commit from szc

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/petrelfs/suzhaochen/hugging-models/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a5e84e4cec402110e6ebeec6b1bac8ad4fa4a1aaf09dca57a285df74f96f3d
+size 4840412800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc98487fc83653188f85fe2c5a61edb1822ac5d59568c6dadfbd437b495eb47
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc6d6201d36d678d30a968f341dd628522293df3aac54d6e2c028ee4d8e53c3
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930af43cbc69a3214f568903fb1c63c9b55023a19456afee6579b82a4c410c4d
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e8920465989aad1d8586b37a870e272b3da460a9bdbe64901c32c6db86bf61
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8b58db877e74fac464d651642de45f7e0672c266946664d315544564bac808
+size 2684488496

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953695232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2370 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9961612284069097,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.976,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0889,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-06,
+      "loss": 1.0516,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0442,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9154,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-05,
+      "loss": 0.8071,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8045,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9049,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7444,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8022,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.8045,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2e-05,
+      "loss": 0.786,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.999965463076377e-05,
+      "loss": 0.7576,
+      "step": 13
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.999861854691106e-05,
+      "loss": 0.7801,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.7678,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.999447456932676e-05,
+      "loss": 0.7011,
+      "step": 16
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9991366961835643e-05,
+      "loss": 0.8029,
+      "step": 17
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.7107,
+      "step": 18
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9983081582712684e-05,
+      "loss": 0.7184,
+      "step": 19
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.7116,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 0.7298,
+      "step": 21
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9965482753212154e-05,
+      "loss": 0.7372,
+      "step": 22
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.995823918037908e-05,
+      "loss": 0.7515,
+      "step": 23
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.708,
+      "step": 24
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.994168902089112e-05,
+      "loss": 0.7191,
+      "step": 25
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.7124,
+      "step": 26
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9922392066001724e-05,
+      "loss": 0.7441,
+      "step": 27
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.991171517679013e-05,
+      "loss": 0.7104,
+      "step": 28
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9900353647278466e-05,
+      "loss": 0.685,
+      "step": 29
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.6841,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9875579853729677e-05,
+      "loss": 0.6772,
+      "step": 31
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9862169300913784e-05,
+      "loss": 0.6912,
+      "step": 32
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.7304,
+      "step": 33
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9833305514727396e-05,
+      "loss": 0.6452,
+      "step": 34
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.981785427508966e-05,
+      "loss": 0.673,
+      "step": 35
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.689,
+      "step": 36
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9784918439034216e-05,
+      "loss": 0.7039,
+      "step": 37
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9767436117621416e-05,
+      "loss": 0.7361,
+      "step": 38
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.6826,
+      "step": 39
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.6094,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9710946170250702e-05,
+      "loss": 0.667,
+      "step": 41
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.6549,
+      "step": 42
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9669930175366474e-05,
+      "loss": 0.6342,
+      "step": 43
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.964841954916235e-05,
+      "loss": 0.666,
+      "step": 44
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.962624246950012e-05,
+      "loss": 0.6416,
+      "step": 45
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9603400468236e-05,
+      "loss": 0.6966,
+      "step": 46
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.957989512315489e-05,
+      "loss": 0.6545,
+      "step": 47
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.634,
+      "step": 48
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9530900941667733e-05,
+      "loss": 0.6945,
+      "step": 49
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9505415489478293e-05,
+      "loss": 0.6561,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.947927346167132e-05,
+      "loss": 0.6611,
+      "step": 51
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.945247666397725e-05,
+      "loss": 0.6934,
+      "step": 52
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9425026947353994e-05,
+      "loss": 0.6464,
+      "step": 53
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.645,
+      "step": 54
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.936817638651871e-05,
