train

.gitattributes

@@ -32,3 +32,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00006.bin filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00006.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00006.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00006.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00006.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00006.bin filter=lfs diff=lfs merge=lfs -text

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45512536a198e4dd0b805e1cac53e6ee3f1f27254344b70acee3de2305aaee2f
+size 9956543883

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8244c7716278d7fa0121de6bdac1bbd282afbc50138348bd1f4ed7207242cbdd
+size 9940856385

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35042b4f44fdcc1a19dbbc9e847c0810af4fe85ae4a6aedf16b8e48cacaf5223
+size 9940856943

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3af976460e27eb9f5a39fc199782cafb1151ce263024207472efde001379eb
+size 9867415289

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e92f3c165c5cba4bc03067635215d2253f7f843172cce436b064bf6380a9f2
+size 9867456961

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6034657b0aa56d56b220e4ba7461f057b08195cd37c0dfbaf6d50a9ae6d7c32
+size 2490476207

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063467520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

trainer_state.json

@@ -0,0 +1,2401 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9924528301886792,
+  "global_step": 396,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.25e-06,
+      "loss": 0.8661,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5e-06,
+      "loss": 0.8758,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.7376,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-06,
+      "loss": 0.7434,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.25e-06,
+      "loss": 0.6945,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.6896,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.6587,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1e-05,
+      "loss": 0.6568,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.125e-05,
+      "loss": 0.6368,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6348,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.375e-05,
+      "loss": 0.6196,
+      "step": 11
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6126,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.6079,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.5893,
+      "step": 14
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.567,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 0.5891,
+      "step": 16
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9999658256641746e-05,
+      "loss": 0.5882,
+      "step": 17
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9998633049924693e-05,
+      "loss": 0.559,
+      "step": 18
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.999692444992035e-05,
+      "loss": 0.5827,
+      "step": 19
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.999453257340926e-05,
+      "loss": 0.5694,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.999145758387301e-05,
+      "loss": 0.5581,
+      "step": 21
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.998769969148305e-05,
+      "loss": 0.5604,
+      "step": 22
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9983259153086328e-05,
+      "loss": 0.5556,
+      "step": 23
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9978136272187745e-05,
+      "loss": 0.5674,
+      "step": 24
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.997233139892941e-05,
+      "loss": 0.5265,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.99658449300667e-05,
+      "loss": 0.5486,
+      "step": 26
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.995867730894114e-05,
+      "loss": 0.5432,
+      "step": 27
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9950829025450116e-05,
+      "loss": 0.5616,
+      "step": 28
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9942300616013378e-05,
+      "loss": 0.5415,
+      "step": 29
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9933092663536384e-05,
+      "loss": 0.5493,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.992320579737045e-05,
+      "loss": 0.5608,
+      "step": 31
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9912640693269754e-05,
+      "loss": 0.5353,
+      "step": 32
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.990139807334512e-05,
+      "loss": 0.5511,
+      "step": 33
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9889478706014687e-05,
+      "loss": 0.5331,
+      "step": 34
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.5402,
+      "step": 35
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.5244,
+      "step": 36
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.984966849725452e-05,
+      "loss": 0.5238,
+      "step": 37
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9835050748723826e-05,
+      "loss": 0.5306,
+      "step": 38
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.981976078753884e-05,
+      "loss": 0.5177,
+      "step": 39
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9803799658748096e-05,
+      "loss": 0.5193,
+      "step": 40
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9787168453273546e-05,
+      "loss": 0.4995,
+      "step": 41
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9769868307835996e-05,
+      "loss": 0.517,
+      "step": 42
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.97519004048774e-05,
+      "loss": 0.5225,
+      "step": 43
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.973326597248006e-05,
+      "loss": 0.5065,
+      "step": 44
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9713966284282677e-05,
+      "loss": 0.5198,
+      "step": 45
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 0.5226,
+      "step": 46
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9673376462299186e-05,
+      "loss": 0.5022,
+      "step": 47
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9652089102773487e-05,
+      "loss": 0.513,
+      "step": 48
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.963014203577896e-05,
+      "loss": 0.4919,
+      "step": 49
