Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00223efab0d26506448b5fd217f1bebdd658227dee59c10abf83fd1271cc3c75
+size 4943178720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1500bf47a4bb0567f06f397c79467d3d7097ac6ac6c732fe11abf5bb8cdcbb
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a56c231d8801d62f0ccae7b8c0e8df8dd9a4094bd6db85e0c36de7b94e9d46
+size 4540532728

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483496960
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-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.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-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.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.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.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.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.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "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": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,3297 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9423076923076925,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 26.249136076838056,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.1102,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 26.110264576346324,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.0997,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 25.94374396489923,
+      "learning_rate": 1.5e-06,
+      "loss": 1.1239,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 22.37475129701464,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1059,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 16.25191401266457,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0405,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 22.679130338310745,
+      "learning_rate": 3e-06,
+      "loss": 1.0213,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 15.916959043580418,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0104,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 9.482985220910942,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9937,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.965472899289267,
+      "learning_rate": 4.5e-06,
+      "loss": 0.9693,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 12.298531856803667,
+      "learning_rate": 5e-06,
+      "loss": 0.962,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.569727331935135,
+      "learning_rate": 4.999941186489917e-06,
+      "loss": 0.9374,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.377638735854951,
+      "learning_rate": 4.999764748726891e-06,
+      "loss": 0.9315,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.601213320961148,
+      "learning_rate": 4.999470695012462e-06,
+      "loss": 0.9317,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.018739227425751,
+      "learning_rate": 4.999059039182093e-06,
+      "loss": 0.9246,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.719715824372754,
+      "learning_rate": 4.998529800604525e-06,
+      "loss": 0.9136,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.9341753543248505,
+      "learning_rate": 4.99788300418086e-06,
+      "loss": 0.9221,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.060460637107745,
+      "learning_rate": 4.997118680343392e-06,
+      "loss": 0.9021,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.576152525840241,
+      "learning_rate": 4.996236865054177e-06,
+      "loss": 0.8804,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.2384463037464157,
+      "learning_rate": 4.995237599803336e-06,
+      "loss": 0.8864,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.961735655562835,
+      "learning_rate": 4.994120931607106e-06,
+      "loss": 0.884,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.715236432103334,
+      "learning_rate": 4.992886913005628e-06,
+      "loss": 0.8803,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.526746110251263,
+      "learning_rate": 4.991535602060475e-06,
+      "loss": 0.8856,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.663980149991846,
+      "learning_rate": 4.9900670623519185e-06,
+      "loss": 0.8613,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.4521755603079787,
+      "learning_rate": 4.988481362975939e-06,
+      "loss": 0.8692,
+      "step": 24
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.414349491574281,
+      "learning_rate": 4.986778578540973e-06,
+      "loss": 0.8602,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.8508832900360477,
+      "learning_rate": 4.984958789164404e-06,
+      "loss": 0.8526,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.196516977267481,
+      "learning_rate": 4.983022080468794e-06,
+      "loss": 0.8416,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.6095238921057553,
+      "learning_rate": 4.980968543577849e-06,
+      "loss": 0.8477,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.2205063108737506,
+      "learning_rate": 4.978798275112142e-06,
+      "loss": 0.8502,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.453254154090838,
+      "learning_rate": 4.976511377184557e-06,
+      "loss": 0.8468,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.9249988861975766,
+      "learning_rate": 4.97410795739549e-06,
+      "loss": 0.8391,
+      "step": 31
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.462696000038617,
+      "learning_rate": 4.971588128827783e-06,
+      "loss": 0.8436,
+      "step": 32
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.587837288732032,
+      "learning_rate": 4.968952010041408e-06,
+      "loss": 0.8564,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.2433648029783635,
+      "learning_rate": 4.966199725067883e-06,
+      "loss": 0.8501,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.55480062205993,
+      "learning_rate": 4.96333140340444e-06,
+      "loss": 0.8474,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 3.430958497804354,
+      "learning_rate": 4.960347180007932e-06,
+      "loss": 0.8343,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.0559248054083428,
+      "learning_rate": 4.957247195288479e-06,
+      "loss": 0.8358,
+      "step": 37
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.2032433802521147,
+      "learning_rate": 4.9540315951028695e-06,
+      "loss": 0.8538,
+      "step": 38
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.757473867230571,
+      "learning_rate": 4.9507005307476894e-06,
+      "loss": 0.8488,
+      "step": 39
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.045305839090202,
+      "learning_rate": 4.947254158952209e-06,
+      "loss": 0.8463,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.9629285351308554,
+      "learning_rate": 4.943692641871005e-06,
+      "loss": 0.828,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.7499225905634037,
+      "learning_rate": 4.940016147076337e-06,
+      "loss": 0.835,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.606092501631258,
+      "learning_rate": 4.9362248475502515e-06,
+      "loss": 0.8269,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.674180949875197,
+      "learning_rate": 4.932318921676458e-06,
+      "loss": 0.8417,
+      "step": 44
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.7285602808097336,
+      "learning_rate": 4.928298553231924e-06,
+      "loss": 0.8142,
+      "step": 45
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.7015909165553387,
+      "learning_rate": 4.924163931378233e-06,
+      "loss": 0.8323,
+      "step": 46
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5415943230444498,
+      "learning_rate": 4.919915250652686e-06,
+      "loss": 0.8244,
+      "step": 47
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.776100967798618,
+      "learning_rate": 4.9155527109591435e-06,
+      "loss": 0.8516,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.711552634387251,
+      "learning_rate": 4.911076517558623e-06,
+      "loss": 0.8313,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.905341213972799,
+      "learning_rate": 4.906486881059641e-06,
+      "loss": 0.827,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6533492618702206,
+      "learning_rate": 4.901784017408303e-06,
+      "loss": 0.8298,
+      "step": 51
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.3477688431170414,
+      "learning_rate": 4.896968147878146e-06,
+      "loss": 0.8014,
+      "step": 52
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.8384104093830587,
+      "learning_rate": 4.892039499059721e-06,
+      "loss": 0.8116,
+      "step": 53
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.432850021289229,
+      "learning_rate": 4.886998302849938e-06,
+      "loss": 0.8156,
+      "step": 54
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.804790940572451,
+      "learning_rate": 4.881844796441153e-06,
+      "loss": 0.8159,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3348703819353926,
+      "learning_rate": 4.876579222310007e-06,
+      "loss": 0.8096,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.1901608706880134,
+      "learning_rate": 4.8712018282060165e-06,
+      "loss": 0.811,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.660868627279477,
+      "learning_rate": 4.86571286713992e-06,
+      "loss": 0.818,
+      "step": 58
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.7869506219362514,
