
+      "grad_norm": 17.57340431213379,
+      "learning_rate": 2.2080682455853597e-05,
+      "loss": 20.0495,
+      "step": 284
+    },
+    {
+      "epoch": 1.092130518234165,
+      "grad_norm": 17.793813705444336,
+      "learning_rate": 2.192779273338215e-05,
+      "loss": 19.6591,
+      "step": 285
+    },
+    {
+      "epoch": 1.0959692898272553,
+      "grad_norm": 17.183975219726562,
+      "learning_rate": 2.1775019586744923e-05,
+      "loss": 21.4261,
+      "step": 286
+    },
+    {
+      "epoch": 1.0998080614203456,
+      "grad_norm": 17.502321243286133,
+      "learning_rate": 2.162236881296518e-05,
+      "loss": 20.4338,
+      "step": 287
+    },
+    {
+      "epoch": 1.1036468330134357,
+      "grad_norm": 16.18671226501465,
+      "learning_rate": 2.1469846204422723e-05,
+      "loss": 20.8599,
+      "step": 288
+    },
+    {
+      "epoch": 1.107485604606526,
+      "grad_norm": 16.251554489135742,
+      "learning_rate": 2.1317457548634058e-05,
+      "loss": 21.8091,
+      "step": 289
+    },
+    {
+      "epoch": 1.111324376199616,
+      "grad_norm": 16.855628967285156,
+      "learning_rate": 2.116520862803286e-05,
+      "loss": 22.1352,
+      "step": 290
+    },
+    {
+      "epoch": 1.1151631477927064,
+      "grad_norm": 17.795156478881836,
+      "learning_rate": 2.1013105219750478e-05,
+      "loss": 21.5766,
+      "step": 291
+    },
+    {
+      "epoch": 1.1190019193857965,
+      "grad_norm": 17.897003173828125,
+      "learning_rate": 2.0861153095396748e-05,
+      "loss": 22.034,
+      "step": 292
+    },
+    {
+      "epoch": 1.1228406909788868,
+      "grad_norm": 17.152738571166992,
+      "learning_rate": 2.070935802084101e-05,
+      "loss": 21.4751,
+      "step": 293
+    },
+    {
+      "epoch": 1.126679462571977,
+      "grad_norm": 18.294397354125977,
+      "learning_rate": 2.0557725755993283e-05,
+      "loss": 21.8068,
+      "step": 294
+    },
+    {
+      "epoch": 1.1305182341650672,
+      "grad_norm": 16.99103355407715,
+      "learning_rate": 2.0406262054585738e-05,
+      "loss": 20.2328,
+      "step": 295
+    },
+    {
+      "epoch": 1.1343570057581573,
+      "grad_norm": 17.327777862548828,
+      "learning_rate": 2.0254972663954357e-05,
+      "loss": 21.6014,
+      "step": 296
+    },
+    {
+      "epoch": 1.1381957773512477,
+      "grad_norm": 16.88957405090332,
+      "learning_rate": 2.0103863324820833e-05,
+      "loss": 20.027,
+      "step": 297
+    },
+    {
+      "epoch": 1.1420345489443378,
+      "grad_norm": 17.30256462097168,
+      "learning_rate": 1.995293977107475e-05,
+      "loss": 21.1921,
+      "step": 298
+    },
+    {
+      "epoch": 1.145873320537428,
+      "grad_norm": 16.07200050354004,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 21.384,
+      "step": 299
+    },
+    {
+      "epoch": 1.1497120921305182,
+      "grad_norm": 16.85907745361328,
+      "learning_rate": 1.965167291983757e-05,
+      "loss": 21.8715,
+      "step": 300
+    },
+    {
+      "epoch": 1.1535508637236085,
+      "grad_norm": 17.825361251831055,
+      "learning_rate": 1.9501341054008292e-05,
+      "loss": 21.3469,
+      "step": 301
+    },
+    {
+      "epoch": 1.1573896353166986,
+      "grad_norm": 17.06654930114746,
+      "learning_rate": 1.9351217836456313e-05,
+      "loss": 21.4779,
+      "step": 302
+    },
+    {
+      "epoch": 1.161228406909789,
+      "grad_norm": 17.776653289794922,
+      "learning_rate": 1.9201308963652552e-05,
+      "loss": 19.489,
+      "step": 303
+    },
+    {
+      "epoch": 1.165067178502879,
+      "grad_norm": 16.5079402923584,
+      "learning_rate": 1.9051620123934537e-05,
+      "loss": 20.2179,
+      "step": 304
+    },
+    {
+      "epoch": 1.1689059500959693,
+      "grad_norm": 18.33095932006836,
+      "learning_rate": 1.890215699729057e-05,
+      "loss": 20.6006,
+      "step": 305
+    },
+    {
+      "epoch": 1.1727447216890594,
+      "grad_norm": 16.471492767333984,
+      "learning_rate": 1.8752925255144226e-05,
+      "loss": 20.8791,
+      "step": 306
+    },
+    {
+      "epoch": 1.1765834932821497,
+      "grad_norm": 16.422468185424805,
+      "learning_rate": 1.860393056013911e-05,
+      "loss": 20.9214,
+      "step": 307
+    },
+    {
+      "epoch": 1.18042226487524,
+      "grad_norm": 16.32746696472168,
+      "learning_rate": 1.8455178565923992e-05,
+      "loss": 18.8008,
+      "step": 308
+    },
+    {
+      "epoch": 1.1842610364683301,
+      "grad_norm": 15.671878814697266,
+      "learning_rate": 1.8306674916938303e-05,
+      "loss": 21.7142,
+      "step": 309
+    },
+    {
+      "epoch": 1.1880998080614202,
+      "grad_norm": 17.514930725097656,
+      "learning_rate": 1.815842524819793e-05,
+      "loss": 20.0245,
+      "step": 310
+    },
+    {
+      "epoch": 1.1919385796545106,
+      "grad_norm": 17.478960037231445,
+      "learning_rate": 1.8010435185081404e-05,
+      "loss": 20.6899,
+      "step": 311
+    },
+    {
+      "epoch": 1.1957773512476009,
+      "grad_norm": 17.39609718322754,
+      "learning_rate": 1.786271034311645e-05,
+      "loss": 22.0616,
+      "step": 312
+    },
+    {
+      "epoch": 1.199616122840691,
+      "grad_norm": 17.008588790893555,
+      "learning_rate": 1.7715256327766886e-05,
+      "loss": 20.1968,
+      "step": 313
+    },
+    {
+      "epoch": 1.2034548944337813,