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9607536761368484e-05,
+      "loss": 0.5182,
+      "step": 50
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.958427482458253e-05,
+      "loss": 0.5067,
+      "step": 51
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9560357815343577e-05,
+      "loss": 0.5196,
+      "step": 52
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9535787368347444e-05,
+      "loss": 0.5092,
+      "step": 53
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.5075,
+      "step": 54
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9484692923060095e-05,
+      "loss": 0.4976,
+      "step": 55
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.5013,
+      "step": 56
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9431005457431654e-05,
+      "loss": 0.4874,
+      "step": 57
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9403193901161614e-05,
+      "loss": 0.5119,
+      "step": 58
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9374739649079155e-05,
+      "loss": 0.4872,
+      "step": 59
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.934564464599461e-05,
+      "loss": 0.4822,
+      "step": 60
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9315910880512792e-05,
+      "loss": 0.4976,
+      "step": 61
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9285540384897073e-05,
+      "loss": 0.495,
+      "step": 62
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9254535234930486e-05,
+      "loss": 0.4942,
+      "step": 63
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.922289754977385e-05,
+      "loss": 0.4924,
+      "step": 64
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.919062949182091e-05,
+      "loss": 0.478,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9157733266550577e-05,
+      "loss": 0.4918,
+      "step": 66
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9124211122376138e-05,
+      "loss": 0.4908,
+      "step": 67
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.909006535049163e-05,
+      "loss": 0.4915,
+      "step": 68
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9055298284715192e-05,
+      "loss": 0.5002,
+      "step": 69
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9019912301329593e-05,
+      "loss": 0.4956,
+      "step": 70
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.898390981891979e-05,
+      "loss": 0.4728,
+      "step": 71
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8947293298207637e-05,
+      "loss": 0.471,
+      "step": 72
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.5036,
+      "step": 73
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.887222819443612e-05,
+      "loss": 0.4837,
+      "step": 74
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.883378474197689e-05,
+      "loss": 0.4758,
+      "step": 75
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.4789,
+      "step": 76
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.875508917352643e-05,
+      "loss": 0.4798,
+      "step": 77
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8714842436272774e-05,
+      "loss": 0.4737,
+      "step": 78
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8674000051114953e-05,
+      "loss": 0.4618,
+      "step": 79
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.863256480957574e-05,
+      "loss": 0.479,
+      "step": 80
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8590539543698852e-05,
+      "loss": 0.4616,
+      "step": 81
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.854792712585539e-05,
+      "loss": 0.4825,
+      "step": 82
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8504730468547508e-05,
+      "loss": 0.478,
+      "step": 83
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8460952524209355e-05,
+      "loss": 0.4773,
+      "step": 84
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8416596285005274e-05,
+      "loss": 0.4626,
+      "step": 85
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 0.498,
+      "step": 86
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8326161088077905e-05,
+      "loss": 0.4772,
+      "step": 87
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8280088311480203e-05,
+      "loss": 0.4749,
+      "step": 88
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.823344960184526e-05,
+      "loss": 0.4575,
+      "step": 89
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8186248146866928e-05,
+      "loss": 0.4649,
+      "step": 90
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.813848717270195e-05,
+      "loss": 0.4666,
+      "step": 91
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.4606,
+      "step": 92
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.804129976242792e-05,
+      "loss": 0.4658,
+      "step": 93
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7991879968949248e-05,
+      "loss": 0.4434,
+      "step": 94
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7941913941090712e-05,
+      "loss": 0.4583,
+      "step": 95
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.4769,
+      "step": 96
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.784035687978153e-05,
+      "loss": 0.4477,
+      "step": 97
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7788772787621126e-05,
+      "loss": 0.4576,
+      "step": 98
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7736656343186897e-05,
+      "loss": 0.4457,
+      "step": 99
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7684011108568593e-05,
+      "loss": 0.4774,
+      "step": 100
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7630840681998068e-05,
+      "loss": 0.4716,
+      "step": 101
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.757714869760335e-05,
+      "loss": 0.4352,
+      "step": 102
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.752293882516025e-05,
+      "loss": 0.457,
+      "step": 103
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7468214769841542e-05,
+      "loss": 0.4525,
+      "step": 104
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7412980271963712e-05,
+      "loss": 0.4518,
+      "step": 105
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.735723910673132e-05,
+      "loss": 0.478,
+      "step": 106
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7300995083978965e-05,