+      "learning_rate": 4.860112597371772e-06,
+      "loss": 0.8267,
+      "step": 59
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.3781426665180727,
+      "learning_rate": 4.85440128239879e-06,
+      "loss": 0.8112,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.015345568347538,
+      "learning_rate": 4.8485791909429575e-06,
+      "loss": 0.8151,
+      "step": 61
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.4423049063633546,
+      "learning_rate": 4.842646596938383e-06,
+      "loss": 0.8282,
+      "step": 62
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.6311610579830345,
+      "learning_rate": 4.8366037795184086e-06,
+      "loss": 0.8224,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.2899705695712282,
+      "learning_rate": 4.830451023002477e-06,
+      "loss": 0.8249,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.734019031576332,
+      "learning_rate": 4.824188616882754e-06,
+      "loss": 0.8136,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.0962707496285153,
+      "learning_rate": 4.817816855810507e-06,
+      "loss": 0.8184,
+      "step": 66
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 2.9665475220491966,
+      "learning_rate": 4.811336039582244e-06,
+      "loss": 0.817,
+      "step": 67
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.3700279096809824,
+      "learning_rate": 4.804746473125605e-06,
+      "loss": 0.81,
+      "step": 68
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.027450051648286,
+      "learning_rate": 4.798048466485018e-06,
+      "loss": 0.8219,
+      "step": 69
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.752180087601986,
+      "learning_rate": 4.791242334807106e-06,
+      "loss": 0.8101,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.573031098084336,
+      "learning_rate": 4.784328398325866e-06,
+      "loss": 0.8099,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.7123062400387576,
+      "learning_rate": 4.7773069823475945e-06,
+      "loss": 0.8088,
+      "step": 72
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.474407154924412,
+      "learning_rate": 4.770178417235589e-06,
+      "loss": 0.8232,
+      "step": 73
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 2.4442790557938965,
+      "learning_rate": 4.762943038394597e-06,
+      "loss": 0.8051,
+      "step": 74
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.1553005222889583,
+      "learning_rate": 4.755601186255041e-06,
+      "loss": 0.825,
+      "step": 75
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.312089317706644,
+      "learning_rate": 4.7481532062569945e-06,
+      "loss": 0.8168,
+      "step": 76
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.2731409969922693,
+      "learning_rate": 4.7405994488339375e-06,
+      "loss": 0.8095,
+      "step": 77
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.444830999943097,
+      "learning_rate": 4.732940269396259e-06,
+      "loss": 0.8108,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.315315922207351,
+      "learning_rate": 4.725176028314541e-06,
+      "loss": 0.8072,
+      "step": 79
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.231139324893734,
+      "learning_rate": 4.7173070909026015e-06,
+      "loss": 0.8093,
+      "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.3706185711850956,
+      "learning_rate": 4.7093338274003035e-06,
+      "loss": 0.8011,
+      "step": 81
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.2002695782644905,
+      "learning_rate": 4.701256612956137e-06,
+      "loss": 0.8136,
+      "step": 82
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.704162588410486,
+      "learning_rate": 4.693075827609569e-06,
+      "loss": 0.8161,
+      "step": 83
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.9269420606373808,
+      "learning_rate": 4.684791856273161e-06,
+      "loss": 0.8023,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.4468707403860037,
+      "learning_rate": 4.676405088714458e-06,
+      "loss": 0.8019,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.07255184003701,
+      "learning_rate": 4.667915919537651e-06,
+      "loss": 0.8155,
+      "step": 86
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.2036583211359746,
+      "learning_rate": 4.6593247481650105e-06,
+      "loss": 0.8175,
+      "step": 87
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.8140377607105893,
+      "learning_rate": 4.65063197881809e-06,
+      "loss": 0.8047,
+      "step": 88
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.1515853560068243,
+      "learning_rate": 4.641838020498713e-06,
+      "loss": 0.8185,
+      "step": 89
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 2.422760543528869,
+      "learning_rate": 4.632943286969724e-06,
+      "loss": 0.8053,
+      "step": 90
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.0829660459092776,
+      "learning_rate": 4.6239481967355226e-06,
+      "loss": 0.8016,
+      "step": 91
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.1797861749114857,
+      "learning_rate": 4.614853173022374e-06,
+      "loss": 0.8068,
+      "step": 92
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.6076944835409135,
+      "learning_rate": 4.605658643758492e-06,
+      "loss": 0.8121,
+      "step": 93
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8970468662695665,
+      "learning_rate": 4.59636504155391e-06,
+      "loss": 0.8146,
+      "step": 94
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.195985971319255,
+      "learning_rate": 4.586972803680119e-06,
+      "loss": 0.7956,
+      "step": 95
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.7905344729119324,
+      "learning_rate": 4.577482372049503e-06,
+      "loss": 0.7953,
+      "step": 96
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.940825819357636,
+      "learning_rate": 4.567894193194538e-06,
+      "loss": 0.8047,
+      "step": 97
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.7851389603760988,
+      "learning_rate": 4.558208718246787e-06,
+      "loss": 0.8105,
+      "step": 98
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.4544053049998884,
+      "learning_rate": 4.548426402915674e-06,
+      "loss": 0.8007,
+      "step": 99
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.1082597379545165,
+      "learning_rate": 4.538547707467038e-06,
+      "loss": 0.805,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9122304736142002,
+      "learning_rate": 4.528573096701484e-06,
+      "loss": 0.8067,
+      "step": 101
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.990095091929317,
+      "learning_rate": 4.5185030399325085e-06,
+      "loss": 0.8025,
+      "step": 102
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.029120797101969,
+      "learning_rate": 4.508338010964419e-06,
+      "loss": 0.8051,
+      "step": 103
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.9232157433946324,
+      "learning_rate": 4.498078488070044e-06,
+      "loss": 0.8078,
+      "step": 104
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.026639315850326,
+      "learning_rate": 4.4877249539682235e-06,
+      "loss": 0.7957,
+      "step": 105
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.321397841878117,
+      "learning_rate": 4.477277895801105e-06,
+      "loss": 0.8039,
+      "step": 106
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.1058946605532656,
+      "learning_rate": 4.466737805111218e-06,
+      "loss": 0.7921,
+      "step": 107
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.9367272096486814,
+      "learning_rate": 4.456105177818345e-06,
+      "loss": 0.7922,
+      "step": 108
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 2.5699051489574605,
+      "learning_rate": 4.445380514196192e-06,
+      "loss": 0.7984,
+      "step": 109
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.0519065594178003,
+      "learning_rate": 4.434564318848851e-06,
+      "loss": 0.784,
+      "step": 110
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 2.809445653695483,
+      "learning_rate": 4.423657100687051e-06,
+      "loss": 0.7835,
+      "step": 111
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.170793808104346,
+      "learning_rate": 4.41265937290422e-06,
+      "loss": 0.8039,
+      "step": 112
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.612499453872831,
+      "learning_rate": 4.401571652952338e-06,
+      "loss": 0.8099,
+      "step": 113
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.1820432279807718,
+      "learning_rate": 4.390394462517589e-06,
+      "loss": 0.7929,
+      "step": 114
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.335653384387635,
+      "learning_rate": 4.379128327495813e-06,
+      "loss": 0.7999,
+      "step": 115
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.9923005143051236,
+      "learning_rate": 4.367773777967769e-06,
+      "loss": 0.8123,
+      "step": 116
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.1550829328561787,
+      "learning_rate": 4.3563313481741855e-06,
+      "loss": 0.7905,
+      "step": 117
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.8608335678809116,
+      "learning_rate": 4.344801576490631e-06,
+      "loss": 0.8051,
+      "step": 118
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 2.1245561127414923,
+      "learning_rate": 4.3331850054021806e-06,
