add model files.

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "../model/codellama-instructed-by-evol-resummarized-by-wizardcoder-gpt4-13B-CL-1x80g-1epoch-0613",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e688dcbb68f75bf83d371a0631d43c7e1556fa9b68ecee4885e1da3e0830dbac
+size 4978265800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584fd00632397ecc18d4e98126dbc13d975f523c30eb5ff2a6313c0b523e6f4d
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1680efcbccb4bf288db511f46ed541bc5aa68fe158f676b10365f562ecb5c091
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d197534885338c6ab9c0bd77cea6ca7bcdfba429c4bd5b25c0e6680ff2c25a
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec71d6733c8646f4475724a50628035f99eec8c013a342c32970a98dd0b187bc
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdde82f57094500c6f8bbda764d5f7c5712dc9115537fe5eac9a987e46413f89
+size 1245236920

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "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-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-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-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-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-00002-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-00002-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-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-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-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-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-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.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-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-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-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-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-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-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 +1,29 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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
+  },
+  "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 +1,83 @@
+{
+  "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": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2634 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9985789194391228,
+  "eval_steps": 500,
+  "global_step": 434,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2154.8345,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 312.5255,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2138.2986,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 343.9667,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 8198.7002,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 2178.5674,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 23595.8965,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 67273.3125,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3e-05,
+      "loss": 141691.7031,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 103845.0469,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 468.9194,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4e-05,
+      "loss": 1383.6638,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1525188.25,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 41394.4219,
+      "step": 14
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5e-05,
+      "loss": 531693.3125,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.988066825775656e-05,
+      "loss": 424.9092,
+      "step": 16
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.976133651551313e-05,
+      "loss": 4699.9478,
+      "step": 17
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.964200477326969e-05,
+      "loss": 3598.4495,
+      "step": 18
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.952267303102625e-05,
+      "loss": 329783.8438,
+      "step": 19
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.940334128878282e-05,
+      "loss": 108553.8594,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9284009546539385e-05,
+      "loss": 669686.625,
+      "step": 21
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9164677804295945e-05,
+      "loss": 516.546,
+      "step": 22
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.904534606205251e-05,
+      "loss": 1165.3262,
+      "step": 23
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.892601431980907e-05,
+      "loss": 14278.1465,
+      "step": 24
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.880668257756563e-05,
+      "loss": 803169.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.8687350835322196e-05,
+      "loss": 3864.5024,
+      "step": 26
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.856801909307876e-05,
+      "loss": 286386.7812,
+      "step": 27
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.844868735083533e-05,
+      "loss": 9645701.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.832935560859189e-05,
+      "loss": 10830.8975,
+      "step": 29
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.821002386634845e-05,
+      "loss": 7533.4912,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.809069212410501e-05,
+      "loss": 11029.4629,
+      "step": 31
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.797136038186158e-05,
+      "loss": 5534.8965,
+      "step": 32
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.785202863961814e-05,
+      "loss": 3849.7932,
+      "step": 33
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7732696897374704e-05,
+      "loss": 14622.9688,
+      "step": 34
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.761336515513127e-05,
+      "loss": 2258.0952,
+      "step": 35
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.749403341288783e-05,
+      "loss": 562.1243,
+      "step": 36
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7374701670644396e-05,
+      "loss": 1060.5302,
+      "step": 37
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7255369928400955e-05,
+      "loss": 94356.0781,
+      "step": 38
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.713603818615752e-05,
+      "loss": 325.8985,
+      "step": 39
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.701670644391408e-05,
+      "loss": 1542.8948,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.6897374701670647e-05,
+      "loss": 25336.4648,
+      "step": 41
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.677804295942721e-05,
+      "loss": 8603.3447,
+      "step": 42
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.665871121718377e-05,
+      "loss": 164.9301,
+      "step": 43