+      "loss": 0.6702,
+      "step": 55
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9338779469193638e-05,
+      "loss": 0.6402,
+      "step": 56
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.6362,
+      "step": 57
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9278052513379256e-05,
+      "loss": 0.64,
+      "step": 58
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9246726669534416e-05,
+      "loss": 0.6144,
+      "step": 59
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.6316,
+      "step": 60
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9182161068802742e-05,
+      "loss": 0.6689,
+      "step": 61
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9148925771710347e-05,
+      "loss": 0.6518,
+      "step": 62
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9115058523116734e-05,
+      "loss": 0.5923,
+      "step": 63
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.908056166236305e-05,
+      "loss": 0.6988,
+      "step": 64
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9045437572280193e-05,
+      "loss": 0.601,
+      "step": 65
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.6722,
+      "step": 66
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8973317451908642e-05,
+      "loss": 0.6582,
+      "step": 67
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.6201,
+      "step": 68
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8898718088114688e-05,
+      "loss": 0.6033,
+      "step": 69
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8860495104301346e-05,
+      "loss": 0.6243,
+      "step": 70
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8821660092002642e-05,
+      "loss": 0.6268,
+      "step": 71
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.6348,
+      "step": 72
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.874216475397386e-05,
+      "loss": 0.6298,
+      "step": 73
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.870150991929261e-05,
+      "loss": 0.6497,
+      "step": 74
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.6562,
+      "step": 75
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8618399959331642e-05,
+      "loss": 0.5886,
+      "step": 76
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8575950574776595e-05,
+      "loss": 0.5922,
+      "step": 77
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.6052,
+      "step": 78
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8489277657026377e-05,
+      "loss": 0.6444,
+      "step": 79
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.844506011066308e-05,
+      "loss": 0.6532,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8400259231507716e-05,
+      "loss": 0.5913,
+      "step": 81
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.6115,
+      "step": 82
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8308919893176397e-05,
+      "loss": 0.6151,
+      "step": 83
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.6356,
+      "step": 84
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8215284878234644e-05,
+      "loss": 0.6219,
+      "step": 85
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.816761455197657e-05,
+      "loss": 0.5587,
+      "step": 86
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.811938005715857e-05,
+      "loss": 0.5837,
+      "step": 87
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8070584725522763e-05,
+      "loss": 0.6195,
+      "step": 88
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.802123192755044e-05,
+      "loss": 0.5801,
+      "step": 89
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.6022,
+      "step": 90
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7920867606817625e-05,
+      "loss": 0.5874,
+      "step": 91
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7869863016606893e-05,
+      "loss": 0.5941,
+      "step": 92
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.5673,
+      "step": 93
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7766226591669787e-05,
+      "loss": 0.5274,
+      "step": 94
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.771360191551e-05,
+      "loss": 0.5781,
+      "step": 95
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5466,
+      "step": 96
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.760675781050109e-05,
+      "loss": 0.5735,
+      "step": 97
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.755254576178535e-05,
+      "loss": 0.611,
+      "step": 98
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7497812029677344e-05,
+      "loss": 0.5805,
+      "step": 99
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7442560394846518e-05,
+      "loss": 0.6469,
+      "step": 100
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.738679467373586e-05,
+      "loss": 0.5659,
+      "step": 101
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.6031,
+      "step": 102
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7273736415730488e-05,
+      "loss": 0.5683,
+      "step": 103
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7216451688204623e-05,
+      "loss": 0.5778,
+      "step": 104
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7158668492597186e-05,
+      "loss": 0.5899,
+      "step": 105
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7100390820215805e-05,
+      "loss": 0.5718,
+      "step": 106
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.704162269652352e-05,
+      "loss": 0.621,
+      "step": 107
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.5605,
+      "step": 108
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6922631366164795e-05,
+      "loss": 0.5819,
+      "step": 109
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.5916,
+      "step": 110
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6801727377709195e-05,
+      "loss": 0.5853,
+      "step": 111
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6740568555253153e-05,