+      "grad_norm": 18.373451232910156,
+      "learning_rate": 1.7568078734219934e-05,
+      "loss": 21.7361,
+      "step": 314
+    },
+    {
+      "epoch": 1.2072936660268714,
+      "grad_norm": 17.162620544433594,
+      "learning_rate": 1.7421183147173915e-05,
+      "loss": 20.7115,
+      "step": 315
+    },
+    {
+      "epoch": 1.2111324376199617,
+      "grad_norm": 17.564990997314453,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 20.3664,
+      "step": 316
+    },
+    {
+      "epoch": 1.2149712092130518,
+      "grad_norm": 16.083980560302734,
+      "learning_rate": 1.7128260277662307e-05,
+      "loss": 21.2208,
+      "step": 317
+    },
+    {
+      "epoch": 1.2188099808061421,
+      "grad_norm": 16.320255279541016,
+      "learning_rate": 1.6982244110243627e-05,
+      "loss": 19.6076,
+      "step": 318
+    },
+    {
+      "epoch": 1.2226487523992322,
+      "grad_norm": 16.825092315673828,
+      "learning_rate": 1.683653217899792e-05,
+      "loss": 22.2103,
+      "step": 319
+    },
+    {
+      "epoch": 1.2264875239923225,
+      "grad_norm": 16.72588539123535,
+      "learning_rate": 1.6691130013008514e-05,
+      "loss": 20.7865,
+      "step": 320
+    },
+    {
+      "epoch": 1.2303262955854126,
+      "grad_norm": 16.987138748168945,
+      "learning_rate": 1.654604312960457e-05,
+      "loss": 20.3091,
+      "step": 321
+    },
+    {
+      "epoch": 1.234165067178503,
+      "grad_norm": 17.015310287475586,
+      "learning_rate": 1.6401277034151798e-05,
+      "loss": 22.1052,
+      "step": 322
+    },
+    {
+      "epoch": 1.238003838771593,
+      "grad_norm": 18.03606605529785,
+      "learning_rate": 1.6256837219843472e-05,
+      "loss": 21.0887,
+      "step": 323
+    },
+    {
+      "epoch": 1.2418426103646834,
+      "grad_norm": 18.330631256103516,
+      "learning_rate": 1.611272916749205e-05,
+      "loss": 19.8342,
+      "step": 324
+    },
+    {
+      "epoch": 1.2456813819577734,
+      "grad_norm": 17.45516586303711,
+      "learning_rate": 1.5968958345321178e-05,
+      "loss": 21.2693,
+      "step": 325
+    },
+    {
+      "epoch": 1.2495201535508638,
+      "grad_norm": 16.1998348236084,
+      "learning_rate": 1.58255302087582e-05,
+      "loss": 20.9778,
+      "step": 326
+    },
+    {
+      "epoch": 1.2533589251439539,
+      "grad_norm": 17.573469161987305,
+      "learning_rate": 1.568245020022715e-05,
+      "loss": 21.1408,
+      "step": 327
+    },
+    {
+      "epoch": 1.2571976967370442,
+      "grad_norm": 17.92475700378418,
+      "learning_rate": 1.5539723748942245e-05,
+      "loss": 20.7829,
+      "step": 328
+    },
+    {
+      "epoch": 1.2610364683301343,
+      "grad_norm": 17.939800262451172,
+      "learning_rate": 1.5397356270701856e-05,
+      "loss": 20.7192,
+      "step": 329
+    },
+    {
+      "epoch": 1.2648752399232246,
+      "grad_norm": 16.325746536254883,
+      "learning_rate": 1.5255353167683017e-05,
+      "loss": 20.8419,
+      "step": 330
+    },
+    {
+      "epoch": 1.2687140115163147,
+      "grad_norm": 16.557632446289062,
+      "learning_rate": 1.5113719828236438e-05,
+      "loss": 22.6103,
+      "step": 331
+    },
+    {
+      "epoch": 1.272552783109405,
+      "grad_norm": 22.712125778198242,
+      "learning_rate": 1.4972461626682033e-05,
+      "loss": 20.6929,
+      "step": 332
+    },
+    {
+      "epoch": 1.2763915547024953,
+      "grad_norm": 16.070537567138672,
+      "learning_rate": 1.4831583923104999e-05,
+      "loss": 20.8418,
+      "step": 333
+    },
+    {
+      "epoch": 1.2802303262955854,
+      "grad_norm": 16.767885208129883,
+      "learning_rate": 1.4691092063152417e-05,
+      "loss": 22.7305,
+      "step": 334
+    },
+    {
+      "epoch": 1.2840690978886755,
+      "grad_norm": 16.39026641845703,
+      "learning_rate": 1.4550991377830426e-05,
+      "loss": 22.0039,
+      "step": 335
+    },
+    {
+      "epoch": 1.2879078694817658,
+      "grad_norm": 16.63512420654297,
+      "learning_rate": 1.4411287183301902e-05,
+      "loss": 21.4299,
+      "step": 336
+    },
+    {
+      "epoch": 1.2917466410748562,
+      "grad_norm": 17.900527954101562,
+      "learning_rate": 1.4271984780684778e-05,
+      "loss": 22.4775,
+      "step": 337
+    },
+    {
+      "epoch": 1.2955854126679462,
+      "grad_norm": 17.05221939086914,
+      "learning_rate": 1.4133089455850879e-05,
+      "loss": 21.9468,
+      "step": 338
+    },
+    {
+      "epoch": 1.2994241842610363,
+      "grad_norm": 17.210445404052734,
+      "learning_rate": 1.399460647922532e-05,
+      "loss": 20.1815,
+      "step": 339
+    },
+    {
+      "epoch": 1.3032629558541267,
+      "grad_norm": 16.748929977416992,
+      "learning_rate": 1.3856541105586545e-05,
+      "loss": 22.235,
+      "step": 340
+    },
+    {
+      "epoch": 1.307101727447217,
+      "grad_norm": 15.610675811767578,
+      "learning_rate": 1.371889857386693e-05,
+      "loss": 20.9521,
+      "step": 341
+    },
+    {
+      "epoch": 1.310940499040307,
+      "grad_norm": 17.04247283935547,
+      "learning_rate": 1.3581684106953987e-05,
+      "loss": 20.1059,
+      "step": 342
+    },
+    {
+      "epoch": 1.3147792706333974,
+      "grad_norm": 16.33750343322754,
+      "learning_rate": 1.3444902911492174e-05,
+      "loss": 22.5783,
+      "step": 343
+    },
+    {
+      "epoch": 1.3186180422264875,
+      "grad_norm": 16.650222778320312,