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.653937947494034e-05,
+      "loss": 35805.4766,
+      "step": 44
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.64200477326969e-05,
+      "loss": 178383.0625,
+      "step": 45
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6300715990453463e-05,
+      "loss": 756.3121,
+      "step": 46
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.618138424821002e-05,
+      "loss": 3312.0427,
+      "step": 47
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.606205250596659e-05,
+      "loss": 2473.1311,
+      "step": 48
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.594272076372315e-05,
+      "loss": 8402.5947,
+      "step": 49
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.582338902147972e-05,
+      "loss": 93.5995,
+      "step": 50
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.570405727923628e-05,
+      "loss": 235.2204,
+      "step": 51
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.5584725536992847e-05,
+      "loss": 21004.8418,
+      "step": 52
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.5465393794749406e-05,
+      "loss": 9018.7559,
+      "step": 53
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.5346062052505965e-05,
+      "loss": 31628.4824,
+      "step": 54
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.522673031026253e-05,
+      "loss": 98.9685,
+      "step": 55
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.510739856801909e-05,
+      "loss": 55139.7383,
+      "step": 56
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.498806682577566e-05,
+      "loss": 3274.8267,
+      "step": 57
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.486873508353222e-05,
+      "loss": 387.2443,
+      "step": 58
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.474940334128879e-05,
+      "loss": 115.7972,
+      "step": 59
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.463007159904535e-05,
+      "loss": 4086.0728,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.4510739856801914e-05,
+      "loss": 13200.7227,
+      "step": 61
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.4391408114558474e-05,
+      "loss": 392.8962,
+      "step": 62
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.427207637231503e-05,
+      "loss": 1629.9041,
+      "step": 63
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.41527446300716e-05,
+      "loss": 665.3759,
+      "step": 64
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.4033412887828165e-05,
+      "loss": 1822.3533,
+      "step": 65
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.391408114558473e-05,
+      "loss": 84440.8281,
+      "step": 66
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.379474940334129e-05,
+      "loss": 156.116,
+      "step": 67
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.367541766109786e-05,
+      "loss": 33720.3906,
+      "step": 68
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.3556085918854416e-05,
+      "loss": 57585.8555,
+      "step": 69
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.343675417661098e-05,
+      "loss": 27.3209,
+      "step": 70
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.331742243436754e-05,
+      "loss": 1515.2338,
+      "step": 71
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.319809069212411e-05,
+      "loss": 360.9213,
+      "step": 72
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.3078758949880674e-05,
+      "loss": 44361.9766,
+      "step": 73
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.295942720763723e-05,
+      "loss": 2210.8513,
+      "step": 74
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.28400954653938e-05,
+      "loss": 1037.6666,
+      "step": 75
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.272076372315036e-05,
+      "loss": 4023.9438,
+      "step": 76
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.2601431980906925e-05,
+      "loss": 82307.1484,
+      "step": 77
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.2482100238663484e-05,
+      "loss": 323.2414,
+      "step": 78
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.236276849642005e-05,
+      "loss": 135475.5312,
+      "step": 79
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.2243436754176616e-05,
+      "loss": 3599.7883,
+      "step": 80
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.2124105011933175e-05,
+      "loss": 363409.875,
+      "step": 81
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.200477326968974e-05,
+      "loss": 125604.3984,
+      "step": 82
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.18854415274463e-05,
+      "loss": 220.2469,
+      "step": 83
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.176610978520287e-05,
+      "loss": 1677.0813,
+      "step": 84
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.1646778042959426e-05,
+      "loss": 4098.7871,
+      "step": 85
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.152744630071599e-05,
+      "loss": 2398.8313,
+      "step": 86
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.140811455847255e-05,
+      "loss": 923.5432,
+      "step": 87
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.1288782816229125e-05,
+      "loss": 10474.2695,
+      "step": 88
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.1169451073985684e-05,
+      "loss": 85930.8516,
+      "step": 89
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.105011933174224e-05,
+      "loss": 628.9391,
+      "step": 90
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.093078758949881e-05,
+      "loss": 266.4478,
+      "step": 91
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.081145584725537e-05,
+      "loss": 3529850.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.0692124105011935e-05,
+      "loss": 30642.959,
+      "step": 93
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.0572792362768494e-05,
+      "loss": 4583143.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.045346062052506e-05,
+      "loss": 6407.5708,
+      "step": 95
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.0334128878281626e-05,
+      "loss": 3839.4238,
+      "step": 96
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.021479713603819e-05,
+      "loss": 815.6643,
+      "step": 97
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.009546539379475e-05,
+      "loss": 349.929,
+      "step": 98
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.997613365155131e-05,
+      "loss": 371217.7812,
+      "step": 99
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.985680190930788e-05,
+      "loss": 176.3654,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9737470167064437e-05,