+      "loss": 0.5812,
+      "step": 112
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6678944135794375e-05,
+      "loss": 0.5458,
+      "step": 113
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.5753,
+      "step": 114
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6554315564278102e-05,
+      "loss": 0.5455,
+      "step": 115
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.649132002079552e-05,
+      "loss": 0.6005,
+      "step": 116
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.5967,
+      "step": 117
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6363988174803638e-05,
+      "loss": 0.5674,
+      "step": 118
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6299660667594814e-05,
+      "loss": 0.5659,
+      "step": 119
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.5563,
+      "step": 120
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6169704701186528e-05,
+      "loss": 0.571,
+      "step": 121
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6104085218545633e-05,
+      "loss": 0.593,
+      "step": 122
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6038044103254775e-05,
+      "loss": 0.5485,
+      "step": 123
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.5426,
+      "step": 124
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5904715250387498e-05,
+      "loss": 0.5758,
+      "step": 125
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.5921,
+      "step": 126
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.576975498009583e-05,
+      "loss": 0.5577,
+      "step": 127
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.570167469866962e-05,
+      "loss": 0.5053,
+      "step": 128
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.563320058063622e-05,
+      "loss": 0.5801,
+      "step": 129
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5564337355766412e-05,
+      "loss": 0.5667,
+      "step": 130
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5495089780708062e-05,
+      "loss": 0.5525,
+      "step": 131
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.565,
+      "step": 132
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5355460739029585e-05,
+      "loss": 0.5496,
+      "step": 133
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5285088917124555e-05,
+      "loss": 0.537,
+      "step": 134
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5214352033794981e-05,
+      "loss": 0.5648,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5143254975109538e-05,
+      "loss": 0.5768,
+      "step": 136
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5071802652015592e-05,
+      "loss": 0.5166,
+      "step": 137
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5731,
+      "step": 138
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4927851978748177e-05,
+      "loss": 0.5489,
+      "step": 139
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4855363571801523e-05,
+      "loss": 0.5946,
+      "step": 140
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4782539786213184e-05,
+      "loss": 0.5283,
+      "step": 141
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4709385652202204e-05,
+      "loss": 0.5168,
+      "step": 142
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4635906222806058e-05,
+      "loss": 0.5446,
+      "step": 143
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.5433,
+      "step": 144
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4487991802004625e-05,
+      "loss": 0.5433,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4413567027617442e-05,
+      "loss": 0.5404,
+      "step": 146
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.5319,
+      "step": 147
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4263808054542541e-05,
+      "loss": 0.5363,
+      "step": 148
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.418848420028325e-05,
+      "loss": 0.5518,
+      "step": 149
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.4885,
+      "step": 150
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4036973770503623e-05,
+      "loss": 0.54,
+      "step": 151
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.5192,
+      "step": 152
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3884347962746949e-05,
+      "loss": 0.5538,
+      "step": 153
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3807629958244498e-05,
+      "loss": 0.5061,
+      "step": 154
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.373064894609194e-05,
+      "loss": 0.5201,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.5383,
+      "step": 156
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3575919186134862e-05,
+      "loss": 0.565,
+      "step": 157
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.349818112611015e-05,
+      "loss": 0.5636,
+      "step": 158
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.5505,
+      "step": 159
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3341985493931877e-05,
+      "loss": 0.5721,
+      "step": 160
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3263538710811559e-05,
+      "loss": 0.4852,
+      "step": 161
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.5074,
+      "step": 162
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3105974303239838e-05,
+      "loss": 0.5606,
+      "step": 163
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3026867562368262e-05,
+      "loss": 0.5678,
+      "step": 164
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2947551744109044e-05,
+      "loss": 0.5402,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.5172,
+      "step": 166
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2788314804085904e-05,
+      "loss": 0.5358,
+      "step": 167
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.5312,
+      "step": 168
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2628307478842955e-05,
+      "loss": 0.5445,
+      "step": 169