+      "learning_rate": 1.3308560177685334e-05,
+      "loss": 20.9683,
+      "step": 344
+    },
+    {
+      "epoch": 1.3224568138195778,
+      "grad_norm": 16.820764541625977,
+      "learning_rate": 1.3172661079099752e-05,
+      "loss": 19.93,
+      "step": 345
+    },
+    {
+      "epoch": 1.326295585412668,
+      "grad_norm": 17.346710205078125,
+      "learning_rate": 1.303721077246784e-05,
+      "loss": 20.52,
+      "step": 346
+    },
+    {
+      "epoch": 1.3301343570057582,
+      "grad_norm": 17.263507843017578,
+      "learning_rate": 1.2902214397492462e-05,
+      "loss": 21.0038,
+      "step": 347
+    },
+    {
+      "epoch": 1.3339731285988483,
+      "grad_norm": 17.55599594116211,
+      "learning_rate": 1.2767677076651913e-05,
+      "loss": 20.0553,
+      "step": 348
+    },
+    {
+      "epoch": 1.3378119001919386,
+      "grad_norm": 16.44485092163086,
+      "learning_rate": 1.2633603915005534e-05,
+      "loss": 19.7822,
+      "step": 349
+    },
+    {
+      "epoch": 1.3416506717850287,
+      "grad_norm": 16.858556747436523,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 19.2506,
+      "step": 350
+    },
+    {
+      "epoch": 1.345489443378119,
+      "grad_norm": 16.211315155029297,
+      "learning_rate": 1.2366870401276304e-05,
+      "loss": 21.2656,
+      "step": 351
+    },
+    {
+      "epoch": 1.3493282149712091,
+      "grad_norm": 16.584392547607422,
+      "learning_rate": 1.223422017047733e-05,
+      "loss": 20.7353,
+      "step": 352
+    },
+    {
+      "epoch": 1.3531669865642995,
+      "grad_norm": 16.187578201293945,
+      "learning_rate": 1.210205434105622e-05,
+      "loss": 21.1905,
+      "step": 353
+    },
+    {
+      "epoch": 1.3570057581573896,
+      "grad_norm": 16.611042022705078,
+      "learning_rate": 1.1970377928085371e-05,
+      "loss": 21.2483,
+      "step": 354
+    },
+    {
+      "epoch": 1.3608445297504799,
+      "grad_norm": 16.303922653198242,
+      "learning_rate": 1.1839195928066102e-05,
+      "loss": 20.2743,
+      "step": 355
+    },
+    {
+      "epoch": 1.36468330134357,
+      "grad_norm": 16.44252586364746,
+      "learning_rate": 1.1708513318739095e-05,
+      "loss": 21.34,
+      "step": 356
+    },
+    {
+      "epoch": 1.3685220729366603,
+      "grad_norm": 16.870229721069336,
+      "learning_rate": 1.1578335058895498e-05,
+      "loss": 20.5273,
+      "step": 357
+    },
+    {
+      "epoch": 1.3723608445297506,
+      "grad_norm": 17.659400939941406,
+      "learning_rate": 1.1448666088188764e-05,
+      "loss": 19.7263,
+      "step": 358
+    },
+    {
+      "epoch": 1.3761996161228407,
+      "grad_norm": 16.4289493560791,
+      "learning_rate": 1.1319511326947222e-05,
+      "loss": 21.7212,
+      "step": 359
+    },
+    {
+      "epoch": 1.3800383877159308,
+      "grad_norm": 15.762267112731934,
+      "learning_rate": 1.1190875675987356e-05,
+      "loss": 20.5204,
+      "step": 360
+    },
+    {
+      "epoch": 1.383877159309021,
+      "grad_norm": 16.620811462402344,
+      "learning_rate": 1.1062764016427862e-05,
+      "loss": 20.9438,
+      "step": 361
+    },
+    {
+      "epoch": 1.3877159309021114,
+      "grad_norm": 15.502689361572266,
+      "learning_rate": 1.0935181209504422e-05,
+      "loss": 20.7568,
+      "step": 362
+    },
+    {
+      "epoch": 1.3915547024952015,
+      "grad_norm": 16.41027069091797,
+      "learning_rate": 1.0808132096385248e-05,
+      "loss": 20.323,
+      "step": 363
+    },
+    {
+      "epoch": 1.3953934740882916,
+      "grad_norm": 17.651681900024414,
+      "learning_rate": 1.068162149798737e-05,
+      "loss": 20.1112,
+      "step": 364
+    },
+    {
+      "epoch": 1.399232245681382,
+      "grad_norm": 17.555715560913086,
+      "learning_rate": 1.0555654214793722e-05,
+      "loss": 22.2747,
+      "step": 365
+    },
+    {
+      "epoch": 1.4030710172744723,
+      "grad_norm": 17.43577766418457,
+      "learning_rate": 1.0430235026670978e-05,
+      "loss": 21.3942,
+      "step": 366
+    },
+    {
+      "epoch": 1.4069097888675623,
+      "grad_norm": 16.61440658569336,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 22.5395,
+      "step": 367
+    },
+    {
+      "epoch": 1.4107485604606527,
+      "grad_norm": 15.602707862854004,
+      "learning_rate": 1.018105995093613e-05,
+      "loss": 21.2575,
+      "step": 368
+    },
+    {
+      "epoch": 1.4145873320537428,
+      "grad_norm": 17.061851501464844,
+      "learning_rate": 1.005731351834766e-05,
+      "loss": 21.1615,
+      "step": 369
+    },
+    {
+      "epoch": 1.418426103646833,
+      "grad_norm": 16.832231521606445,
+      "learning_rate": 9.934134090518593e-06,
+      "loss": 21.3402,
+      "step": 370
+    },
+    {
+      "epoch": 1.4222648752399232,
+      "grad_norm": 17.012224197387695,
+      "learning_rate": 9.811526341529582e-06,
+      "loss": 19.6323,
+      "step": 371
+    },
+    {
+      "epoch": 1.4261036468330135,
+      "grad_norm": 16.545629501342773,
+      "learning_rate": 9.689494923768755e-06,
+      "loss": 19.4946,
+      "step": 372
+    },
+    {
+      "epoch": 1.4299424184261036,
+      "grad_norm": 16.054431915283203,
+      "learning_rate": 9.568044467755181e-06,
+      "loss": 21.2497,
+      "step": 373
+    },
+    {
+      "epoch": 1.433781190019194,
+      "grad_norm": 16.18979835510254,