+      "loss": 64.4966,
+      "step": 101
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9618138424821e-05,
+      "loss": 17530.2637,
+      "step": 102
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.949880668257757e-05,
+      "loss": 544.7783,
+      "step": 103
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.9379474940334135e-05,
+      "loss": 7955.9927,
+      "step": 104
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.9260143198090694e-05,
+      "loss": 197.6159,
+      "step": 105
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.914081145584726e-05,
+      "loss": 1884.6552,
+      "step": 106
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.902147971360382e-05,
+      "loss": 1102.6284,
+      "step": 107
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.8902147971360386e-05,
+      "loss": 52947.9766,
+      "step": 108
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.8782816229116945e-05,
+      "loss": 836.1002,
+      "step": 109
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.866348448687351e-05,
+      "loss": 8226.0859,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.854415274463008e-05,
+      "loss": 671.9891,
+      "step": 111
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.8424821002386637e-05,
+      "loss": 3420.7861,
+      "step": 112
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.83054892601432e-05,
+      "loss": 6020.8076,
+      "step": 113
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.818615751789976e-05,
+      "loss": 9401.3975,
+      "step": 114
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.806682577565633e-05,
+      "loss": 888.0344,
+      "step": 115
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.794749403341289e-05,
+      "loss": 20902.9258,
+      "step": 116
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.7828162291169453e-05,
+      "loss": 33.6206,
+      "step": 117
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.770883054892602e-05,
+      "loss": 36034.0859,
+      "step": 118
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.758949880668258e-05,
+      "loss": 4315.4829,
+      "step": 119
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.7470167064439145e-05,
+      "loss": 41.5108,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.7350835322195704e-05,
+      "loss": 118439.2344,
+      "step": 121
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.723150357995227e-05,
+      "loss": 56936.8984,
+      "step": 122
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.711217183770883e-05,
+      "loss": 70.141,
+      "step": 123
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.6992840095465396e-05,
+      "loss": 1669.0631,
+      "step": 124
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.6873508353221955e-05,
+      "loss": 993.8124,
+      "step": 125
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.675417661097852e-05,
+      "loss": 323.3054,
+      "step": 126
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.663484486873509e-05,
+      "loss": 2687.2642,
+      "step": 127
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.651551312649165e-05,
+      "loss": 809.3516,
+      "step": 128
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.639618138424821e-05,
+      "loss": 2634.0364,
+      "step": 129
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.627684964200477e-05,
+      "loss": 1219.66,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.615751789976134e-05,
+      "loss": 340.3108,
+      "step": 131
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.60381861575179e-05,
+      "loss": 202.8932,
+      "step": 132
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.5918854415274464e-05,
+      "loss": 2560.3716,
+      "step": 133
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.579952267303103e-05,
+      "loss": 194.0811,
+      "step": 134
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.5680190930787596e-05,
+      "loss": 280622.0938,
+      "step": 135
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.5560859188544155e-05,
+      "loss": 1152.0107,
+      "step": 136
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.5441527446300715e-05,
+      "loss": 1275.4032,
+      "step": 137
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.532219570405728e-05,
+      "loss": 2975.0798,
+      "step": 138
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.520286396181384e-05,
+      "loss": 4207.3472,
+      "step": 139
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.5083532219570406e-05,
+      "loss": 1444.906,
+      "step": 140
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.496420047732697e-05,
+      "loss": 10217.4951,
+      "step": 141
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.484486873508354e-05,
+      "loss": 2441.9373,
+      "step": 142
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.47255369928401e-05,
+      "loss": 2693.4023,
+      "step": 143
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.4606205250596664e-05,
+      "loss": 289.4755,
+      "step": 144
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.448687350835322e-05,
+      "loss": 3141.6868,
+      "step": 145
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.436754176610978e-05,
+      "loss": 4827.5513,
+      "step": 146
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.424821002386635e-05,
+      "loss": 140.7513,
+      "step": 147
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.4128878281622915e-05,
+      "loss": 407.0926,
+      "step": 148
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.400954653937948e-05,
+      "loss": 11325.877,
+      "step": 149
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.389021479713604e-05,
+      "loss": 1355.1071,
+      "step": 150
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.3770883054892606e-05,
+      "loss": 2447.5452,
+      "step": 151
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.3651551312649165e-05,
+      "loss": 179011.7969,
+      "step": 152
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.353221957040573e-05,
+      "loss": 4771.3545,
+      "step": 153
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.341288782816229e-05,
+      "loss": 10228.957,
+      "step": 154
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.329355608591885e-05,
+      "loss": 6799.0142,
+      "step": 155
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.3174224343675416e-05,
+      "loss": 62602.7656,
+      "step": 156
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.305489260143198e-05,
+      "loss": 1877.1234,
+      "step": 157