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2548028728946548e-05,
+      "loss": 0.5613,
+      "step": 170
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2467573976902936e-05,
+      "loss": 0.5302,
+      "step": 171
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.238694878003138e-05,
+      "loss": 0.5078,
+      "step": 172
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2306158707424402e-05,
+      "loss": 0.5054,
+      "step": 173
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.5123,
+      "step": 174
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2144106267931877e-05,
+      "loss": 0.5358,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2062855094631777e-05,
+      "loss": 0.56,
+      "step": 176
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1981461431993978e-05,
+      "loss": 0.54,
+      "step": 177
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1899930902191904e-05,
+      "loss": 0.5478,
+      "step": 178
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.181826913685291e-05,
+      "loss": 0.5194,
+      "step": 179
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.5653,
+      "step": 180
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1654574471008712e-05,
+      "loss": 0.4922,
+      "step": 181
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1572552877523855e-05,
+      "loss": 0.5214,
+      "step": 182
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1490422661761744e-05,
+      "loss": 0.4977,
+      "step": 183
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1408189496772369e-05,
+      "loss": 0.5505,
+      "step": 184
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1325859062716795e-05,
+      "loss": 0.5024,
+      "step": 185
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.5251,
+      "step": 186
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1160929141252303e-05,
+      "loss": 0.5484,
+      "step": 187
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1078341046187588e-05,
+      "loss": 0.5381,
+      "step": 188
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0995678465958168e-05,
+      "loss": 0.4959,
+      "step": 189
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0912947110386484e-05,
+      "loss": 0.5104,
+      "step": 190
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0830152694045553e-05,
+      "loss": 0.4918,
+      "step": 191
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.5424,
+      "step": 192
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0664397558732245e-05,
+      "loss": 0.4953,
+      "step": 193
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.527,
+      "step": 194
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0498458856606972e-05,
+      "loss": 0.5497,
+      "step": 195
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0415434993638269e-05,
+      "loss": 0.4698,
+      "step": 196
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0332382434976267e-05,
+      "loss": 0.3475,
+      "step": 197
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.4007,
+      "step": 198
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0166214179197265e-05,
+      "loss": 0.3814,
+      "step": 199
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0083109959960974e-05,
+      "loss": 0.3838,
+      "step": 200
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1e-05,
+      "loss": 0.3688,
+      "step": 201
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.916890040039031e-06,
+      "loss": 0.3937,
+      "step": 202
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.833785820802739e-06,
+      "loss": 0.3287,
+      "step": 203
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.3906,
+      "step": 204
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.667617565023734e-06,
+      "loss": 0.4174,
+      "step": 205
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.584565006361735e-06,
+      "loss": 0.4,
+      "step": 206
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.501541143393028e-06,
+      "loss": 0.3431,
+      "step": 207
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.352,
+      "step": 208
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.33560244126776e-06,
+      "loss": 0.3633,
+      "step": 209
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.3844,
+      "step": 210
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.169847305954448e-06,
+      "loss": 0.3414,
+      "step": 211
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.087052889613519e-06,
+      "loss": 0.3803,
+      "step": 212
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.004321534041836e-06,
+      "loss": 0.3827,
+      "step": 213
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.921658953812416e-06,
+      "loss": 0.3358,
+      "step": 214
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.839070858747697e-06,
+      "loss": 0.3669,
+      "step": 215
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.3405,
+      "step": 216
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.674140937283208e-06,
+      "loss": 0.3535,
+      "step": 217
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.591810503227634e-06,
+      "loss": 0.3346,
+      "step": 218
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.509577338238255e-06,
+      "loss": 0.3597,
+      "step": 219
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.427447122476148e-06,
+      "loss": 0.3383,
+      "step": 220
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.34542552899129e-06,
+      "loss": 0.329,
+      "step": 221
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.3833,
+      "step": 222
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.181730863147094e-06,
+      "loss": 0.3895,
+      "step": 223
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.100069097808103e-06,
+      "loss": 0.4046,
+      "step": 224
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.018538568006027e-06,
+      "loss": 0.3605,
+      "step": 225