+      "loss": 0.7979,
+      "step": 119
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 3.0733225632670127,
+      "learning_rate": 4.321482181477891e-06,
+      "loss": 0.7712,
+      "step": 120
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 3.2998040554493366,
+      "learning_rate": 4.309693655345084e-06,
+      "loss": 0.7523,
+      "step": 121
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 3.0325218749275624,
+      "learning_rate": 4.29781998166344e-06,
+      "loss": 0.7591,
+      "step": 122
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 3.696913587445061,
+      "learning_rate": 4.2858617190989e-06,
+      "loss": 0.7447,
+      "step": 123
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.852432566856283,
+      "learning_rate": 4.273819430297382e-06,
+      "loss": 0.7557,
+      "step": 124
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 4.684715882065128,
+      "learning_rate": 4.261693681858306e-06,
+      "loss": 0.7596,
+      "step": 125
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 3.5092399399988343,
+      "learning_rate": 4.2494850443079305e-06,
+      "loss": 0.7467,
+      "step": 126
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 3.851985488385657,
+      "learning_rate": 4.237194092072521e-06,
+      "loss": 0.7475,
+      "step": 127
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 3.328297635562109,
+      "learning_rate": 4.2248214034513114e-06,
+      "loss": 0.7442,
+      "step": 128
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.9102386032965373,
+      "learning_rate": 4.212367560589299e-06,
+      "loss": 0.7651,
+      "step": 129
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 3.06457511968988,
+      "learning_rate": 4.199833149449853e-06,
+      "loss": 0.7418,
+      "step": 130
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 3.2168853165359175,
+      "learning_rate": 4.187218759787148e-06,
+      "loss": 0.743,
+      "step": 131
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.787806998778304,
+      "learning_rate": 4.174524985118411e-06,
+      "loss": 0.7583,
+      "step": 132
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.9052093067187443,
+      "learning_rate": 4.161752422695995e-06,
+      "loss": 0.7657,
+      "step": 133
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 3.0182785590623173,
+      "learning_rate": 4.148901673479285e-06,
+      "loss": 0.7362,
+      "step": 134
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 3.344873463157497,
+      "learning_rate": 4.135973342106416e-06,
+      "loss": 0.7558,
+      "step": 135
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 2.859789074330451,
+      "learning_rate": 4.122968036865827e-06,
+      "loss": 0.7486,
+      "step": 136
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 3.228835212527119,
+      "learning_rate": 4.109886369667636e-06,
+      "loss": 0.7655,
+      "step": 137
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 2.731179147211052,
+      "learning_rate": 4.096728956014857e-06,
+      "loss": 0.7528,
+      "step": 138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 2.652548225590943,
+      "learning_rate": 4.083496414974434e-06,
+      "loss": 0.7448,
+      "step": 139
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 2.318475213880663,
+      "learning_rate": 4.070189369148117e-06,
+      "loss": 0.7577,
+      "step": 140
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 2.63738412652813,
+      "learning_rate": 4.056808444643163e-06,
+      "loss": 0.7475,
+      "step": 141
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 2.557947896210419,
+      "learning_rate": 4.043354271042884e-06,
+      "loss": 0.7368,
+      "step": 142
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.555902551567185,
+      "learning_rate": 4.02982748137702e-06,
+      "loss": 0.7434,
+      "step": 143
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 2.331216526916747,
+      "learning_rate": 4.0162287120919545e-06,
+      "loss": 0.7592,
+      "step": 144
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 2.298359286001758,
+      "learning_rate": 4.002558603020772e-06,
+      "loss": 0.7407,
+      "step": 145
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 2.2941501459555806,
+      "learning_rate": 3.988817797353149e-06,
+      "loss": 0.7534,
+      "step": 146
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 2.195437955425272,
+      "learning_rate": 3.975006941605099e-06,
+      "loss": 0.7501,
+      "step": 147
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.2354482392933583,
+      "learning_rate": 3.961126685588541e-06,
+      "loss": 0.7628,
+      "step": 148
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.271851901257072,
+      "learning_rate": 3.947177682380738e-06,
+      "loss": 0.7559,
+      "step": 149
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.06190688358819,
+      "learning_rate": 3.933160588293564e-06,
+      "loss": 0.7381,
+      "step": 150
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 2.1082422406253145,
+      "learning_rate": 3.9190760628426225e-06,
+      "loss": 0.761,
+      "step": 151
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.257445076263947,
+      "learning_rate": 3.904924768716216e-06,
+      "loss": 0.7339,
+      "step": 152
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 2.0575089260504065,
+      "learning_rate": 3.890707371744169e-06,
+      "loss": 0.7481,
+      "step": 153
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.2929887801738205,
+      "learning_rate": 3.8764245408664964e-06,
+      "loss": 0.7378,
+      "step": 154
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 2.0516588845869244,
+      "learning_rate": 3.862076948101934e-06,
+      "loss": 0.7565,
+      "step": 155
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 2.265288203536537,
+      "learning_rate": 3.847665268516314e-06,
+      "loss": 0.7489,
+      "step": 156
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.3008837342067174,
+      "learning_rate": 3.833190180190808e-06,
+      "loss": 0.7387,
+      "step": 157
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 2.303244798174658,
+      "learning_rate": 3.818652364190018e-06,
+      "loss": 0.7456,
+      "step": 158
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 2.266318666547602,
+      "learning_rate": 3.8040525045299337e-06,
+      "loss": 0.7574,
+      "step": 159
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 2.12834726687523,
+      "learning_rate": 3.7893912881457505e-06,
+      "loss": 0.7444,
+      "step": 160
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.3349048004783968,
+      "learning_rate": 3.7746694048595458e-06,
+      "loss": 0.7576,
+      "step": 161
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 2.3189890726535025,
+      "learning_rate": 3.759887547347825e-06,
+      "loss": 0.7661,
+      "step": 162
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 2.4796894123137703,
+      "learning_rate": 3.745046411108928e-06,
+      "loss": 0.75,
+      "step": 163
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 2.3870417794754446,
+      "learning_rate": 3.730146694430308e-06,
+      "loss": 0.7553,
+      "step": 164
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.0568742731615752,
+      "learning_rate": 3.7151890983556747e-06,
+      "loss": 0.7493,
+      "step": 165
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.4078734682098344,
+      "learning_rate": 3.700174326652011e-06,
+      "loss": 0.7413,
+      "step": 166
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 2.1293229041387853,
+      "learning_rate": 3.685103085776457e-06,
+      "loss": 0.7467,
+      "step": 167
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 2.117068360526989,
+      "learning_rate": 3.6699760848430753e-06,
+      "loss": 0.7396,
+      "step": 168
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.9883016666638709,
+      "learning_rate": 3.654794035589484e-06,
+      "loss": 0.7491,
+      "step": 169
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.2563683164117534,
+      "learning_rate": 3.6395576523433672e-06,
+      "loss": 0.7518,
+      "step": 170
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.3064779080171744,
+      "learning_rate": 3.6242676519888693e-06,
+      "loss": 0.7565,
+      "step": 171
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 1.9222922356745977,
+      "learning_rate": 3.608924753932862e-06,
+      "loss": 0.7353,
+      "step": 172
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 2.2598801622305547,
+      "learning_rate": 3.593529680071097e-06,
+      "loss": 0.7466,
+      "step": 173
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 2.0105134715596082,
+      "learning_rate": 3.578083154754241e-06,
+      "loss": 0.7427,
+      "step": 174
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.482181765049527,
+      "learning_rate": 3.5625859047537904e-06,
+      "loss": 0.7531,
+      "step": 175
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.989275137459208,
+      "learning_rate": 3.547038659227881e-06,
+      "loss": 0.7458,
+      "step": 176
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 2.375903859138452,
+      "learning_rate": 3.5314421496869777e-06,
+      "loss": 0.7497,
+      "step": 177
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.818443971455023,