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.293556085918855e-05,
+      "loss": 23234.3672,
+      "step": 158
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.281622911694511e-05,
+      "loss": 3270.4211,
+      "step": 159
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2696897374701674e-05,
+      "loss": 210849.625,
+      "step": 160
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.257756563245823e-05,
+      "loss": 21.4817,
+      "step": 161
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.24582338902148e-05,
+      "loss": 440.5267,
+      "step": 162
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.233890214797136e-05,
+      "loss": 11568.3057,
+      "step": 163
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.2219570405727925e-05,
+      "loss": 222751.4375,
+      "step": 164
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.210023866348449e-05,
+      "loss": 8170.4053,
+      "step": 165
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.198090692124105e-05,
+      "loss": 895.7988,
+      "step": 166
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.1861575178997616e-05,
+      "loss": 1350.8844,
+      "step": 167
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.1742243436754176e-05,
+      "loss": 5618.6152,
+      "step": 168
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.162291169451074e-05,
+      "loss": 4986.3745,
+      "step": 169
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.15035799522673e-05,
+      "loss": 47760.0273,
+      "step": 170
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.138424821002387e-05,
+      "loss": 1268.5199,
+      "step": 171
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.126491646778043e-05,
+      "loss": 2829.28,
+      "step": 172
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.1145584725537e-05,
+      "loss": 63647.0195,
+      "step": 173
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.102625298329356e-05,
+      "loss": 289.5919,
+      "step": 174
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.090692124105012e-05,
+      "loss": 212786.1406,
+      "step": 175
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.0787589498806684e-05,
+      "loss": 750.4266,
+      "step": 176
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.0668257756563243e-05,
+      "loss": 439.2351,
+      "step": 177
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.054892601431981e-05,
+      "loss": 3095.3596,
+      "step": 178
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.0429594272076372e-05,
+      "loss": 1786.9099,
+      "step": 179
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.031026252983294e-05,
+      "loss": 24.2971,
+      "step": 180
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.01909307875895e-05,
+      "loss": 8940.6621,
+      "step": 181
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.0071599045346067e-05,
+      "loss": 35.1568,
+      "step": 182
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.9952267303102627e-05,
+      "loss": 464.3121,
+      "step": 183
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.983293556085919e-05,
+      "loss": 1286.3716,
+      "step": 184
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9713603818615755e-05,
+      "loss": 2473.5828,
+      "step": 185
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.9594272076372315e-05,
+      "loss": 53711.5586,
+      "step": 186
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.947494033412888e-05,
+      "loss": 28963.9258,
+      "step": 187
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.935560859188544e-05,
+      "loss": 75207.0234,
+      "step": 188
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.923627684964201e-05,
+      "loss": 4702.6685,
+      "step": 189
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.911694510739857e-05,
+      "loss": 4575.6294,
+      "step": 190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.8997613365155135e-05,
+      "loss": 651.8832,
+      "step": 191
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.8878281622911694e-05,
+      "loss": 71858.8516,
+      "step": 192
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.8758949880668257e-05,
+      "loss": 3636.6687,
+      "step": 193
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.8639618138424823e-05,
+      "loss": 76.8694,
+      "step": 194
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8520286396181382e-05,
+      "loss": 390.3317,
+      "step": 195
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.840095465393795e-05,
+      "loss": 2925.4253,
+      "step": 196
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.828162291169451e-05,
+      "loss": 2840.2637,
+      "step": 197
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.8162291169451077e-05,
+      "loss": 19435.1816,
+      "step": 198
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8042959427207637e-05,
+      "loss": 13893.8916,
+      "step": 199
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.7923627684964203e-05,
+      "loss": 85997.7031,
+      "step": 200
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7804295942720766e-05,
+      "loss": 1057.1903,
+      "step": 201
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7684964200477325e-05,
+      "loss": 222.8144,
+      "step": 202
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.756563245823389e-05,
+      "loss": 3508.3396,
+      "step": 203
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.7446300715990454e-05,
+      "loss": 77230.9922,
+      "step": 204
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.732696897374702e-05,
+      "loss": 118.6687,
+      "step": 205
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.720763723150358e-05,
+      "loss": 818.3032,
+      "step": 206
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7088305489260145e-05,
+      "loss": 614.3881,
+      "step": 207
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6968973747016708e-05,
+      "loss": 1442.3588,
+      "step": 208
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6849642004773274e-05,
+      "loss": 11598.5752,
+      "step": 209
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.6730310262529833e-05,
+      "loss": 3279.7495,
+      "step": 210
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.6610978520286396e-05,
+      "loss": 9819.6895,
+      "step": 211
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6491646778042962e-05,
+      "loss": 619.9316,
+      "step": 212
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.637231503579952e-05,
+      "loss": 43706.6953,
+      "step": 213
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6252983293556088e-05,