+      "loss": 0.4472,
+      "step": 107
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7244252047910893e-05,
+      "loss": 0.4443,
+      "step": 108
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.718701387683824e-05,
+      "loss": 0.4216,
+      "step": 109
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7129284482913973e-05,
+      "loss": 0.4337,
+      "step": 110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.4494,
+      "step": 111
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7012367842724887e-05,
+      "loss": 0.4231,
+      "step": 112
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6953188587557122e-05,
+      "loss": 0.4385,
+      "step": 113
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6893534091185658e-05,
+      "loss": 0.4513,
+      "step": 114
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6833408430916085e-05,
+      "loss": 0.4532,
+      "step": 115
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.4427,
+      "step": 116
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6711760088641197e-05,
+      "loss": 0.449,
+      "step": 117
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6650245721138483e-05,
+      "loss": 0.4229,
+      "step": 118
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.658827681817458e-05,
+      "loss": 0.428,
+      "step": 119
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6525857615241686e-05,
+      "loss": 0.4522,
+      "step": 120
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.646299237860941e-05,
+      "loss": 0.4357,
+      "step": 121
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6399685405033168e-05,
+      "loss": 0.4428,
+      "step": 122
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6335941021460507e-05,
+      "loss": 0.4299,
+      "step": 123
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6271763584735373e-05,
+      "loss": 0.4459,
+      "step": 124
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6207157481300315e-05,
+      "loss": 0.446,
+      "step": 125
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6142127126896682e-05,
+      "loss": 0.433,
+      "step": 126
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6076676966262815e-05,
+      "loss": 0.4322,
+      "step": 127
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6010811472830253e-05,
+      "loss": 0.4187,
+      "step": 128
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5944535148417982e-05,
+      "loss": 0.4231,
+      "step": 129
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.4323,
+      "step": 130
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5810768154019386e-05,
+      "loss": 0.4322,
+      "step": 131
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5743286626829437e-05,
+      "loss": 0.4322,
+      "step": 132
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5675412553627638e-05,
+      "loss": 0.4192,
+      "step": 133
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.560715057351673e-05,
+      "loss": 0.3991,
+      "step": 134
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5538505352112373e-05,
+      "loss": 0.4059,
+      "step": 135
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.3876,
+      "step": 136
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5400083978535475e-05,
+      "loss": 0.4075,
+      "step": 137
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.533031728727994e-05,
+      "loss": 0.4278,
+      "step": 138
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.526018627591834e-05,
+      "loss": 0.4178,
+      "step": 139
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5189695737812153e-05,
+      "loss": 0.4035,
+      "step": 140
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5118850490896012e-05,
+      "loss": 0.3904,
+      "step": 141
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.504765537734844e-05,
+      "loss": 0.3911,
+      "step": 142
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4976115263260876e-05,
+      "loss": 0.3752,
+      "step": 143
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4904235038305084e-05,
+      "loss": 0.4027,
+      "step": 144
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4832019615398962e-05,
+      "loss": 0.3846,
+      "step": 145
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 0.3962,
+      "step": 146
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4686602941621618e-05,
+      "loss": 0.3967,
+      "step": 147
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.461341162978688e-05,
+      "loss": 0.392,
+      "step": 148
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.4096,
+      "step": 149
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4466088068528068e-05,
+      "loss": 0.4014,
+      "step": 150
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4391965888473705e-05,
+      "loss": 0.3856,
+      "step": 151
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4317543523384928e-05,
+      "loss": 0.3677,
+      "step": 152
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4242826059931538e-05,
+      "loss": 0.3858,
+      "step": 153
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4167818604952906e-05,
+      "loss": 0.3814,
+      "step": 154
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.409252628510894e-05,
+      "loss": 0.4017,
+      "step": 155
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.3981,
+      "step": 156
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3941107654463619e-05,
+      "loss": 0.3867,
+      "step": 157
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3864991692924524e-05,
+      "loss": 0.3948,
+      "step": 158
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3788611564337277e-05,
+      "loss": 0.3747,
+      "step": 159
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3711972489182208e-05,
+      "loss": 0.3866,
+      "step": 160
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3635079705638298e-05,
+      "loss": 0.3982,
+      "step": 161
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3557938469225167e-05,
+      "loss": 0.3835,
+      "step": 162
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3480554052443847e-05,
+      "loss": 0.3955,