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.937144905368226e-06,
+      "loss": 0.3349,
+      "step": 226
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.855893732068124e-06,
+      "loss": 0.3799,
+      "step": 227
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3595,
+      "step": 228
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.6938412925756e-06,
+      "loss": 0.3914,
+      "step": 229
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.613051219968624e-06,
+      "loss": 0.3809,
+      "step": 230
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.532426023097063e-06,
+      "loss": 0.3735,
+      "step": 231
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.451971271053455e-06,
+      "loss": 0.3383,
+      "step": 232
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.371692521157048e-06,
+      "loss": 0.352,
+      "step": 233
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.3623,
+      "step": 234
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.2116851959140965e-06,
+      "loss": 0.3862,
+      "step": 235
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.3456,
+      "step": 236
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.3511,
+      "step": 237
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.973132437631743e-06,
+      "loss": 0.3538,
+      "step": 238
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.8940256967601625e-06,
+      "loss": 0.3419,
+      "step": 239
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.322,
+      "step": 240
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.736461289188445e-06,
+      "loss": 0.3453,
+      "step": 241
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.6580145060681255e-06,
+      "loss": 0.3638,
+      "step": 242
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.3489,
+      "step": 243
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.501818873889856e-06,
+      "loss": 0.3718,
+      "step": 244
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.424080813865139e-06,
+      "loss": 0.3421,
+      "step": 245
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.3703,
+      "step": 246
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.269351053908061e-06,
+      "loss": 0.3663,
+      "step": 247
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.192370041755505e-06,
+      "loss": 0.3639,
+      "step": 248
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.115652037253054e-06,
+      "loss": 0.354,
+      "step": 249
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.387,
+      "step": 250
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.963026229496378e-06,
+      "loss": 0.3497,
+      "step": 251
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.3506,
+      "step": 252
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.811515799716754e-06,
+      "loss": 0.3564,
+      "step": 253
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.736191945457463e-06,
+      "loss": 0.372,
+      "step": 254
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.3864,
+      "step": 255
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.586432972382561e-06,
+      "loss": 0.3509,
+      "step": 256
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.512008197995379e-06,
+      "loss": 0.33,
+      "step": 257
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.3502,
+      "step": 258
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.364093777193944e-06,
+      "loss": 0.3871,
+      "step": 259
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.290614347797802e-06,
+      "loss": 0.3443,
+      "step": 260
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.217460213786822e-06,
+      "loss": 0.3523,
+      "step": 261
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.144636428198477e-06,
+      "loss": 0.3418,
+      "step": 262
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.072148021251822e-06,
+      "loss": 0.362,
+      "step": 263
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3536,
+      "step": 264
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.92819734798441e-06,
+      "loss": 0.3204,
+      "step": 265
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.856745024890466e-06,
+      "loss": 0.3443,
+      "step": 266
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.78564796620502e-06,
+      "loss": 0.3452,
+      "step": 267
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.714911082875446e-06,
+      "loss": 0.335,
+      "step": 268
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.644539260970417e-06,
+      "loss": 0.3533,
+      "step": 269
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.3615,
+      "step": 270
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.504910219291941e-06,
+      "loss": 0.3504,
+      "step": 271
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.435662644233594e-06,
+      "loss": 0.35,
+      "step": 272
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.3667994193637794e-06,
+      "loss": 0.3265,
+      "step": 273
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.298325301330383e-06,
+      "loss": 0.3376,
+      "step": 274
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.23024501990417e-06,
+      "loss": 0.3586,
+      "step": 275
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.3414,
+      "step": 276
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.095284749612504e-06,
+      "loss": 0.3386,
+      "step": 277
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.3291,
+      "step": 278
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.961955896745224e-06,
+      "loss": 0.314,
+      "step": 279
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.89591478145437e-06,
+      "loss": 0.3626,
+      "step": 280
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.830295298813475e-06,
+      "loss": 0.336,
+      "step": 281
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.3582,
+      "step": 282