+      "learning_rate": 9.447179581963156e-06,
+      "loss": 22.5627,
+      "step": 374
+    },
+    {
+      "epoch": 1.437619961612284,
+      "grad_norm": 16.570592880249023,
+      "learning_rate": 9.326904852647344e-06,
+      "loss": 19.4798,
+      "step": 375
+    },
+    {
+      "epoch": 1.4414587332053743,
+      "grad_norm": 16.715749740600586,
+      "learning_rate": 9.207224843668732e-06,
+      "loss": 22.351,
+      "step": 376
+    },
+    {
+      "epoch": 1.4452975047984644,
+      "grad_norm": 16.769977569580078,
+      "learning_rate": 9.088144096321472e-06,
+      "loss": 21.9362,
+      "step": 377
+    },
+    {
+      "epoch": 1.4491362763915547,
+      "grad_norm": 17.325634002685547,
+      "learning_rate": 8.969667129160547e-06,
+      "loss": 21.8168,
+      "step": 378
+    },
+    {
+      "epoch": 1.452975047984645,
+      "grad_norm": 16.272539138793945,
+      "learning_rate": 8.851798437830323e-06,
+      "loss": 20.2932,
+      "step": 379
+    },
+    {
+      "epoch": 1.4568138195777351,
+      "grad_norm": 16.569541931152344,
+      "learning_rate": 8.734542494893955e-06,
+      "loss": 22.7741,
+      "step": 380
+    },
+    {
+      "epoch": 1.4606525911708252,
+      "grad_norm": 16.735231399536133,
+      "learning_rate": 8.617903749663666e-06,
+      "loss": 20.8389,
+      "step": 381
+    },
+    {
+      "epoch": 1.4644913627639156,
+      "grad_norm": 17.50290298461914,
+      "learning_rate": 8.50188662803194e-06,
+      "loss": 21.3456,
+      "step": 382
+    },
+    {
+      "epoch": 1.4683301343570059,
+      "grad_norm": 16.45136260986328,
+      "learning_rate": 8.386495532303556e-06,
+      "loss": 21.3918,
+      "step": 383
+    },
+    {
+      "epoch": 1.472168905950096,
+      "grad_norm": 16.945947647094727,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 21.3806,
+      "step": 384
+    },
+    {
+      "epoch": 1.476007677543186,
+      "grad_norm": 17.403200149536133,
+      "learning_rate": 8.15760890883607e-06,
+      "loss": 21.5741,
+      "step": 385
+    },
+    {
+      "epoch": 1.4798464491362764,
+      "grad_norm": 15.925960540771484,
+      "learning_rate": 8.044122066269149e-06,
+      "loss": 20.3568,
+      "step": 386
+    },
+    {
+      "epoch": 1.4836852207293667,
+      "grad_norm": 15.36002254486084,
+      "learning_rate": 7.931278619620364e-06,
+      "loss": 21.4072,
+      "step": 387
+    },
+    {
+      "epoch": 1.4875239923224568,
+      "grad_norm": 18.0460205078125,
+      "learning_rate": 7.819082850768434e-06,
+      "loss": 21.0651,
+      "step": 388
+    },
+    {
+      "epoch": 1.491362763915547,
+      "grad_norm": 16.68878746032715,
+      "learning_rate": 7.70753901701575e-06,
+      "loss": 19.6786,
+      "step": 389
+    },
+    {
+      "epoch": 1.4952015355086372,
+      "grad_norm": 16.785842895507812,
+      "learning_rate": 7.5966513509268365e-06,
+      "loss": 21.9675,
+      "step": 390
+    },
+    {
+      "epoch": 1.4952015355086372,
+      "eval_loss": 1.7116776704788208,
+      "eval_runtime": 31.0248,
+      "eval_samples_per_second": 9.541,
+      "eval_steps_per_second": 4.77,
+      "step": 390
+    },
+    {
+      "epoch": 1.4990403071017275,
+      "grad_norm": 16.459524154663086,
+      "learning_rate": 7.4864240601677265e-06,
+      "loss": 19.1034,
+      "step": 391
+    },
+    {
+      "epoch": 1.5028790786948176,
+      "grad_norm": 16.578235626220703,
+      "learning_rate": 7.3768613273463234e-06,
+      "loss": 20.6083,
+      "step": 392
+    },
+    {
+      "epoch": 1.5067178502879077,
+      "grad_norm": 15.791862487792969,
+      "learning_rate": 7.267967309853666e-06,
+      "loss": 20.8469,
+      "step": 393
+    },
+    {
+      "epoch": 1.510556621880998,
+      "grad_norm": 16.680150985717773,
+      "learning_rate": 7.159746139706194e-06,
+      "loss": 21.1103,
+      "step": 394
+    },
+    {
+      "epoch": 1.5143953934740884,
+      "grad_norm": 15.956221580505371,
+      "learning_rate": 7.0522019233889545e-06,
+      "loss": 21.1805,
+      "step": 395
+    },
+    {
+      "epoch": 1.5182341650671785,
+      "grad_norm": 16.348682403564453,
+      "learning_rate": 6.9453387416997695e-06,
+      "loss": 20.605,
+      "step": 396
+    },
+    {
+      "epoch": 1.5220729366602685,
+      "grad_norm": 16.562957763671875,
+      "learning_rate": 6.839160649594401e-06,
+      "loss": 21.1429,
+      "step": 397
+    },
+    {
+      "epoch": 1.5259117082533589,
+      "grad_norm": 15.684383392333984,
+      "learning_rate": 6.733671676032674e-06,
+      "loss": 23.0287,
+      "step": 398
+    },
+    {
+      "epoch": 1.5297504798464492,
+      "grad_norm": 16.632112503051758,
+      "learning_rate": 6.628875823825612e-06,
+      "loss": 20.5922,
+      "step": 399
+    },
+    {
+      "epoch": 1.5335892514395395,
+      "grad_norm": 15.957228660583496,
+      "learning_rate": 6.524777069483526e-06,
+      "loss": 20.5221,
+      "step": 400
+    },
+    {
+      "epoch": 1.5374280230326296,
+      "grad_norm": 16.59423828125,
+      "learning_rate": 6.421379363065142e-06,
+      "loss": 21.1484,
+      "step": 401
+    },
+    {
+      "epoch": 1.5412667946257197,
+      "grad_norm": 16.450971603393555,
+      "learning_rate": 6.318686628027723e-06,
+      "loss": 19.4515,
+      "step": 402
+    },
+    {
+      "epoch": 1.54510556621881,
+      "grad_norm": 15.815667152404785,