+      "loss": 64.7919,
+      "step": 214
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.613365155131265e-05,
+      "loss": 3574.5085,
+      "step": 215
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6014319809069216e-05,
+      "loss": 678.5247,
+      "step": 216
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5894988066825776e-05,
+      "loss": 66.3897,
+      "step": 217
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5775656324582342e-05,
+      "loss": 41925.4766,
+      "step": 218
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.5656324582338905e-05,
+      "loss": 190234.2188,
+      "step": 219
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.5536992840095464e-05,
+      "loss": 1073.3352,
+      "step": 220
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.541766109785203e-05,
+      "loss": 87.6374,
+      "step": 221
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.529832935560859e-05,
+      "loss": 26874.1582,
+      "step": 222
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.517899761336516e-05,
+      "loss": 410.1149,
+      "step": 223
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.5059665871121718e-05,
+      "loss": 7732.0552,
+      "step": 224
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.494033412887828e-05,
+      "loss": 1358.0614,
+      "step": 225
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.4821002386634844e-05,
+      "loss": 33285.3281,
+      "step": 226
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.470167064439141e-05,
+      "loss": 8909.3711,
+      "step": 227
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.4582338902147972e-05,
+      "loss": 407.9029,
+      "step": 228
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.4463007159904535e-05,
+      "loss": 912.2557,
+      "step": 229
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.4343675417661098e-05,
+      "loss": 11245.6484,
+      "step": 230
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.4224343675417664e-05,
+      "loss": 13153.9141,
+      "step": 231
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.4105011933174227e-05,
+      "loss": 1926.8518,
+      "step": 232
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.398568019093079e-05,
+      "loss": 275.4235,
+      "step": 233
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3866348448687352e-05,
+      "loss": 2805.95,
+      "step": 234
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3747016706443915e-05,
+      "loss": 3201.3953,
+      "step": 235
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.3627684964200477e-05,
+      "loss": 788.0258,
+      "step": 236
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.350835322195704e-05,
+      "loss": 11083.1758,
+      "step": 237
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.3389021479713606e-05,
+      "loss": 55374.0273,
+      "step": 238
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.326968973747017e-05,
+      "loss": 584374.6875,
+      "step": 239
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.3150357995226732e-05,
+      "loss": 61.7834,
+      "step": 240
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.3031026252983294e-05,
+      "loss": 16746.6934,
+      "step": 241
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.291169451073986e-05,
+      "loss": 729.4385,
+      "step": 242
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.2792362768496423e-05,
+      "loss": 2346.0439,
+      "step": 243
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.2673031026252983e-05,
+      "loss": 22444.0,
+      "step": 244
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.2553699284009545e-05,
+      "loss": 11688.8047,
+      "step": 245
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.243436754176611e-05,
+      "loss": 8438.4268,
+      "step": 246
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.2315035799522674e-05,
+      "loss": 513.0939,
+      "step": 247
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.2195704057279237e-05,
+      "loss": 145.1669,
+      "step": 248
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.20763723150358e-05,
+      "loss": 33718.2617,
+      "step": 249
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.1957040572792366e-05,
+      "loss": 5309.7217,
+      "step": 250
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.183770883054893e-05,
+      "loss": 1561.8147,
+      "step": 251
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.171837708830549e-05,
+      "loss": 401.0991,
+      "step": 252
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.1599045346062054e-05,
+      "loss": 691.1371,
+      "step": 253
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.1479713603818617e-05,
+      "loss": 5117.2085,
+      "step": 254
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.136038186157518e-05,
+      "loss": 441.8343,
+      "step": 255
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1241050119331742e-05,
+      "loss": 4239.8047,
+      "step": 256
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1121718377088308e-05,
+      "loss": 2131.5051,
+      "step": 257
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.100238663484487e-05,
+      "loss": 15543.0732,
+      "step": 258
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.0883054892601433e-05,
+      "loss": 1561.8523,
+      "step": 259
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.0763723150357996e-05,
+      "loss": 501.6205,
+      "step": 260
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.0644391408114562e-05,
+      "loss": 31348.1641,
+      "step": 261
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.052505966587112e-05,
+      "loss": 9407.1494,
+      "step": 262
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.0405727923627684e-05,
+      "loss": 5945.5815,
+      "step": 263
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.0286396181384247e-05,
+      "loss": 198.1411,
+      "step": 264
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.0167064439140813e-05,
+      "loss": 1753.7537,
+      "step": 265
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.0047732696897376e-05,
+      "loss": 1425.4434,
+      "step": 266
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.992840095465394e-05,
+      "loss": 417.404,
+      "step": 267
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.98090692124105e-05,
+      "loss": 3352.2693,
+      "step": 268
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.9689737470167067e-05,
+      "loss": 419649.4062,
+      "step": 269
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.957040572792363e-05,