+      "step": 163
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3402931744416432e-05,
+      "loss": 0.396,
+      "step": 164
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.332507685052457e-05,
+      "loss": 0.3615,
+      "step": 165
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3246994692046837e-05,
+      "loss": 0.3688,
+      "step": 166
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3168690605795044e-05,
+      "loss": 0.379,
+      "step": 167
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.3919,
+      "step": 168
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3011438072693077e-05,
+      "loss": 0.379,
+      "step": 169
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.293250037384465e-05,
+      "loss": 0.3981,
+      "step": 170
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2853362242491054e-05,
+      "loss": 0.3692,
+      "step": 171
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2774029087618448e-05,
+      "loss": 0.3874,
+      "step": 172
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.269450633154258e-05,
+      "loss": 0.38,
+      "step": 173
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.26147994095382e-05,
+      "loss": 0.3664,
+      "step": 174
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.253491376946754e-05,
+      "loss": 0.3683,
+      "step": 175
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.3811,
+      "step": 176
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2374628187278888e-05,
+      "loss": 0.3797,
+      "step": 177
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2294239200467516e-05,
+      "loss": 0.3807,
+      "step": 178
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2213693405454345e-05,
+      "loss": 0.3739,
+      "step": 179
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.213299630743747e-05,
+      "loss": 0.368,
+      "step": 180
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2052153421956343e-05,
+      "loss": 0.3832,
+      "step": 181
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1971170274514802e-05,
+      "loss": 0.3755,
+      "step": 182
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1890052400203405e-05,
+      "loss": 0.3721,
+      "step": 183
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1808805343321102e-05,
+      "loss": 0.3693,
+      "step": 184
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1727434656996306e-05,
+      "loss": 0.3726,
+      "step": 185
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.3628,
+      "step": 186
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.3836,
+      "step": 187
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.148263647711842e-05,
+      "loss": 0.3655,
+      "step": 188
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.140082696760078e-05,
+      "loss": 0.3545,
+      "step": 189
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1318921713420691e-05,
+      "loss": 0.3729,
+      "step": 190
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.123692631269348e-05,
+      "loss": 0.3612,
+      "step": 191
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1154846369695864e-05,
+      "loss": 0.3791,
+      "step": 192
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.107268749448292e-05,
+      "loss": 0.3442,
+      "step": 193
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.099045530250463e-05,
+      "loss": 0.3685,
+      "step": 194
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0908155414222083e-05,
+      "loss": 0.3605,
+      "step": 195
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.3586,
+      "step": 196
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0743375053338879e-05,
+      "loss": 0.3606,
+      "step": 197
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0660905843256995e-05,
+      "loss": 0.3685,
+      "step": 198
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0578391461138642e-05,
+      "loss": 0.3423,
+      "step": 199
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0495837546732224e-05,
+      "loss": 0.3627,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0413249742488132e-05,
+      "loss": 0.3553,
+      "step": 201
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0330633693173083e-05,
+      "loss": 0.3589,
+      "step": 202
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0247995045484303e-05,
+      "loss": 0.3459,
+      "step": 203
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0165339447663586e-05,
+      "loss": 0.3685,
+      "step": 204
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.008267254911125e-05,
+      "loss": 0.362,
+      "step": 205
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1e-05,
+      "loss": 0.3458,
+      "step": 206
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.917327450888751e-06,
+      "loss": 0.3453,
+      "step": 207
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.834660552336415e-06,
+      "loss": 0.3375,
+      "step": 208
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.7520049545157e-06,
+      "loss": 0.3785,
+      "step": 209
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.669366306826919e-06,
+      "loss": 0.3649,
+      "step": 210
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.586750257511868e-06,
+      "loss": 0.3462,
+      "step": 211
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.504162453267776e-06,
+      "loss": 0.3458,
+      "step": 212
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.421608538861361e-06,
+      "loss": 0.3471,
+      "step": 213
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.339094156743007e-06,
+      "loss": 0.3649,
+      "step": 214
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.256624946661126e-06,
+      "loss": 0.3558,
+      "step": 215
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.3356,
+      "step": 216
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.091844585777919e-06,
+      "loss": 0.3252,
+      "step": 217
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.009544697495373e-06,
+      "loss": 0.3354,
+      "step": 218
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.927312505517086e-06,
+      "loss": 0.323,
+      "step": 219
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.84515363030414e-06,