+      "learning_rate": 6.216702761078166e-06,
+      "loss": 20.9243,
+      "step": 403
+    },
+    {
+      "epoch": 1.5489443378119003,
+      "grad_norm": 16.43648338317871,
+      "learning_rate": 6.115431632025154e-06,
+      "loss": 21.8014,
+      "step": 404
+    },
+    {
+      "epoch": 1.5527831094049904,
+      "grad_norm": 15.677999496459961,
+      "learning_rate": 6.01487708363232e-06,
+      "loss": 20.509,
+      "step": 405
+    },
+    {
+      "epoch": 1.5566218809980805,
+      "grad_norm": 15.919227600097656,
+      "learning_rate": 5.915042931472425e-06,
+      "loss": 21.2447,
+      "step": 406
+    },
+    {
+      "epoch": 1.5604606525911708,
+      "grad_norm": 15.848505973815918,
+      "learning_rate": 5.8159329637825745e-06,
+      "loss": 21.4095,
+      "step": 407
+    },
+    {
+      "epoch": 1.5642994241842612,
+      "grad_norm": 15.660775184631348,
+      "learning_rate": 5.717550941320482e-06,
+      "loss": 21.0583,
+      "step": 408
+    },
+    {
+      "epoch": 1.5681381957773513,
+      "grad_norm": 16.026033401489258,
+      "learning_rate": 5.619900597221753e-06,
+      "loss": 21.2968,
+      "step": 409
+    },
+    {
+      "epoch": 1.5719769673704413,
+      "grad_norm": 16.016826629638672,
+      "learning_rate": 5.522985636858239e-06,
+      "loss": 20.5098,
+      "step": 410
+    },
+    {
+      "epoch": 1.5758157389635317,
+      "grad_norm": 16.44532012939453,
+      "learning_rate": 5.42680973769743e-06,
+      "loss": 20.4221,
+      "step": 411
+    },
+    {
+      "epoch": 1.579654510556622,
+      "grad_norm": 16.122182846069336,
+      "learning_rate": 5.33137654916292e-06,
+      "loss": 20.8718,
+      "step": 412
+    },
+    {
+      "epoch": 1.583493282149712,
+      "grad_norm": 16.150543212890625,
+      "learning_rate": 5.236689692495916e-06,
+      "loss": 20.9968,
+      "step": 413
+    },
+    {
+      "epoch": 1.5873320537428022,
+      "grad_norm": 17.00517463684082,
+      "learning_rate": 5.14275276061785e-06,
+      "loss": 21.4716,
+      "step": 414
+    },
+    {
+      "epoch": 1.5911708253358925,
+      "grad_norm": 16.143770217895508,
+      "learning_rate": 5.049569317994013e-06,
+      "loss": 19.5914,
+      "step": 415
+    },
+    {
+      "epoch": 1.5950095969289828,
+      "grad_norm": 15.659564018249512,
+      "learning_rate": 4.957142900498335e-06,
+      "loss": 22.1265,
+      "step": 416
+    },
+    {
+      "epoch": 1.598848368522073,
+      "grad_norm": 15.749252319335938,
+      "learning_rate": 4.865477015279185e-06,
+      "loss": 20.5613,
+      "step": 417
+    },
+    {
+      "epoch": 1.602687140115163,
+      "grad_norm": 16.31047248840332,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 23.077,
+      "step": 418
+    },
+    {
+      "epoch": 1.6065259117082533,
+      "grad_norm": 15.302318572998047,
+      "learning_rate": 4.684440725838862e-06,
+      "loss": 21.2777,
+      "step": 419
+    },
+    {
+      "epoch": 1.6103646833013436,
+      "grad_norm": 15.675249099731445,
+      "learning_rate": 4.5950771910944605e-06,
+      "loss": 21.9063,
+      "step": 420
+    },
+    {
+      "epoch": 1.6142034548944337,
+      "grad_norm": 16.395877838134766,
+      "learning_rate": 4.5064879273194745e-06,
+      "loss": 22.1439,
+      "step": 421
+    },
+    {
+      "epoch": 1.6180422264875238,
+      "grad_norm": 16.09247398376465,
+      "learning_rate": 4.4186762960603224e-06,
+      "loss": 23.4098,
+      "step": 422
+    },
+    {
+      "epoch": 1.6218809980806141,
+      "grad_norm": 16.875818252563477,
+      "learning_rate": 4.331645629355915e-06,
+      "loss": 19.9787,
+      "step": 423
+    },
+    {
+      "epoch": 1.6257197696737045,
+      "grad_norm": 15.509851455688477,
+      "learning_rate": 4.245399229611238e-06,
+      "loss": 20.8531,
+      "step": 424
+    },
+    {
+      "epoch": 1.6295585412667948,
+      "grad_norm": 15.853813171386719,
+      "learning_rate": 4.159940369472015e-06,
+      "loss": 21.1502,
+      "step": 425
+    },
+    {
+      "epoch": 1.6333973128598849,
+      "grad_norm": 16.189851760864258,
+      "learning_rate": 4.075272291700557e-06,
+      "loss": 21.4833,
+      "step": 426
+    },
+    {
+      "epoch": 1.637236084452975,
+      "grad_norm": 16.603588104248047,
+      "learning_rate": 3.991398209052686e-06,
+      "loss": 20.5711,
+      "step": 427
+    },
+    {
+      "epoch": 1.6410748560460653,
+      "grad_norm": 16.684690475463867,
+      "learning_rate": 3.908321304155846e-06,
+      "loss": 20.9092,
+      "step": 428
+    },
+    {
+      "epoch": 1.6449136276391556,
+      "grad_norm": 16.88503646850586,
+      "learning_rate": 3.826044729388326e-06,
+      "loss": 19.7428,
+      "step": 429
+    },
+    {
+      "epoch": 1.6487523992322457,
+      "grad_norm": 17.10723304748535,
+      "learning_rate": 3.7445716067596503e-06,
+      "loss": 20.6075,
+      "step": 430
+    },
+    {
+      "epoch": 1.6525911708253358,
+      "grad_norm": 15.53963565826416,
+      "learning_rate": 3.6639050277921057e-06,
+      "loss": 22.9,
+      "step": 431
+    },
+    {
+      "epoch": 1.6564299424184261,
+      "grad_norm": 15.606730461120605,
+      "learning_rate": 3.5840480534034355e-06,
+      "loss": 21.504,
+      "step": 432
+    },
+    {
+      "epoch": 1.6602687140115164,
+      "grad_norm": 16.915599822998047,