+      "loss": 331.6387,
+      "step": 270
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9451073985680193e-05,
+      "loss": 3271.9436,
+      "step": 271
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9331742243436756e-05,
+      "loss": 257.6401,
+      "step": 272
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.9212410501193318e-05,
+      "loss": 77.437,
+      "step": 273
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.909307875894988e-05,
+      "loss": 4351.1445,
+      "step": 274
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.8973747016706444e-05,
+      "loss": 945.9266,
+      "step": 275
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.885441527446301e-05,
+      "loss": 863.4519,
+      "step": 276
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8735083532219573e-05,
+      "loss": 3068.04,
+      "step": 277
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8615751789976135e-05,
+      "loss": 152.3694,
+      "step": 278
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8496420047732698e-05,
+      "loss": 27651.7871,
+      "step": 279
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.837708830548926e-05,
+      "loss": 1480.9608,
+      "step": 280
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.8257756563245823e-05,
+      "loss": 20972.2227,
+      "step": 281
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.8138424821002386e-05,
+      "loss": 509.0767,
+      "step": 282
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.801909307875895e-05,
+      "loss": 25930.4199,
+      "step": 283
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.7899761336515515e-05,
+      "loss": 33.3048,
+      "step": 284
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.7780429594272078e-05,
+      "loss": 12881.1221,
+      "step": 285
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.766109785202864e-05,
+      "loss": 125079.1875,
+      "step": 286
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.7541766109785203e-05,
+      "loss": 17346.0098,
+      "step": 287
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.742243436754177e-05,
+      "loss": 3085.6494,
+      "step": 288
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.7303102625298332e-05,
+      "loss": 1862.4844,
+      "step": 289
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.718377088305489e-05,
+      "loss": 584.3925,
+      "step": 290
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.7064439140811457e-05,
+      "loss": 1440.3424,
+      "step": 291
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.694510739856802e-05,
+      "loss": 10591.7715,
+      "step": 292
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.6825775656324583e-05,
+      "loss": 3629.6746,
+      "step": 293
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.6706443914081145e-05,
+      "loss": 203.7102,
+      "step": 294
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.6587112171837708e-05,
+      "loss": 1990.9237,
+      "step": 295
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.6467780429594274e-05,
+      "loss": 4698.8696,
+      "step": 296
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.6348448687350837e-05,
+      "loss": 12364.7568,
+      "step": 297
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.62291169451074e-05,
+      "loss": 3250.7644,
+      "step": 298
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.6109785202863962e-05,
+      "loss": 563.4382,
+      "step": 299
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.5990453460620525e-05,
+      "loss": 4512.2549,
+      "step": 300
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.5871121718377088e-05,
+      "loss": 356.9354,
+      "step": 301
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.575178997613365e-05,
+      "loss": 20561.3516,
+      "step": 302
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.5632458233890217e-05,
+      "loss": 1720.2273,
+      "step": 303
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.551312649164678e-05,
+      "loss": 61301.4414,
+      "step": 304
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.5393794749403342e-05,
+      "loss": 2145.4048,
+      "step": 305
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.5274463007159905e-05,
+      "loss": 32.2598,
+      "step": 306
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.515513126491647e-05,
+      "loss": 98319.1484,
+      "step": 307
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.5035799522673034e-05,
+      "loss": 41.3583,
+      "step": 308
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.4916467780429595e-05,
+      "loss": 969.0966,
+      "step": 309
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.4797136038186157e-05,
+      "loss": 11281.6221,
+      "step": 310
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.467780429594272e-05,
+      "loss": 140.3954,
+      "step": 311
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.4558472553699284e-05,
+      "loss": 40839.0352,
+      "step": 312
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.4439140811455847e-05,
+      "loss": 687.9666,
+      "step": 313
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.4319809069212412e-05,
+      "loss": 15623.2422,
+      "step": 314
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.4200477326968974e-05,
+      "loss": 36405.7031,
+      "step": 315
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.4081145584725539e-05,
+      "loss": 18.3407,
+      "step": 316
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3961813842482101e-05,
+      "loss": 20860.0215,
+      "step": 317
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3842482100238662e-05,
+      "loss": 136255.6094,
+      "step": 318
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3723150357995227e-05,
+      "loss": 114715.4141,
+      "step": 319
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.360381861575179e-05,
+      "loss": 380233.5312,
+      "step": 320
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.3484486873508354e-05,
+      "loss": 92655.1797,
+      "step": 321
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.3365155131264917e-05,
+      "loss": 221169.5625,
+      "step": 322
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3245823389021481e-05,
+      "loss": 14491.3555,
+      "step": 323
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3126491646778044e-05,
+      "loss": 604.6326,
+      "step": 324
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.3007159904534608e-05,
+      "loss": 1070.2869,
+      "step": 325
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2887828162291171e-05,