+      "learning_rate": 3.515797109959458e-06,
+      "loss": 0.7416,
+      "step": 178
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 2.1798526485495127,
+      "learning_rate": 3.500104276157083e-06,
+      "loss": 0.7477,
+      "step": 179
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.8954837732640064,
+      "learning_rate": 3.484364386640365e-06,
+      "loss": 0.7511,
+      "step": 180
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 2.1614293408819023,
+      "learning_rate": 3.4685781819838233e-06,
+      "loss": 0.7517,
+      "step": 181
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.1506646824589497,
+      "learning_rate": 3.452746404941143e-06,
+      "loss": 0.7355,
+      "step": 182
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.169292733116705,
+      "learning_rate": 3.4368698004102284e-06,
+      "loss": 0.74,
+      "step": 183
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 2.418141938844683,
+      "learning_rate": 3.420949115398151e-06,
+      "loss": 0.7503,
+      "step": 184
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.0599479007715886,
+      "learning_rate": 3.404985098986007e-06,
+      "loss": 0.7569,
+      "step": 185
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.9525184362879087,
+      "learning_rate": 3.388978502293666e-06,
+      "loss": 0.7354,
+      "step": 186
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 2.639288273379809,
+      "learning_rate": 3.372930078444439e-06,
+      "loss": 0.7567,
+      "step": 187
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 2.0510480212606232,
+      "learning_rate": 3.3568405825296355e-06,
+      "loss": 0.7433,
+      "step": 188
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.1578817124425735,
+      "learning_rate": 3.34071077157304e-06,
+      "loss": 0.7417,
+      "step": 189
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.5268212959295893,
+      "learning_rate": 3.3245414044952927e-06,
+      "loss": 0.7485,
+      "step": 190
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 2.159749201380735,
+      "learning_rate": 3.308333242078179e-06,
+      "loss": 0.7507,
+      "step": 191
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 2.308409227797682,
+      "learning_rate": 3.292087046928838e-06,
+      "loss": 0.752,
+      "step": 192
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 2.6229465595278616,
+      "learning_rate": 3.2758035834438804e-06,
+      "loss": 0.7348,
+      "step": 193
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.055730524359484,
+      "learning_rate": 3.2594836177734208e-06,
+      "loss": 0.7421,
+      "step": 194
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 2.0176570132314837,
+      "learning_rate": 3.2431279177850317e-06,
+      "loss": 0.7536,
+      "step": 195
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 2.403883281288115,
+      "learning_rate": 3.226737253027614e-06,
+      "loss": 0.7279,
+      "step": 196
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 2.000280638267734,
+      "learning_rate": 3.210312394695189e-06,
+      "loss": 0.7437,
+      "step": 197
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.220127089726233,
+      "learning_rate": 3.1938541155906146e-06,
+      "loss": 0.7477,
+      "step": 198
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.1887426336139875,
+      "learning_rate": 3.177363190089221e-06,
+      "loss": 0.7474,
+      "step": 199
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.981302078482481,
+      "learning_rate": 3.1608403941023793e-06,
+      "loss": 0.7396,
+      "step": 200
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 2.264086468679179,
+      "learning_rate": 3.144286505040992e-06,
+      "loss": 0.7391,
+      "step": 201
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 2.125610702261824,
+      "learning_rate": 3.1277023017789166e-06,
+      "loss": 0.7449,
+      "step": 202
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.167346271778115,
+      "learning_rate": 3.111088564616317e-06,
+      "loss": 0.741,
+      "step": 203
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.375363723765046,
+      "learning_rate": 3.094446075242952e-06,
+      "loss": 0.7469,
+      "step": 204
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.9942074170938597,
+      "learning_rate": 3.0777756167013946e-06,
+      "loss": 0.7431,
+      "step": 205
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 2.146743351563113,
+      "learning_rate": 3.0610779733501904e-06,
+      "loss": 0.752,
+      "step": 206
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.1525241003649174,
+      "learning_rate": 3.044353930826952e-06,
+      "loss": 0.7345,
+      "step": 207
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.8638029080202694,
+      "learning_rate": 3.0276042760113937e-06,
+      "loss": 0.7343,
+      "step": 208
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.8356317644401954,
+      "learning_rate": 3.0108297969883105e-06,
+      "loss": 0.7336,
+      "step": 209
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 2.0787011804537583,
+      "learning_rate": 2.9940312830104936e-06,
+      "loss": 0.7505,
+      "step": 210
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.8672332467108457,
+      "learning_rate": 2.977209524461601e-06,
+      "loss": 0.7479,
+      "step": 211
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 2.0236026898201063,
+      "learning_rate": 2.960365312818967e-06,
+      "loss": 0.7563,
+      "step": 212
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.9813232623431425,
+      "learning_rate": 2.9434994406163574e-06,
+      "loss": 0.7405,
+      "step": 213
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 2.009874379662123,
+      "learning_rate": 2.9266127014066905e-06,
+      "loss": 0.7576,
+      "step": 214
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.9182181733436605,
+      "learning_rate": 2.9097058897246904e-06,
+      "loss": 0.732,
+      "step": 215
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 2.2713302836846836,
+      "learning_rate": 2.8927798010495095e-06,
+      "loss": 0.7557,
+      "step": 216
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.8499354567551494,
+      "learning_rate": 2.875835231767297e-06,
+      "loss": 0.746,
+      "step": 217
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.056857824508339,
+      "learning_rate": 2.8588729791337298e-06,
+      "loss": 0.7327,
+      "step": 218
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 2.0366392068105768,
+      "learning_rate": 2.8418938412365016e-06,
+      "loss": 0.7649,
+      "step": 219
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 2.075283194301643,
+      "learning_rate": 2.8248986169577697e-06,
+      "loss": 0.7498,
+      "step": 220
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.8137465567608382,
+      "learning_rate": 2.807888105936571e-06,
+      "loss": 0.7426,
+      "step": 221
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.9713775183042563,
+      "learning_rate": 2.7908631085311933e-06,
+      "loss": 0.7573,
+      "step": 222
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.9347350716569554,
+      "learning_rate": 2.7738244257815234e-06,
+      "loss": 0.739,
+      "step": 223
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.04529529738096,
+      "learning_rate": 2.756772859371351e-06,
+      "loss": 0.743,
+      "step": 224
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.1971388123428754,
+      "learning_rate": 2.7397092115906554e-06,
+      "loss": 0.7471,
+      "step": 225
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.7934500775315345,
+      "learning_rate": 2.7226342852978542e-06,
+      "loss": 0.7443,
+      "step": 226
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.268705081511345,
+      "learning_rate": 2.7055488838820266e-06,
+      "loss": 0.7414,
+      "step": 227
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.9139342117735205,
+      "learning_rate": 2.6884538112251147e-06,
+      "loss": 0.7406,
+      "step": 228
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.3588112901077714,
+      "learning_rate": 2.6713498716641017e-06,
+      "loss": 0.7575,
+      "step": 229
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 1.7941800288489695,
+      "learning_rate": 2.6542378699531645e-06,
+      "loss": 0.7459,
+      "step": 230
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 2.5891645782274955,
+      "learning_rate": 2.6371186112258118e-06,
+      "loss": 0.7472,
+      "step": 231
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.8268045992021926,
+      "learning_rate": 2.6199929009570003e-06,
+      "loss": 0.7489,
+      "step": 232
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 2.703784770062622,
+      "learning_rate": 2.602861544925236e-06,
+      "loss": 0.7272,
+      "step": 233
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 2.00621810320303,
+      "learning_rate": 2.5857253491746646e-06,
+      "loss": 0.7434,
+      "step": 234
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 3.0770514249566507,
+      "learning_rate": 2.568585119977142e-06,
+      "loss": 0.7547,
+      "step": 235
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.199087929149206,
+      "learning_rate": 2.551441663794304e-06,
+      "loss": 0.7362,