+      "learning_rate": 3.505003713790689e-06,
+      "loss": 21.3113,
+      "step": 433
+    },
+    {
+      "epoch": 1.6641074856046065,
+      "grad_norm": 16.729263305664062,
+      "learning_rate": 3.4267750083152584e-06,
+      "loss": 21.0463,
+      "step": 434
+    },
+    {
+      "epoch": 1.6679462571976966,
+      "grad_norm": 16.304168701171875,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 20.9805,
+      "step": 435
+    },
+    {
+      "epoch": 1.671785028790787,
+      "grad_norm": 16.270374298095703,
+      "learning_rate": 3.2727763423617913e-06,
+      "loss": 21.1003,
+      "step": 436
+    },
+    {
+      "epoch": 1.6756238003838773,
+      "grad_norm": 15.20581340789795,
+      "learning_rate": 3.197012225409729e-06,
+      "loss": 20.0619,
+      "step": 437
+    },
+    {
+      "epoch": 1.6794625719769674,
+      "grad_norm": 17.438676834106445,
+      "learning_rate": 3.1220754294251837e-06,
+      "loss": 19.7497,
+      "step": 438
+    },
+    {
+      "epoch": 1.6833013435700575,
+      "grad_norm": 17.613048553466797,
+      "learning_rate": 3.0479687979075523e-06,
+      "loss": 21.0865,
+      "step": 439
+    },
+    {
+      "epoch": 1.6871401151631478,
+      "grad_norm": 16.843353271484375,
+      "learning_rate": 2.974695142855388e-06,
+      "loss": 21.8551,
+      "step": 440
+    },
+    {
+      "epoch": 1.690978886756238,
+      "grad_norm": 16.841970443725586,
+      "learning_rate": 2.9022572446597007e-06,
+      "loss": 20.6149,
+      "step": 441
+    },
+    {
+      "epoch": 1.6948176583493282,
+      "grad_norm": 15.736058235168457,
+      "learning_rate": 2.8306578519984527e-06,
+      "loss": 19.9789,
+      "step": 442
+    },
+    {
+      "epoch": 1.6986564299424183,
+      "grad_norm": 17.377676010131836,
+      "learning_rate": 2.7598996817322613e-06,
+      "loss": 21.6122,
+      "step": 443
+    },
+    {
+      "epoch": 1.7024952015355086,
+      "grad_norm": 15.351333618164062,
+      "learning_rate": 2.6899854188013054e-06,
+      "loss": 21.8045,
+      "step": 444
+    },
+    {
+      "epoch": 1.706333973128599,
+      "grad_norm": 15.400979042053223,
+      "learning_rate": 2.6209177161234445e-06,
+      "loss": 21.6742,
+      "step": 445
+    },
+    {
+      "epoch": 1.710172744721689,
+      "grad_norm": 15.909041404724121,
+      "learning_rate": 2.552699194493549e-06,
+      "loss": 21.2103,
+      "step": 446
+    },
+    {
+      "epoch": 1.714011516314779,
+      "grad_norm": 16.288795471191406,
+      "learning_rate": 2.4853324424840674e-06,
+      "loss": 19.6584,
+      "step": 447
+    },
+    {
+      "epoch": 1.7178502879078694,
+      "grad_norm": 16.88001251220703,
+      "learning_rate": 2.418820016346779e-06,
+      "loss": 20.9527,
+      "step": 448
+    },
+    {
+      "epoch": 1.7216890595009597,
+      "grad_norm": 15.426772117614746,
+      "learning_rate": 2.3531644399158197e-06,
+      "loss": 22.1142,
+      "step": 449
+    },
+    {
+      "epoch": 1.72552783109405,
+      "grad_norm": 16.2529354095459,
+      "learning_rate": 2.2883682045119063e-06,
+      "loss": 20.6667,
+      "step": 450
+    },
+    {
+      "epoch": 1.7293666026871402,
+      "grad_norm": 22.660812377929688,
+      "learning_rate": 2.224433768847789e-06,
+      "loss": 21.2103,
+      "step": 451
+    },
+    {
+      "epoch": 1.7332053742802302,
+      "grad_norm": 16.202503204345703,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 20.0658,
+      "step": 452
+    },
+    {
+      "epoch": 1.7370441458733206,
+      "grad_norm": 15.147746086120605,
+      "learning_rate": 2.0991599679916624e-06,
+      "loss": 20.9152,
+      "step": 453
+    },
+    {
+      "epoch": 1.7408829174664109,
+      "grad_norm": 15.011345863342285,
+      "learning_rate": 2.0378253563519247e-06,
+      "loss": 20.4116,
+      "step": 454
+    },
+    {
+      "epoch": 1.744721689059501,
+      "grad_norm": 15.8588228225708,
+      "learning_rate": 1.977362051376158e-06,
+      "loss": 18.8413,
+      "step": 455
+    },
+    {
+      "epoch": 1.748560460652591,
+      "grad_norm": 16.016305923461914,
+      "learning_rate": 1.9177723473627646e-06,
+      "loss": 19.489,
+      "step": 456
+    },
+    {
+      "epoch": 1.7523992322456814,
+      "grad_norm": 15.62695026397705,
+      "learning_rate": 1.859058505461095e-06,
+      "loss": 20.4723,
+      "step": 457
+    },
+    {
+      "epoch": 1.7562380038387717,
+      "grad_norm": 15.519407272338867,
+      "learning_rate": 1.801222753585638e-06,
+      "loss": 22.4733,
+      "step": 458
+    },
+    {
+      "epoch": 1.7600767754318618,
+      "grad_norm": 15.624913215637207,
+      "learning_rate": 1.7442672863314968e-06,
+      "loss": 22.5163,
+      "step": 459
+    },
+    {
+      "epoch": 1.763915547024952,
+      "grad_norm": 16.19761085510254,
+      "learning_rate": 1.6881942648911076e-06,
+      "loss": 21.959,
+      "step": 460
+    },
+    {
+      "epoch": 1.7677543186180422,
+      "grad_norm": 15.693192481994629,
+      "learning_rate": 1.6330058169722384e-06,
+      "loss": 20.8804,
+      "step": 461
+    },
+    {
+      "epoch": 1.7715930902111325,
+      "grad_norm": 15.414134979248047,
+      "learning_rate": 1.578704036717238e-06,
+      "loss": 19.8119,
+      "step": 462
+    },
+    {
+      "epoch": 1.7754318618042226,
+      "grad_norm": 16.06474494934082,
+      "learning_rate": 1.5252909846235896e-06,