+      "loss": 1943.536,
+      "step": 326
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2768496420047732e-05,
+      "loss": 13625.3975,
+      "step": 327
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2649164677804295e-05,
+      "loss": 18923.8242,
+      "step": 328
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2529832935560859e-05,
+      "loss": 8192.084,
+      "step": 329
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2410501193317422e-05,
+      "loss": 18687.1094,
+      "step": 330
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2291169451073986e-05,
+      "loss": 24.7262,
+      "step": 331
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2171837708830549e-05,
+      "loss": 31110.3066,
+      "step": 332
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2052505966587113e-05,
+      "loss": 22251.8145,
+      "step": 333
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1933174224343676e-05,
+      "loss": 1738.8523,
+      "step": 334
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.1813842482100239e-05,
+      "loss": 135108.0,
+      "step": 335
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1694510739856803e-05,
+      "loss": 421.1908,
+      "step": 336
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1575178997613366e-05,
+      "loss": 1606.5295,
+      "step": 337
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.145584725536993e-05,
+      "loss": 2758.7969,
+      "step": 338
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.1336515513126491e-05,
+      "loss": 3688.4736,
+      "step": 339
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.1217183770883056e-05,
+      "loss": 42112.6953,
+      "step": 340
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.1097852028639618e-05,
+      "loss": 1432.4136,
+      "step": 341
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.0978520286396183e-05,
+      "loss": 1795.425,
+      "step": 342
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.0859188544152746e-05,
+      "loss": 7462.5249,
+      "step": 343
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.0739856801909308e-05,
+      "loss": 314273.4688,
+      "step": 344
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.0620525059665871e-05,
+      "loss": 82580.6328,
+      "step": 345
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.0501193317422435e-05,
+      "loss": 7970.0132,
+      "step": 346
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.0381861575178998e-05,
+      "loss": 34508.6797,
+      "step": 347
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.026252983293556e-05,
+      "loss": 69825.7188,
+      "step": 348
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.0143198090692124e-05,
+      "loss": 841.0046,
+      "step": 349
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.0023866348448688e-05,
+      "loss": 1370.4319,
+      "step": 350
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.90453460620525e-06,
+      "loss": 296.6957,
+      "step": 351
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.785202863961815e-06,
+      "loss": 469730.4062,
+      "step": 352
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.665871121718378e-06,
+      "loss": 25752.3867,
+      "step": 353
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.54653937947494e-06,
+      "loss": 3364.7927,
+      "step": 354
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.427207637231505e-06,
+      "loss": 2272.8479,
+      "step": 355
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.307875894988068e-06,
+      "loss": 6455.9248,
+      "step": 356
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.18854415274463e-06,
+      "loss": 1536.6981,
+      "step": 357
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.069212410501193e-06,
+      "loss": 1008.3629,
+      "step": 358
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.949880668257757e-06,
+      "loss": 5969.8877,
+      "step": 359
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.83054892601432e-06,
+      "loss": 3844.1497,
+      "step": 360
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.711217183770885e-06,
+      "loss": 5906.2695,
+      "step": 361
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.591885441527446e-06,
+      "loss": 22959.3652,
+      "step": 362
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.47255369928401e-06,
+      "loss": 356.8062,
+      "step": 363
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.353221957040573e-06,
+      "loss": 10640.417,
+      "step": 364
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.233890214797137e-06,
+      "loss": 15015.7236,
+      "step": 365
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.1145584725537e-06,
+      "loss": 27919.8359,
+      "step": 366
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 7.995226730310263e-06,
+      "loss": 93.8642,
+      "step": 367
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 7.875894988066825e-06,
+      "loss": 531.3182,
+      "step": 368
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 7.75656324582339e-06,
+      "loss": 44.6307,
+      "step": 369
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 7.637231503579952e-06,
+      "loss": 617.2424,
+      "step": 370
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.517899761336517e-06,
+      "loss": 35023.9141,
+      "step": 371
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.398568019093079e-06,
+      "loss": 301.8852,
+      "step": 372
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.279236276849642e-06,
+      "loss": 4805.9424,
+      "step": 373
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.159904534606206e-06,
+      "loss": 981.1636,
+      "step": 374
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.040572792362769e-06,
+      "loss": 2385.3809,
+      "step": 375
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.921241050119331e-06,
+      "loss": 17975.209,
+      "step": 376
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.801909307875895e-06,
+      "loss": 14639.3535,
+      "step": 377
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.682577565632458e-06,
+      "loss": 184.0828,
+      "step": 378
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 6.563245823389022e-06,
+      "loss": 4096.9023,
+      "step": 379
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 6.4439140811455855e-06,
+      "loss": 3484.0598,
+      "step": 380
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 6.324582338902147e-06,
+      "loss": 875.6252,
+      "step": 381
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 6.205250596658711e-06,