+      "loss": 0.3416,
+      "step": 220
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.763073687306523e-06,
+      "loss": 0.3422,
+      "step": 221
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.68107828657931e-06,
+      "loss": 0.3504,
+      "step": 222
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.599173032399222e-06,
+      "loss": 0.3416,
+      "step": 223
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.51736352288158e-06,
+      "loss": 0.3433,
+      "step": 224
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.3428,
+      "step": 225
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.35405409719266e-06,
+      "loss": 0.3247,
+      "step": 226
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.2725653430037e-06,
+      "loss": 0.3468,
+      "step": 227
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.191194656678905e-06,
+      "loss": 0.3345,
+      "step": 228
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.109947599796599e-06,
+      "loss": 0.3538,
+      "step": 229
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.0288297254852e-06,
+      "loss": 0.3226,
+      "step": 230
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.947846578043658e-06,
+      "loss": 0.3383,
+      "step": 231
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.867003692562533e-06,
+      "loss": 0.3451,
+      "step": 232
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.786306594545658e-06,
+      "loss": 0.3489,
+      "step": 233
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.705760799532485e-06,
+      "loss": 0.3336,
+      "step": 234
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.625371812721115e-06,
+      "loss": 0.343,
+      "step": 235
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.3559,
+      "step": 236
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.46508623053246e-06,
+      "loss": 0.3399,
+      "step": 237
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.385200590461803e-06,
+      "loss": 0.3366,
+      "step": 238
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.305493668457421e-06,
+      "loss": 0.3328,
+      "step": 239
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.225970912381557e-06,
+      "loss": 0.3518,
+      "step": 240
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.14663775750895e-06,
+      "loss": 0.3355,
+      "step": 241
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.067499626155354e-06,
+      "loss": 0.309,
+      "step": 242
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.988561927306927e-06,
+      "loss": 0.3517,
+      "step": 243
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.3139,
+      "step": 244
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.831309394204957e-06,
+      "loss": 0.3344,
+      "step": 245
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.7530053079531664e-06,
+      "loss": 0.3276,
+      "step": 246
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.674923149475433e-06,
+      "loss": 0.3427,
+      "step": 247
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.59706825558357e-06,
+      "loss": 0.3124,
+      "step": 248
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.519445947556156e-06,
+      "loss": 0.3219,
+      "step": 249
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.442061530774835e-06,
+      "loss": 0.3247,
+      "step": 250
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.364920294361701e-06,
+      "loss": 0.323,
+      "step": 251
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.2880275108177915e-06,
+      "loss": 0.3198,
+      "step": 252
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.211388435662722e-06,
+      "loss": 0.3259,
+      "step": 253
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.13500830707548e-06,
+      "loss": 0.3237,
+      "step": 254
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.058892345536387e-06,
+      "loss": 0.3235,
+      "step": 255
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.3133,
+      "step": 256
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.907473714891061e-06,
+      "loss": 0.3261,
+      "step": 257
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.832181395047099e-06,
+      "loss": 0.3524,
+      "step": 258
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.7571739400684644e-06,
+      "loss": 0.3447,
+      "step": 259
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.6824564766150724e-06,
+      "loss": 0.3377,
+      "step": 260
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.608034111526298e-06,
+      "loss": 0.3128,
+      "step": 261
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.533911931471936e-06,
+      "loss": 0.3247,
+      "step": 262
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.3273,
+      "step": 263
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.386588370213124e-06,
+      "loss": 0.334,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.3133970583783865e-06,
+      "loss": 0.3001,
+      "step": 265
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.240526069629265e-06,
+      "loss": 0.3199,
+      "step": 266
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.167980384601041e-06,
+      "loss": 0.3307,
+      "step": 267
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.095764961694923e-06,
+      "loss": 0.2982,
+      "step": 268
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.023884736739132e-06,
+      "loss": 0.3142,
+      "step": 269
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.952344622651566e-06,
+      "loss": 0.3093,
+      "step": 270
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.881149509103993e-06,
+      "loss": 0.2976,
+      "step": 271
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.8103042621878515e-06,
+      "loss": 0.3136,
+      "step": 272
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.739813724081661e-06,
+      "loss": 0.2955,
+      "step": 273
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.669682712720065e-06,
+      "loss": 0.2928,
+      "step": 274
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.599916021464531e-06,
+      "loss": 0.2877,
+      "step": 275
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.2912,