+      "loss": 21.2434,
+      "step": 463
+    },
+    {
+      "epoch": 1.7792706333973127,
+      "grad_norm": 16.06039810180664,
+      "learning_rate": 1.4727686874657143e-06,
+      "loss": 21.5852,
+      "step": 464
+    },
+    {
+      "epoch": 1.783109404990403,
+      "grad_norm": 17.113985061645508,
+      "learning_rate": 1.421139138218064e-06,
+      "loss": 21.6185,
+      "step": 465
+    },
+    {
+      "epoch": 1.7869481765834934,
+      "grad_norm": 15.716484069824219,
+      "learning_rate": 1.3704042959795132e-06,
+      "loss": 21.6163,
+      "step": 466
+    },
+    {
+      "epoch": 1.7907869481765835,
+      "grad_norm": 16.430994033813477,
+      "learning_rate": 1.3205660858989944e-06,
+      "loss": 22.8004,
+      "step": 467
+    },
+    {
+      "epoch": 1.7946257197696736,
+      "grad_norm": 16.834121704101562,
+      "learning_rate": 1.2716263991024713e-06,
+      "loss": 20.1899,
+      "step": 468
+    },
+    {
+      "epoch": 1.7984644913627639,
+      "grad_norm": 15.677217483520508,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 18.9967,
+      "step": 469
+    },
+    {
+      "epoch": 1.8023032629558542,
+      "grad_norm": 16.316518783569336,
+      "learning_rate": 1.1764499893210878e-06,
+      "loss": 21.6224,
+      "step": 470
+    },
+    {
+      "epoch": 1.8061420345489443,
+      "grad_norm": 15.550005912780762,
+      "learning_rate": 1.1302168778338922e-06,
+      "loss": 20.9617,
+      "step": 471
+    },
+    {
+      "epoch": 1.8099808061420346,
+      "grad_norm": 15.957982063293457,
+      "learning_rate": 1.0848895124889818e-06,
+      "loss": 20.4512,
+      "step": 472
+    },
+    {
+      "epoch": 1.8138195777351247,
+      "grad_norm": 16.459383010864258,
+      "learning_rate": 1.0404696132469444e-06,
+      "loss": 21.528,
+      "step": 473
+    },
+    {
+      "epoch": 1.817658349328215,
+      "grad_norm": 16.093690872192383,
+      "learning_rate": 9.969588656342982e-07,
+      "loss": 20.7164,
+      "step": 474
+    },
+    {
+      "epoch": 1.8214971209213053,
+      "grad_norm": 16.058801651000977,
+      "learning_rate": 9.54358920679524e-07,
+      "loss": 19.863,
+      "step": 475
+    },
+    {
+      "epoch": 1.8253358925143954,
+      "grad_norm": 16.003698348999023,
+      "learning_rate": 9.126713948504228e-07,
+      "loss": 20.8559,
+      "step": 476
+    },
+    {
+      "epoch": 1.8291746641074855,
+      "grad_norm": 16.547693252563477,
+      "learning_rate": 8.718978699927744e-07,
+      "loss": 22.0172,
+      "step": 477
+    },
+    {
+      "epoch": 1.8330134357005758,
+      "grad_norm": 15.8489408493042,
+      "learning_rate": 8.320398932703144e-07,
+      "loss": 21.21,
+      "step": 478
+    },
+    {
+      "epoch": 1.8368522072936662,
+      "grad_norm": 16.281145095825195,
+      "learning_rate": 7.930989771060299e-07,
+      "loss": 20.4811,
+      "step": 479
+    },
+    {
+      "epoch": 1.8406909788867563,
+      "grad_norm": 15.579625129699707,
+      "learning_rate": 7.550765991247654e-07,
+      "loss": 19.9756,
+      "step": 480
+    },
+    {
+      "epoch": 1.8445297504798464,
+      "grad_norm": 15.547847747802734,
+      "learning_rate": 7.179742020971519e-07,
+      "loss": 20.5781,
+      "step": 481
+    },
+    {
+      "epoch": 1.8483685220729367,
+      "grad_norm": 16.1280517578125,
+      "learning_rate": 6.817931938848803e-07,
+      "loss": 20.1387,
+      "step": 482
+    },
+    {
+      "epoch": 1.852207293666027,
+      "grad_norm": 16.432701110839844,
+      "learning_rate": 6.465349473872478e-07,
+      "loss": 23.4471,
+      "step": 483
+    },
+    {
+      "epoch": 1.856046065259117,
+      "grad_norm": 16.626161575317383,
+      "learning_rate": 6.122008004890851e-07,
+      "loss": 20.4011,
+      "step": 484
+    },
+    {
+      "epoch": 1.8598848368522072,
+      "grad_norm": 16.168102264404297,
+      "learning_rate": 5.78792056009983e-07,
+      "loss": 21.4412,
+      "step": 485
+    },
+    {
+      "epoch": 1.8637236084452975,
+      "grad_norm": 16.56131935119629,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 20.2194,
+      "step": 486
+    },
+    {
+      "epoch": 1.8675623800383878,
+      "grad_norm": 17.292823791503906,
+      "learning_rate": 5.147558099658529e-07,
+      "loss": 21.643,
+      "step": 487
+    },
+    {
+      "epoch": 1.871401151631478,
+      "grad_norm": 16.576915740966797,
+      "learning_rate": 4.841307382755566e-07,
+      "loss": 22.5503,
+      "step": 488
+    },
+    {
+      "epoch": 1.875239923224568,
+      "grad_norm": 15.804405212402344,
+      "learning_rate": 4.5443592866157846e-07,
+      "loss": 20.4958,
+      "step": 489
+    },
+    {
+      "epoch": 1.8790786948176583,
+      "grad_norm": 15.931843757629395,
+      "learning_rate": 4.256725079024554e-07,
+      "loss": 19.8143,
+      "step": 490
+    },
+    {
+      "epoch": 1.8829174664107486,
+      "grad_norm": 17.453289031982422,
+      "learning_rate": 3.978415674348895e-07,
+      "loss": 22.0656,
+      "step": 491
+    },
+    {
+      "epoch": 1.8867562380038387,
+      "grad_norm": 15.733434677124023,
+      "learning_rate": 3.709441633123367e-07,
+      "loss": 19.9285,
+      "step": 492
+    },
+    {
+      "epoch": 1.8905950095969288,
+      "grad_norm": 15.915714263916016,
+      "learning_rate": 3.4498131616493565e-07,
+      "loss": 20.6875,