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7003393324051874e-06,
+      "loss": 0.3337,
+      "step": 283
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.636011825196365e-06,
+      "loss": 0.3402,
+      "step": 284
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.3157,
+      "step": 285
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.5086799792044812e-06,
+      "loss": 0.321,
+      "step": 286
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.4456844357218977e-06,
+      "loss": 0.3552,
+      "step": 287
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.3274,
+      "step": 288
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.3210558642056277e-06,
+      "loss": 0.3862,
+      "step": 289
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.2594314447468457e-06,
+      "loss": 0.3398,
+      "step": 290
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.1982726222908046e-06,
+      "loss": 0.3404,
+      "step": 291
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.3497,
+      "step": 292
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.077368633835205e-06,
+      "loss": 0.3232,
+      "step": 293
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.3984,
+      "step": 294
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.958377303476483e-06,
+      "loss": 0.3158,
+      "step": 295
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.8996091797841976e-06,
+      "loss": 0.2874,
+      "step": 296
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.8413315074028157e-06,
+      "loss": 0.3272,
+      "step": 297
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.783548311795379e-06,
+      "loss": 0.3412,
+      "step": 298
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.726263584269513e-06,
+      "loss": 0.3036,
+      "step": 299
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.3386,
+      "step": 300
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.6132053262641467e-06,
+      "loss": 0.3404,
+      "step": 301
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.5574396051534835e-06,
+      "loss": 0.3025,
+      "step": 302
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.502187970322657e-06,
+      "loss": 0.3014,
+      "step": 303
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.447454238214654e-06,
+      "loss": 0.3266,
+      "step": 304
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3932421894989167e-06,
+      "loss": 0.3144,
+      "step": 305
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3544,
+      "step": 306
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.2863980844900036e-06,
+      "loss": 0.3037,
+      "step": 307
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.2337734083302164e-06,
+      "loss": 0.3378,
+      "step": 308
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.3438,
+      "step": 309
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.130136983393112e-06,
+      "loss": 0.3218,
+      "step": 310
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.0791323931823783e-06,
+      "loss": 0.3144,
+      "step": 311
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.3615,
+      "step": 312
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.9787680724495617e-06,
+      "loss": 0.329,
+      "step": 313
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.929415274477239e-06,
+      "loss": 0.348,
+      "step": 314
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.880619942841435e-06,
+      "loss": 0.3119,
+      "step": 315
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8323854480234348e-06,
+      "loss": 0.3304,
+      "step": 316
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.7847151217653624e-06,
+      "loss": 0.3615,
+      "step": 317
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.3315,
+      "step": 318
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.6910801068236015e-06,
+      "loss": 0.3285,
+      "step": 319
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.332,
+      "step": 320
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.599740768492286e-06,
+      "loss": 0.3314,
+      "step": 321
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5549398893369216e-06,
+      "loss": 0.3171,
+      "step": 322
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.5107223429736273e-06,
+      "loss": 0.3138,
+      "step": 323
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.3464,
+      "step": 324
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.424049425223405e-06,
+      "loss": 0.3239,
+      "step": 325
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3816000406683604e-06,
+      "loss": 0.3651,
+      "step": 326
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.3333,
+      "step": 327
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.2984900807073919e-06,
+      "loss": 0.3037,
+      "step": 328
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.2578352460261456e-06,
+      "loss": 0.3098,
+      "step": 329
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.3431,
+      "step": 330
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1783399079973578e-06,
+      "loss": 0.3466,
+      "step": 331
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1395048956986577e-06,
+      "loss": 0.3573,
+      "step": 332
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1012819118853147e-06,
+      "loss": 0.3155,
+      "step": 333
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.3185,
+      "step": 334
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.026682548091361e-06,
+      "loss": 0.355,
+      "step": 335
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.3425,
+      "step": 336
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.545624277198085e-07,
+      "loss": 0.3329,
+      "step": 337
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.194383376369509e-07,
+      "loss": 0.3512,
+      "step": 338
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.849414768832687e-07,