+      "loss": 372.1837,
+      "step": 382
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 6.0859188544152745e-06,
+      "loss": 374.8253,
+      "step": 383
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 5.966587112171838e-06,
+      "loss": 148.9297,
+      "step": 384
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 5.847255369928402e-06,
+      "loss": 2172.886,
+      "step": 385
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.727923627684965e-06,
+      "loss": 114176.7109,
+      "step": 386
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.608591885441528e-06,
+      "loss": 774.8303,
+      "step": 387
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.489260143198091e-06,
+      "loss": 8663.0283,
+      "step": 388
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.369928400954654e-06,
+      "loss": 39.113,
+      "step": 389
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.250596658711218e-06,
+      "loss": 569.8843,
+      "step": 390
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.13126491646778e-06,
+      "loss": 62.069,
+      "step": 391
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 5.011933174224344e-06,
+      "loss": 16262.8975,
+      "step": 392
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.8926014319809075e-06,
+      "loss": 386.9028,
+      "step": 393
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.77326968973747e-06,
+      "loss": 1635.613,
+      "step": 394
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.653937947494034e-06,
+      "loss": 6881.8877,
+      "step": 395
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.5346062052505965e-06,
+      "loss": 9540.7607,
+      "step": 396
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.41527446300716e-06,
+      "loss": 1987.6592,
+      "step": 397
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.295942720763723e-06,
+      "loss": 6021.2861,
+      "step": 398
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 4.176610978520286e-06,
+      "loss": 2370.6196,
+      "step": 399
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 4.05727923627685e-06,
+      "loss": 1680.244,
+      "step": 400
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.937947494033413e-06,
+      "loss": 82911.6641,
+      "step": 401
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.818615751789976e-06,
+      "loss": 767.3438,
+      "step": 402
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.6992840095465393e-06,
+      "loss": 316.2509,
+      "step": 403
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.579952267303103e-06,
+      "loss": 169716.9688,
+      "step": 404
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.4606205250596656e-06,
+      "loss": 307.0406,
+      "step": 405
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.341288782816229e-06,
+      "loss": 730.7938,
+      "step": 406
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.2219570405727927e-06,
+      "loss": 95440.8516,
+      "step": 407
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.1026252983293554e-06,
+      "loss": 4808.3286,
+      "step": 408
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.983293556085919e-06,
+      "loss": 1284.4513,
+      "step": 409
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.8639618138424826e-06,
+      "loss": 720.0696,
+      "step": 410
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.7446300715990457e-06,
+      "loss": 102548.2656,
+      "step": 411
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.625298329355609e-06,
+      "loss": 84.6599,
+      "step": 412
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.505966587112172e-06,
+      "loss": 1387.675,
+      "step": 413
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.386634844868735e-06,
+      "loss": 424.9204,
+      "step": 414
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.2673031026252983e-06,
+      "loss": 1309.8296,
+      "step": 415
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.1479713603818614e-06,
+      "loss": 6679.3481,
+      "step": 416
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.028639618138425e-06,
+      "loss": 14053.2295,
+      "step": 417
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.909307875894988e-06,
+      "loss": 44.5011,
+      "step": 418
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.7899761336515514e-06,
+      "loss": 4494.7183,
+      "step": 419
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.6706443914081146e-06,
+      "loss": 149.143,
+      "step": 420
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.5513126491646777e-06,
+      "loss": 821.6967,
+      "step": 421
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.4319809069212413e-06,
+      "loss": 1617.1495,
+      "step": 422
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.3126491646778044e-06,
+      "loss": 2006.76,
+      "step": 423
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.1933174224343676e-06,
+      "loss": 64.7329,
+      "step": 424
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0739856801909307e-06,
+      "loss": 1603.62,
+      "step": 425
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.54653937947494e-07,
+      "loss": 2882.3655,
+      "step": 426
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.353221957040573e-07,
+      "loss": 69.2657,
+      "step": 427
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 7.159904534606206e-07,
+      "loss": 286800.9062,
+      "step": 428
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.966587112171838e-07,
+      "loss": 4796.5063,
+      "step": 429
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.77326968973747e-07,
+      "loss": 267.1339,
+      "step": 430
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.579952267303103e-07,
+      "loss": 1926.3707,
+      "step": 431
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.386634844868735e-07,
+      "loss": 7170.8643,
+      "step": 432
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.1933174224343676e-07,
+      "loss": 612.3254,
+      "step": 433
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 7622.6533,
+      "step": 434
+    },
+    {
+      "epoch": 2.0,
+      "step": 434,
+      "total_flos": 1.0362069838124974e+19,
+      "train_loss": 74766.76249146792,
+      "train_runtime": 78556.7962,
+      "train_samples_per_second": 2.831,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 434,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.0362069838124974e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3b5e138d031cee687eda01dc683cc53d51f0d7d85008860f84dc9dd2ed5920
+size 4920