+      "step": 236
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.609728798751417,
+      "learning_rate": 2.5342957872396156e-06,
+      "loss": 0.7387,
+      "step": 237
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.4167509521439583,
+      "learning_rate": 2.5171482970404244e-06,
+      "loss": 0.7291,
+      "step": 238
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.272061225763508,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7054,
+      "step": 239
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.824272633709913,
+      "learning_rate": 2.482851702959577e-06,
+      "loss": 0.6944,
+      "step": 240
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 3.5666822575384316,
+      "learning_rate": 2.4657042127603853e-06,
+      "loss": 0.6993,
+      "step": 241
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 2.3931138116624724,
+      "learning_rate": 2.4485583362056975e-06,
+      "loss": 0.7047,
+      "step": 242
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 2.9320600754571795,
+      "learning_rate": 2.4314148800228584e-06,
+      "loss": 0.6925,
+      "step": 243
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 2.8973919990299133,
+      "learning_rate": 2.4142746508253367e-06,
+      "loss": 0.6965,
+      "step": 244
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.625815226251557,
+      "learning_rate": 2.3971384550747644e-06,
+      "loss": 0.683,
+      "step": 245
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.4155664260482714,
+      "learning_rate": 2.3800070990430006e-06,
+      "loss": 0.6994,
+      "step": 246
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 2.411022689524766,
+      "learning_rate": 2.3628813887741882e-06,
+      "loss": 0.6894,
+      "step": 247
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.28077143295534,
+      "learning_rate": 2.345762130046836e-06,
+      "loss": 0.7023,
+      "step": 248
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.401968274277045,
+      "learning_rate": 2.3286501283358987e-06,
+      "loss": 0.6759,
+      "step": 249
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 2.378798265143013,
+      "learning_rate": 2.311546188774886e-06,
+      "loss": 0.6958,
+      "step": 250
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 2.3673961258869904,
+      "learning_rate": 2.2944511161179743e-06,
+      "loss": 0.6838,
+      "step": 251
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 2.516008730553284,
+      "learning_rate": 2.2773657147021466e-06,
+      "loss": 0.6909,
+      "step": 252
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 2.2281402280211466,
+      "learning_rate": 2.2602907884093454e-06,
+      "loss": 0.6811,
+      "step": 253
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 2.1439630603489315,
+      "learning_rate": 2.24322714062865e-06,
+      "loss": 0.6952,
+      "step": 254
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 2.1634818483654077,
+      "learning_rate": 2.2261755742184783e-06,
+      "loss": 0.698,
+      "step": 255
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 2.196698584094087,
+      "learning_rate": 2.2091368914688067e-06,
+      "loss": 0.6791,
+      "step": 256
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.146209315784236,
+      "learning_rate": 2.19211189406343e-06,
+      "loss": 0.7023,
+      "step": 257
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 2.1405757699513766,
+      "learning_rate": 2.1751013830422303e-06,
+      "loss": 0.6977,
+      "step": 258
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.9616924770190525,
+      "learning_rate": 2.1581061587634992e-06,
+      "loss": 0.6812,
+      "step": 259
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.23295032851048,
+      "learning_rate": 2.14112702086627e-06,
+      "loss": 0.685,
+      "step": 260
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 2.279103072547858,
+      "learning_rate": 2.1241647682327037e-06,
+      "loss": 0.6954,
+      "step": 261
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.1829812242717317,
+      "learning_rate": 2.1072201989504914e-06,
+      "loss": 0.6934,
+      "step": 262
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 2.2223700306607537,
+      "learning_rate": 2.09029411027531e-06,
+      "loss": 0.6886,
+      "step": 263
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.0785442261456337,
+      "learning_rate": 2.073387298593311e-06,
+      "loss": 0.6994,
+      "step": 264
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 2.266610094629974,
+      "learning_rate": 2.0565005593836434e-06,
+      "loss": 0.6969,
+      "step": 265
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.132447543935174,
+      "learning_rate": 2.0396346871810347e-06,
+      "loss": 0.6773,
+      "step": 266
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.0884173463715228,
+      "learning_rate": 2.0227904755383985e-06,
+      "loss": 0.6945,
+      "step": 267
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.2085913230241396,
+      "learning_rate": 2.005968716989507e-06,
+      "loss": 0.6949,
+      "step": 268
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 2.0268180328155507,
+      "learning_rate": 1.98917020301169e-06,
+      "loss": 0.7027,
+      "step": 269
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 2.4747960228822037,
+      "learning_rate": 1.9723957239886067e-06,
+      "loss": 0.6794,
+      "step": 270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.095701576576396,
+      "learning_rate": 1.955646069173048e-06,
+      "loss": 0.6961,
+      "step": 271
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.0823665858025313,
+      "learning_rate": 1.93892202664981e-06,
+      "loss": 0.6786,
+      "step": 272
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.245218571211113,
+      "learning_rate": 1.922224383298606e-06,
+      "loss": 0.6974,
+      "step": 273
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.158681117909884,
+      "learning_rate": 1.905553924757049e-06,
+      "loss": 0.7002,
+      "step": 274
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 2.146126951984283,
+      "learning_rate": 1.888911435383684e-06,
+      "loss": 0.6843,
+      "step": 275
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.1238895111610048,
+      "learning_rate": 1.8722976982210845e-06,
+      "loss": 0.684,
+      "step": 276
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 2.1081813807297984,
+      "learning_rate": 1.8557134949590087e-06,
+      "loss": 0.6868,
+      "step": 277
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 2.0759325520644096,
+      "learning_rate": 1.8391596058976214e-06,
+      "loss": 0.69,
+      "step": 278
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 2.087216621474724,
+      "learning_rate": 1.8226368099107793e-06,
+      "loss": 0.6923,
+      "step": 279
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 2.4018313648831113,
+      "learning_rate": 1.806145884409386e-06,
+      "loss": 0.6931,
+      "step": 280
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 2.0013309281300216,
+      "learning_rate": 1.7896876053048112e-06,
+      "loss": 0.6893,
+      "step": 281
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 2.059546352986111,
+      "learning_rate": 1.7732627469723868e-06,
+      "loss": 0.6867,
+      "step": 282
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.000325940508461,
+      "learning_rate": 1.756872082214969e-06,
+      "loss": 0.6914,
+      "step": 283
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.379361502001129,
+      "learning_rate": 1.7405163822265803e-06,
+      "loss": 0.6906,
+      "step": 284
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.8960887672873148,
+      "learning_rate": 1.7241964165561204e-06,
+      "loss": 0.6673,
+      "step": 285
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 2.172181466809878,
+      "learning_rate": 1.707912953071163e-06,
+      "loss": 0.6781,
+      "step": 286
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 2.015019267745016,
+      "learning_rate": 1.6916667579218216e-06,
+      "loss": 0.6963,
+      "step": 287
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.0355415165674846,
+      "learning_rate": 1.6754585955047081e-06,
+      "loss": 0.6779,
+      "step": 288
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 2.1086130667226977,
+      "learning_rate": 1.6592892284269597e-06,
+      "loss": 0.6998,
+      "step": 289
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.059886916939569,
+      "learning_rate": 1.6431594174703647e-06,
+      "loss": 0.6802,
+      "step": 290
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.0641741782118332,
+      "learning_rate": 1.6270699215555608e-06,
+      "loss": 0.6854,
+      "step": 291
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.1806834552623444,
+      "learning_rate": 1.6110214977063345e-06,
+      "loss": 0.6987,
+      "step": 292
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 2.158353312239409,
+      "learning_rate": 1.5950149010139938e-06,
+      "loss": 0.6823,
+      "step": 293
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.921092711707764,
+      "learning_rate": 1.5790508846018493e-06,
+      "loss": 0.6941,
+      "step": 294
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.3977437347525594,