+      "step": 493
+    },
+    {
+      "epoch": 1.8944337811900192,
+      "grad_norm": 15.583646774291992,
+      "learning_rate": 3.1995401116077516e-07,
+      "loss": 21.8348,
+      "step": 494
+    },
+    {
+      "epoch": 1.8982725527831095,
+      "grad_norm": 17.053115844726562,
+      "learning_rate": 2.958631979685156e-07,
+      "loss": 20.8289,
+      "step": 495
+    },
+    {
+      "epoch": 1.9021113243761996,
+      "grad_norm": 17.572505950927734,
+      "learning_rate": 2.7270979072135104e-07,
+      "loss": 20.5572,
+      "step": 496
+    },
+    {
+      "epoch": 1.9059500959692899,
+      "grad_norm": 15.979856491088867,
+      "learning_rate": 2.5049466798232614e-07,
+      "loss": 20.125,
+      "step": 497
+    },
+    {
+      "epoch": 1.90978886756238,
+      "grad_norm": 15.965109825134277,
+      "learning_rate": 2.2921867271099295e-07,
+      "loss": 21.0769,
+      "step": 498
+    },
+    {
+      "epoch": 1.9136276391554703,
+      "grad_norm": 16.205610275268555,
+      "learning_rate": 2.0888261223143135e-07,
+      "loss": 21.3394,
+      "step": 499
+    },
+    {
+      "epoch": 1.9174664107485606,
+      "grad_norm": 16.218839645385742,
+      "learning_rate": 1.8948725820160662e-07,
+      "loss": 21.4822,
+      "step": 500
+    },
+    {
+      "epoch": 1.9213051823416507,
+      "grad_norm": 15.393239974975586,
+      "learning_rate": 1.7103334658409577e-07,
+      "loss": 20.9145,
+      "step": 501
+    },
+    {
+      "epoch": 1.9251439539347408,
+      "grad_norm": 16.45865249633789,
+      "learning_rate": 1.5352157761815977e-07,
+      "loss": 20.0352,
+      "step": 502
+    },
+    {
+      "epoch": 1.9289827255278311,
+      "grad_norm": 16.02602767944336,
+      "learning_rate": 1.3695261579316777e-07,
+      "loss": 19.5627,
+      "step": 503
+    },
+    {
+      "epoch": 1.9328214971209214,
+      "grad_norm": 16.707592010498047,
+      "learning_rate": 1.2132708982338926e-07,
+      "loss": 21.6733,
+      "step": 504
+    },
+    {
+      "epoch": 1.9366602687140115,
+      "grad_norm": 15.346840858459473,
+      "learning_rate": 1.0664559262413831e-07,
+      "loss": 20.6038,
+      "step": 505
+    },
+    {
+      "epoch": 1.9404990403071016,
+      "grad_norm": 15.660294532775879,
+      "learning_rate": 9.290868128926377e-08,
+      "loss": 20.4834,
+      "step": 506
+    },
+    {
+      "epoch": 1.944337811900192,
+      "grad_norm": 16.100744247436523,
+      "learning_rate": 8.011687707002447e-08,
+      "loss": 21.3543,
+      "step": 507
+    },
+    {
+      "epoch": 1.9481765834932823,
+      "grad_norm": 16.333961486816406,
+      "learning_rate": 6.827066535529946e-08,
+      "loss": 19.4984,
+      "step": 508
+    },
+    {
+      "epoch": 1.9520153550863724,
+      "grad_norm": 16.721385955810547,
+      "learning_rate": 5.737049565317787e-08,
+      "loss": 20.7062,
+      "step": 509
+    },
+    {
+      "epoch": 1.9558541266794625,
+      "grad_norm": 15.953263282775879,
+      "learning_rate": 4.741678157389739e-08,
+      "loss": 21.8326,
+      "step": 510
+    },
+    {
+      "epoch": 1.9596928982725528,
+      "grad_norm": 16.059139251708984,
+      "learning_rate": 3.840990081415141e-08,
+      "loss": 20.5162,
+      "step": 511
+    },
+    {
+      "epoch": 1.963531669865643,
+      "grad_norm": 16.434776306152344,
+      "learning_rate": 3.0350195142753166e-08,
+      "loss": 21.5626,
+      "step": 512
+    },
+    {
+      "epoch": 1.9673704414587332,
+      "grad_norm": 16.480600357055664,
+      "learning_rate": 2.323797038767117e-08,
+      "loss": 21.3467,
+      "step": 513
+    },
+    {
+      "epoch": 1.9712092130518233,
+      "grad_norm": 15.328332901000977,
+      "learning_rate": 1.7073496424427348e-08,
+      "loss": 21.8149,
+      "step": 514
+    },
+    {
+      "epoch": 1.9750479846449136,
+      "grad_norm": 16.419599533081055,
+      "learning_rate": 1.1857007165852474e-08,
+      "loss": 21.2042,
+      "step": 515
+    },
+    {
+      "epoch": 1.978886756238004,
+      "grad_norm": 17.01874351501465,
+      "learning_rate": 7.588700553209926e-09,
+      "loss": 20.3651,
+      "step": 516
+    },
+    {
+      "epoch": 1.982725527831094,
+      "grad_norm": 16.0975284576416,
+      "learning_rate": 4.268738548682261e-09,
+      "loss": 20.8112,
+      "step": 517
+    },
+    {
+      "epoch": 1.986564299424184,
+      "grad_norm": 15.759478569030762,
+      "learning_rate": 1.8972471292344473e-09,
+      "loss": 21.6873,
+      "step": 518
+    },
+    {
+      "epoch": 1.9904030710172744,
+      "grad_norm": 15.517256736755371,
+      "learning_rate": 4.743162818288127e-10,
+      "loss": 22.6064,
+      "step": 519
+    },
+    {
+      "epoch": 1.9942418426103647,
+      "grad_norm": 16.582988739013672,
+      "learning_rate": 0.0,
+      "loss": 21.648,
+      "step": 520
+    },
+    {
+      "epoch": 1.9942418426103647,
+      "eval_loss": 1.710574746131897,
+      "eval_runtime": 31.6354,
+      "eval_samples_per_second": 9.357,
+      "eval_steps_per_second": 4.678,
+      "step": 520
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 260,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.987149504299532e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-520/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4731a0f3900663f201327e2936da7784afe97992472e1b32ebe4fea9e28dab
+size 6648