+      "loss": 0.3399,
+      "step": 339
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.510742282896545e-07,
+      "loss": 0.3041,
+      "step": 340
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.178389311972612e-07,
+      "loss": 0.3213,
+      "step": 341
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.3456,
+      "step": 342
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.532733304655848e-07,
+      "loss": 0.3546,
+      "step": 343
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.219474866207465e-07,
+      "loss": 0.313,
+      "step": 344
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.912625135579587e-07,
+      "loss": 0.3302,
+      "step": 345
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.612205308063646e-07,
+      "loss": 0.3214,
+      "step": 346
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.318236134812917e-07,
+      "loss": 0.3436,
+      "step": 347
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3569,
+      "step": 348
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.749730526460073e-07,
+      "loss": 0.3202,
+      "step": 349
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.475233360227516e-07,
+      "loss": 0.3313,
+      "step": 350
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.207265383286831e-07,
+      "loss": 0.3305,
+      "step": 351
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.945845105217118e-07,
+      "loss": 0.3337,
+      "step": 352
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.6909905833226965e-07,
+      "loss": 0.3286,
+      "step": 353
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.3051,
+      "step": 354
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.2010487684511105e-07,
+      "loss": 0.3574,
+      "step": 355
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.965995317640026e-07,
+      "loss": 0.3531,
+      "step": 356
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.7375753049987974e-07,
+      "loss": 0.3501,
+      "step": 357
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.515804508376508e-07,
+      "loss": 0.3483,
+      "step": 358
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.3006982463352764e-07,
+      "loss": 0.3303,
+      "step": 359
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.3181,
+      "step": 360
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.8905382974930173e-07,
+      "loss": 0.3199,
+      "step": 361
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 0.2989,
+      "step": 362
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.3392,
+      "step": 363
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.3256388237858806e-07,
+      "loss": 0.3426,
+      "step": 364
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.1508156096578748e-07,
+      "loss": 0.3412,
+      "step": 365
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.338,
+      "step": 366
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.82145724910342e-07,
+      "loss": 0.3432,
+      "step": 367
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.6669448527260602e-07,
+      "loss": 0.3142,
+      "step": 368
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.2942,
+      "step": 369
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.3783069908621772e-07,
+      "loss": 0.3565,
+      "step": 370
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.2442014627032318e-07,
+      "loss": 0.346,
+      "step": 371
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.3597,
+      "step": 372
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.964635272153633e-08,
+      "loss": 0.369,
+      "step": 373
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.82848232098732e-08,
+      "loss": 0.302,
+      "step": 374
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.760793399827937e-08,
+      "loss": 0.3438,
+      "step": 375
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.761642258056977e-08,
+      "loss": 0.3122,
+      "step": 376
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.831097910887873e-08,
+      "loss": 0.3243,
+      "step": 377
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.3313,
+      "step": 378
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.176081962092182e-08,
+      "loss": 0.3137,
+      "step": 379
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.451724678784518e-08,
+      "loss": 0.3736,
+      "step": 380
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.796202818819871e-08,
+      "loss": 0.3136,
+      "step": 381
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.2095616616150117e-08,
+      "loss": 0.3652,
+      "step": 382
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.6918417287318245e-08,
+      "loss": 0.3403,
+      "step": 383
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.3303,
+      "step": 384
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.633038164358454e-09,
+      "loss": 0.3345,
+      "step": 385
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.525430673244403e-09,
+      "loss": 0.3318,
+      "step": 386
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.1081799918375454e-09,
+      "loss": 0.3388,
+      "step": 387
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3814530889433298e-09,
+      "loss": 0.3245,
+      "step": 388
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.4536923623096353e-10,
+      "loss": 0.3206,
+      "step": 389
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.3554,
+      "step": 390
+    },
+    {
+      "epoch": 2.0,
+      "step": 390,
+      "total_flos": 2.582018135330652e+17,
+      "train_loss": 0.4808387424701299,
+      "train_runtime": 3317.3657,
+      "train_samples_per_second": 30.144,
+      "train_steps_per_second": 0.118
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2000,
+  "total_flos": 2.582018135330652e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a6985597601299fa1be71c24bf87fd8c6737fc2f3bb2b6bcf651b1bac531e5
+size 4984