+      "learning_rate": 1.563130199589773e-06,
+      "loss": 0.6915,
+      "step": 295
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 2.0303949213498167,
+      "learning_rate": 1.5472535950588575e-06,
+      "loss": 0.6971,
+      "step": 296
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.176759402835286,
+      "learning_rate": 1.5314218180161783e-06,
+      "loss": 0.6809,
+      "step": 297
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.9729876407553733,
+      "learning_rate": 1.5156356133596356e-06,
+      "loss": 0.6933,
+      "step": 298
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.168577615246608,
+      "learning_rate": 1.4998957238429173e-06,
+      "loss": 0.6873,
+      "step": 299
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 2.0839917041722704,
+      "learning_rate": 1.4842028900405422e-06,
+      "loss": 0.6984,
+      "step": 300
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.893739609530612,
+      "learning_rate": 1.4685578503130227e-06,
+      "loss": 0.6922,
+      "step": 301
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 2.0857317964888193,
+      "learning_rate": 1.4529613407721193e-06,
+      "loss": 0.6908,
+      "step": 302
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 2.0026826285563564,
+      "learning_rate": 1.4374140952462109e-06,
+      "loss": 0.6752,
+      "step": 303
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.914005315845231,
+      "learning_rate": 1.4219168452457593e-06,
+      "loss": 0.6988,
+      "step": 304
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.0223609197099552,
+      "learning_rate": 1.4064703199289038e-06,
+      "loss": 0.6842,
+      "step": 305
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 2.1096738426378407,
+      "learning_rate": 1.391075246067139e-06,
+      "loss": 0.6823,
+      "step": 306
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.0768301164703438,
+      "learning_rate": 1.375732348011132e-06,
+      "loss": 0.6898,
+      "step": 307
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.123519591919823,
+      "learning_rate": 1.3604423476566342e-06,
+      "loss": 0.6732,
+      "step": 308
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.1761224742449934,
+      "learning_rate": 1.3452059644105174e-06,
+      "loss": 0.6915,
+      "step": 309
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 2.1481136545780246,
+      "learning_rate": 1.3300239151569251e-06,
+      "loss": 0.6942,
+      "step": 310
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.194600040469437,
+      "learning_rate": 1.3148969142235436e-06,
+      "loss": 0.6788,
+      "step": 311
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 2.1089291541456223,
+      "learning_rate": 1.2998256733479896e-06,
+      "loss": 0.7013,
+      "step": 312
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.19121425222603,
+      "learning_rate": 1.2848109016443255e-06,
+      "loss": 0.6897,
+      "step": 313
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 1.9319788219662473,
+      "learning_rate": 1.2698533055696926e-06,
+      "loss": 0.6976,
+      "step": 314
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.275808654157748,
+      "learning_rate": 1.254953588891073e-06,
+      "loss": 0.6839,
+      "step": 315
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 2.198386215375118,
+      "learning_rate": 1.2401124526521763e-06,
+      "loss": 0.6946,
+      "step": 316
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.8790492694109773,
+      "learning_rate": 1.225330595140455e-06,
+      "loss": 0.676,
+      "step": 317
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.9926892667726497,
+      "learning_rate": 1.2106087118542504e-06,
+      "loss": 0.6824,
+      "step": 318
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 2.0144848585141206,
+      "learning_rate": 1.1959474954700667e-06,
+      "loss": 0.6906,
+      "step": 319
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.0949703627379446,
+      "learning_rate": 1.1813476358099824e-06,
+      "loss": 0.6952,
+      "step": 320
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.878706080567921,
+      "learning_rate": 1.166809819809192e-06,
+      "loss": 0.6846,
+      "step": 321
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 2.106975261880749,
+      "learning_rate": 1.1523347314836857e-06,
+      "loss": 0.6916,
+      "step": 322
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 2.0193667358417486,
+      "learning_rate": 1.1379230518980663e-06,
+      "loss": 0.695,
+      "step": 323
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.8829454822076184,
+      "learning_rate": 1.123575459133504e-06,
+      "loss": 0.6856,
+      "step": 324
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.9885667241669744,
+      "learning_rate": 1.109292628255832e-06,
+      "loss": 0.6849,
+      "step": 325
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.9038960696049037,
+      "learning_rate": 1.0950752312837846e-06,
+      "loss": 0.6901,
+      "step": 326
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 2.0104842271889467,
+      "learning_rate": 1.0809239371573779e-06,
+      "loss": 0.7014,
+      "step": 327
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.9066116631636623,
+      "learning_rate": 1.0668394117064365e-06,
+      "loss": 0.6798,
+      "step": 328
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.9713999361623535,
+      "learning_rate": 1.0528223176192618e-06,
+      "loss": 0.6979,
+      "step": 329
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.8465153504391632,
+      "learning_rate": 1.0388733144114605e-06,
+      "loss": 0.6892,
+      "step": 330
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.9408714006937027,
+      "learning_rate": 1.024993058394902e-06,
+      "loss": 0.6985,
+      "step": 331
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.030993015395332,
+      "learning_rate": 1.0111822026468515e-06,
+      "loss": 0.6925,
+      "step": 332
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.811976430858568,
+      "learning_rate": 9.974413969792285e-07,
+      "loss": 0.6805,
+      "step": 333
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 2.025426310321446,
+      "learning_rate": 9.837712879080464e-07,
+      "loss": 0.6884,
+      "step": 334
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 1.8699504401283087,
+      "learning_rate": 9.701725186229801e-07,
+      "loss": 0.6766,
+      "step": 335
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.9813729971640541,
+      "learning_rate": 9.56645728957117e-07,
+      "loss": 0.6816,
+      "step": 336
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.857568380571694,
+      "learning_rate": 9.431915553568374e-07,
+      "loss": 0.6941,
+      "step": 337
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.8075501016131494,
+      "learning_rate": 9.298106308518847e-07,
+      "loss": 0.6915,
+      "step": 338
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.896748082277053,
+      "learning_rate": 9.165035850255672e-07,
+      "loss": 0.6965,
+      "step": 339
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 1.903236161607879,
+      "learning_rate": 9.032710439851444e-07,
+      "loss": 0.6942,
+      "step": 340
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.0473184895907344,
+      "learning_rate": 8.901136303323654e-07,
+      "loss": 0.6868,
+      "step": 341
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.9225358657320613,
+      "learning_rate": 8.770319631341745e-07,
+      "loss": 0.6833,
+      "step": 342
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.8842364675717973,
+      "learning_rate": 8.640266578935841e-07,
+      "loss": 0.7059,
+      "step": 343
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.9601955634309354,
+      "learning_rate": 8.510983265207152e-07,
+      "loss": 0.6996,
+      "step": 344
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.8136997160021915,
+      "learning_rate": 8.382475773040055e-07,
+      "loss": 0.6836,
+      "step": 345
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.9111490776903417,
+      "learning_rate": 8.254750148815893e-07,
+      "loss": 0.6996,
+      "step": 346
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.8878734449529964,
+      "learning_rate": 8.127812402128521e-07,
+      "loss": 0.6932,
+      "step": 347
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.7623368894317115,
+      "learning_rate": 8.001668505501464e-07,
+      "loss": 0.696,
+      "step": 348
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.9509975903694705,
+      "learning_rate": 7.876324394107018e-07,
+      "loss": 0.6886,
+      "step": 349
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.8836926534531768,
+      "learning_rate": 7.751785965486894e-07,
+      "loss": 0.6898,
+      "step": 350
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.9384474477733897,
+      "learning_rate": 7.628059079274793e-07,
+      "loss": 0.6829,
+      "step": 351
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.8215374593231801,
+      "learning_rate": 7.505149556920698e-07,
+      "loss": 0.6908,
+      "step": 352
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.8093873518769943,
+      "learning_rate": 7.383063181416955e-07,
+      "loss": 0.6983,
+      "step": 353
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.9915437999230632,
+      "learning_rate": 7.261805697026178e-07,
+      "loss": 0.7005,
+      "step": 354
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.89611825729105,
+      "learning_rate": 7.141382809010999e-07,
+      "loss": 0.6931,
+      "step": 355
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8365953198306064,
+      "learning_rate": 7.021800183365607e-07,
+      "loss": 0.6817,
+      "step": 356
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 1.8887825422099398,
+      "learning_rate": 6.903063446549166e-07,
+      "loss": 0.6796,
+      "step": 357
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.0505162217401396,
+      "learning_rate": 6.785178185221095e-07,
+      "loss": 0.6823,
+      "step": 358
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 2.8780046222752,
+      "learning_rate": 6.668149945978203e-07,
+      "loss": 0.6598,
+      "step": 359
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 2.320474085762604,
+      "learning_rate": 6.551984235093692e-07,
+      "loss": 0.6646,
+      "step": 360
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 3.148494101628221,
+      "learning_rate": 6.436686518258156e-07,
+      "loss": 0.6521,
+      "step": 361
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.9894322407930707,
+      "learning_rate": 6.322262220322314e-07,
+      "loss": 0.6497,
+      "step": 362
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.0905514911758116,
+      "learning_rate": 6.208716725041869e-07,
+      "loss": 0.6729,
+      "step": 363
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 2.5235937968654882,
+      "learning_rate": 6.096055374824117e-07,
+      "loss": 0.6536,
+      "step": 364
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 2.7164252624114953,
+      "learning_rate": 5.984283470476621e-07,
+      "loss": 0.6557,
+      "step": 365
+    },
+    {
+      "epoch": 3.07,
+      "grad_norm": 2.1414297977553134,
+      "learning_rate": 5.873406270957804e-07,
+      "loss": 0.6517,
+      "step": 366
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 2.087954653292254,
+      "learning_rate": 5.763428993129499e-07,
+      "loss": 0.6535,
+      "step": 367
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 2.5430489969699166,
+      "learning_rate": 5.654356811511494e-07,
+      "loss": 0.6594,
+      "step": 368
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 2.4893194798160425,
+      "learning_rate": 5.546194858038073e-07,
+      "loss": 0.6702,
+      "step": 369
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 1.9260382585512938,
+      "learning_rate": 5.438948221816559e-07,
+      "loss": 0.6629,
+      "step": 370
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 2.057039216215999,
+      "learning_rate": 5.332621948887823e-07,
+      "loss": 0.6583,
+      "step": 371
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 2.182074257751017,
+      "learning_rate": 5.227221041988955e-07,
+      "loss": 0.6602,
+      "step": 372
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 1.9356067875549532,
+      "learning_rate": 5.122750460317768e-07,
+      "loss": 0.6621,
+      "step": 373
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 1.9075744893117703,
+      "learning_rate": 5.019215119299578e-07,
+      "loss": 0.6673,
+      "step": 374
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 2.0600626341053028,
+      "learning_rate": 4.916619890355812e-07,
+      "loss": 0.6577,
+      "step": 375
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 1.847664227547946,
+      "learning_rate": 4.814969600674926e-07,
+      "loss": 0.6566,
+      "step": 376
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 1.9200825550285445,
+      "learning_rate": 4.714269032985161e-07,
+      "loss": 0.6531,
+      "step": 377
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 1.945604786921752,
+      "learning_rate": 4.614522925329626e-07,
+      "loss": 0.6577,
+      "step": 378
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 1.9471196049311694,
+      "learning_rate": 4.515735970843263e-07,
+      "loss": 0.6659,
+      "step": 379
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 1.8278961360694248,
+      "learning_rate": 4.417912817532133e-07,
+      "loss": 0.6554,
+      "step": 380
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.88830260098924,
+      "learning_rate": 4.321058068054626e-07,
+      "loss": 0.6563,
+      "step": 381
+    },
+    {
+      "epoch": 3.21,
+      "grad_norm": 1.9149749844100774,
+      "learning_rate": 4.225176279504975e-07,
+      "loss": 0.6571,
+      "step": 382
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 1.8814221934773716,
+      "learning_rate": 4.130271963198815e-07,
+      "loss": 0.6572,
+      "step": 383
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 1.8849419819366298,
+      "learning_rate": 4.0363495844609134e-07,
+      "loss": 0.6604,
+      "step": 384
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 1.9046094115295815,
+      "learning_rate": 3.9434135624150854e-07,
+      "loss": 0.6652,
+      "step": 385
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 1.944275827853693,
+      "learning_rate": 3.8514682697762706e-07,
+      "loss": 0.6572,
+      "step": 386
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 1.8699721288071858,
+      "learning_rate": 3.7605180326447806e-07,
+      "loss": 0.6401,
+      "step": 387
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 1.775035768873695,
+      "learning_rate": 3.6705671303027687e-07,
+      "loss": 0.6523,
+      "step": 388
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 1.7843895394177849,
+      "learning_rate": 3.581619795012875e-07,
+      "loss": 0.6516,
+      "step": 389
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 1.919359950542867,
+      "learning_rate": 3.493680211819103e-07,
+      "loss": 0.6607,
+      "step": 390
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 1.8576252034229292,
+      "learning_rate": 3.4067525183499013e-07,
+      "loss": 0.6663,
+      "step": 391
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 1.7764574523914607,
+      "learning_rate": 3.3208408046234904e-07,
+      "loss": 0.6576,
+      "step": 392
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 1.8446907169053142,
+      "learning_rate": 3.2359491128554214e-07,
+      "loss": 0.6582,
+      "step": 393
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 1.7493689583147616,
+      "learning_rate": 3.152081437268398e-07,
+      "loss": 0.6548,
+      "step": 394
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 1.816698197495291,
+      "learning_rate": 3.069241723904318e-07,
+      "loss": 0.6636,
+      "step": 395
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 1.790271464078186,
+      "learning_rate": 2.987433870438641e-07,
+      "loss": 0.657,
+      "step": 396
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 1.743131857961643,
+      "learning_rate": 2.906661725996976e-07,
+      "loss": 0.6652,
+      "step": 397
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 1.7977795864445705,
+      "learning_rate": 2.82692909097399e-07,
+      "loss": 0.6455,
+      "step": 398
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 1.777376679638967,
+      "learning_rate": 2.7482397168545895e-07,
+      "loss": 0.6592,
+      "step": 399
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.806389217351911,
+      "learning_rate": 2.670597306037412e-07,
+      "loss": 0.6606,
+      "step": 400
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 1.773333434653589,
+      "learning_rate": 2.59400551166063e-07,
+      "loss": 0.6576,
+      "step": 401
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 1.7728777287155046,
+      "learning_rate": 2.5184679374300553e-07,
+      "loss": 0.6606,
+      "step": 402
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 1.83343142007096,
+      "learning_rate": 2.4439881374496016e-07,
+      "loss": 0.6713,
+      "step": 403
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.8119712073997163,
+      "learning_rate": 2.3705696160540303e-07,
+      "loss": 0.6596,
+      "step": 404
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.7575305127120062,
+      "learning_rate": 2.298215827644118e-07,
+      "loss": 0.6582,
+      "step": 405
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 1.80965570055429,
+      "learning_rate": 2.2269301765240558e-07,
+      "loss": 0.6508,
+      "step": 406
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 1.8329895956407685,
+      "learning_rate": 2.1567160167413503e-07,
+      "loss": 0.6657,
+      "step": 407
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 1.8295154972235375,
+      "learning_rate": 2.0875766519289436e-07,
+      "loss": 0.6602,
+      "step": 408
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 1.778360539334375,
+      "learning_rate": 2.0195153351498325e-07,
+      "loss": 0.6672,
+      "step": 409
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 1.8281360399477038,
+      "learning_rate": 1.9525352687439548e-07,
+      "loss": 0.6713,
+      "step": 410
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 1.798281276385492,
+      "learning_rate": 1.886639604177573e-07,
+      "loss": 0.6589,
+      "step": 411
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 1.8101646090365584,
+      "learning_rate": 1.821831441894939e-07,
+      "loss": 0.6576,
+      "step": 412
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 1.8163930084993238,
+      "learning_rate": 1.7581138311724754e-07,
+      "loss": 0.6509,
+      "step": 413
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 1.7889849857989786,
+      "learning_rate": 1.6954897699752394e-07,
+      "loss": 0.6654,
+      "step": 414
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 1.7753176697331132,
+      "learning_rate": 1.6339622048159198e-07,
+      "loss": 0.6555,
+      "step": 415
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 1.758833276503715,
+      "learning_rate": 1.5735340306161752e-07,
+      "loss": 0.665,
+      "step": 416
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 1.7863343585516815,
+      "learning_rate": 1.514208090570432e-07,
+      "loss": 0.6484,
+      "step": 417
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 1.7763079205782726,
+      "learning_rate": 1.4559871760121108e-07,
+      "loss": 0.6562,
+      "step": 418
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.8490593873759873,
+      "learning_rate": 1.3988740262822847e-07,
+      "loss": 0.6497,
+      "step": 419
+    },
+    {
+      "epoch": 3.53,
+      "grad_norm": 1.7753823119901868,
+      "learning_rate": 1.3428713286008005e-07,
+      "loss": 0.6534,
+      "step": 420
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 1.7671712087628604,
+      "learning_rate": 1.2879817179398375e-07,
+      "loss": 0.6519,
+      "step": 421
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 1.7594428378082356,
+      "learning_rate": 1.2342077768999372e-07,
+      "loss": 0.6519,
+      "step": 422
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.767897963166057,
+      "learning_rate": 1.1815520355884679e-07,
+      "loss": 0.6528,
+      "step": 423
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 1.7463739318936164,
+      "learning_rate": 1.130016971500622e-07,
+      "loss": 0.6582,
+      "step": 424
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 1.747840277010472,
+      "learning_rate": 1.0796050094027954e-07,
+      "loss": 0.6661,
+      "step": 425
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 1.8160480622182698,
+      "learning_rate": 1.0303185212185485e-07,
+      "loss": 0.646,
+      "step": 426
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 1.7568873705777095,
+      "learning_rate": 9.821598259169729e-08,
+      "loss": 0.6554,
+      "step": 427
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.733832059747267,
+      "learning_rate": 9.351311894036014e-08,
+      "loss": 0.6632,
+      "step": 428
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 1.804637277135235,
+      "learning_rate": 8.892348244137788e-08,
+      "loss": 0.66,
+      "step": 429
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 1.767868039735343,
+      "learning_rate": 8.444728904085737e-08,
+      "loss": 0.659,
+      "step": 430
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 1.770931658466082,
+      "learning_rate": 8.008474934731447e-08,
+      "loss": 0.668,
+      "step": 431
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 1.7732670135950312,
+      "learning_rate": 7.583606862176713e-08,
+      "loss": 0.6548,
+      "step": 432
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 1.7259860505689657,
+      "learning_rate": 7.170144676807683e-08,
+      "loss": 0.6318,
+      "step": 433
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 1.7392331188224266,
+      "learning_rate": 6.768107832354292e-08,
+      "loss": 0.6636,
+      "step": 434
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 1.7732212376542704,
+      "learning_rate": 6.377515244974903e-08,
+      "loss": 0.6626,
+      "step": 435
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 1.7335582830409095,
+      "learning_rate": 5.99838529236646e-08,
+      "loss": 0.668,
+      "step": 436
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 1.7716856700895114,
+      "learning_rate": 5.6307358128994685e-08,
+      "loss": 0.667,
+      "step": 437
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 1.7617896255786891,
+      "learning_rate": 5.274584104779157e-08,
+      "loss": 0.6538,
+      "step": 438
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 1.7528019015815823,
+      "learning_rate": 4.929946925231077e-08,
+      "loss": 0.6534,
+      "step": 439
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 1.8117296265464948,
+      "learning_rate": 4.5968404897130944e-08,
+      "loss": 0.6674,
+      "step": 440
+    },
+    {
+      "epoch": 3.71,
+      "grad_norm": 1.749044793771054,
+      "learning_rate": 4.27528047115211e-08,
+      "loss": 0.6682,
+      "step": 441
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 1.7454523412078409,
+      "learning_rate": 3.965281999206899e-08,
+      "loss": 0.6601,
+      "step": 442
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 1.7598878691389603,
+      "learning_rate": 3.666859659556016e-08,
+      "loss": 0.6603,
+      "step": 443
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 1.7046387508749583,
+      "learning_rate": 3.3800274932117294e-08,
+      "loss": 0.6518,
+      "step": 444
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.7163795248428233,
+      "learning_rate": 3.1047989958592203e-08,
+      "loss": 0.6651,
+      "step": 445
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.777257207147479,
+      "learning_rate": 2.841187117221672e-08,
+      "loss": 0.6558,
+      "step": 446
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 1.8219202465976836,
+      "learning_rate": 2.5892042604510614e-08,
+      "loss": 0.6508,
+      "step": 447
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 1.7767451714812037,
+      "learning_rate": 2.348862281544323e-08,
+      "loss": 0.6509,
+      "step": 448
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 1.7465806936718902,
+      "learning_rate": 2.1201724887858488e-08,
+      "loss": 0.6523,
+      "step": 449
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 1.7329527459099043,
+      "learning_rate": 1.9031456422151374e-08,
+      "loss": 0.6404,
+      "step": 450
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 1.7965434015907633,
+      "learning_rate": 1.6977919531207533e-08,
+      "loss": 0.6603,
+      "step": 451
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 1.7618638033364344,
+      "learning_rate": 1.5041210835596288e-08,
+      "loss": 0.6421,
+      "step": 452
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 1.7717100092665263,
+      "learning_rate": 1.3221421459027329e-08,
+      "loss": 0.6656,
+      "step": 453
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 1.7605568107436471,
+      "learning_rate": 1.1518637024061086e-08,
+      "loss": 0.6668,
+      "step": 454
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 1.751907548134551,
+      "learning_rate": 9.932937648081397e-09,
+      "loss": 0.6579,
+      "step": 455
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 1.7386986707922565,
+      "learning_rate": 8.464397939524915e-09,
+      "loss": 0.6703,
+      "step": 456
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 1.7643987709822369,
+      "learning_rate": 7.113086994372242e-09,
+      "loss": 0.666,
+      "step": 457
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 1.7296344516569304,
+      "learning_rate": 5.879068392894427e-09,
+      "loss": 0.6522,
+      "step": 458
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 1.7593863922129787,
+      "learning_rate": 4.762400196664518e-09,
+      "loss": 0.6586,
+      "step": 459
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 1.7608500271319567,
+      "learning_rate": 3.763134945823088e-09,
+      "loss": 0.6689,
+      "step": 460
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 1.7248718265179743,
+      "learning_rate": 2.8813196566079836e-09,
+      "loss": 0.6476,
+      "step": 461
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 1.7430786741620756,
+      "learning_rate": 2.116995819140821e-09,
+      "loss": 0.6636,
+      "step": 462
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 1.7541283862977322,
+      "learning_rate": 1.4701993954760462e-09,
+      "loss": 0.6639,
+      "step": 463
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 1.7203096912350941,
+      "learning_rate": 9.409608179078433e-10,
+      "loss": 0.6475,
+      "step": 464
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 1.7295283175572225,
+      "learning_rate": 5.293049875393363e-10,
+      "loss": 0.6589,
+      "step": 465
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 1.7037779795629253,
+      "learning_rate": 2.3525127310936035e-10,
+      "loss": 0.6521,
+      "step": 466
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 1.7513315633630457,
+      "learning_rate": 5.88135100831888e-11,
+      "loss": 0.6556,
+      "step": 467
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 1.7159722803516417,
+      "learning_rate": 0.0,
+      "loss": 0.6477,
+      "step": 468
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 468,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 117,
+  "total_flos": 783498671554560.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fa71f886375a49c8138f5964d4f7cd59fe86af7b3bafb59f0884948d34f423
+size 7608