+      "step": 276
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.4614946478876305e-06,
+      "loss": 0.2907,
+      "step": 277
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.392849426483275e-06,
+      "loss": 0.3007,
+      "step": 278
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.324587446372365e-06,
+      "loss": 0.2926,
+      "step": 279
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.256713373170565e-06,
+      "loss": 0.283,
+      "step": 280
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.189231845980618e-06,
+      "loss": 0.2867,
+      "step": 281
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.2894,
+      "step": 282
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.055464851582022e-06,
+      "loss": 0.3048,
+      "step": 283
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.989188527169749e-06,
+      "loss": 0.2936,
+      "step": 284
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.923323033737188e-06,
+      "loss": 0.2986,
+      "step": 285
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.857872873103322e-06,
+      "loss": 0.2929,
+      "step": 286
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.792842518699689e-06,
+      "loss": 0.292,
+      "step": 287
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.72823641526463e-06,
+      "loss": 0.3029,
+      "step": 288
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6640589785394955e-06,
+      "loss": 0.2779,
+      "step": 289
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.6003145949668338e-06,
+      "loss": 0.2852,
+      "step": 290
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.5370076213905904e-06,
+      "loss": 0.2813,
+      "step": 291
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4741423847583134e-06,
+      "loss": 0.3127,
+      "step": 292
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.4117231818254205e-06,
+      "loss": 0.3079,
+      "step": 293
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.349754278861517e-06,
+      "loss": 0.2902,
+      "step": 294
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.288239911358807e-06,
+      "loss": 0.3058,
+      "step": 295
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.3047,
+      "step": 296
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1665915690839165e-06,
+      "loss": 0.2896,
+      "step": 297
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1064659088143424e-06,
+      "loss": 0.2874,
+      "step": 298
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0468114124428806e-06,
+      "loss": 0.3135,
+      "step": 299
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9876321572751143e-06,
+      "loss": 0.2885,
+      "step": 300
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.3046,
+      "step": 301
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.8707155170860303e-06,
+      "loss": 0.3039,
+      "step": 302
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.812986123161762e-06,
+      "loss": 0.2818,
+      "step": 303
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.7557479520891104e-06,
+      "loss": 0.2984,
+      "step": 304
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.6990049160210386e-06,
+      "loss": 0.3234,
+      "step": 305
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.642760893268684e-06,
+      "loss": 0.2838,
+      "step": 306
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.587019728036292e-06,
+      "loss": 0.2963,
+      "step": 307
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.5317852301584642e-06,
+      "loss": 0.2988,
+      "step": 308
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4770611748397556e-06,
+      "loss": 0.2874,
+      "step": 309
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.422851302396655e-06,
+      "loss": 0.288,
+      "step": 310
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.369159318001937e-06,
+      "loss": 0.2732,
+      "step": 311
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.315988891431412e-06,
+      "loss": 0.2854,
+      "step": 312
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.263343656813107e-06,
+      "loss": 0.2872,
+      "step": 313
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.211227212378877e-06,
+      "loss": 0.2925,
+      "step": 314
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1596431202184707e-06,
+      "loss": 0.2951,
+      "step": 315
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.2824,
+      "step": 316
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0580860589092897e-06,
+      "loss": 0.3029,
+      "step": 317
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.008120031050753e-06,
+      "loss": 0.3057,
+      "step": 318
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9587002375720864e-06,
+      "loss": 0.2956,
+      "step": 319
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.2965,
+      "step": 320
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.861512827298051e-06,
+      "loss": 0.2938,
+      "step": 321
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8137518531330768e-06,
+      "loss": 0.2835,
+      "step": 322
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7665503981547428e-06,
+      "loss": 0.2936,
+      "step": 323
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7199116885197996e-06,
+      "loss": 0.289,
+      "step": 324
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6738389119220966e-06,
+      "loss": 0.2895,
+      "step": 325
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6283352173747148e-06,
+      "loss": 0.279,
+      "step": 326
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5834037149947291e-06,
+      "loss": 0.271,
+      "step": 327
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5390474757906449e-06,
+      "loss": 0.2819,
+      "step": 328
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4952695314524912e-06,
+      "loss": 0.2952,
+      "step": 329
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4520728741446087e-06,
+      "loss": 0.2705,
+      "step": 330
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.409460456301147e-06,
+      "loss": 0.2822,
+      "step": 331
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.367435190424261e-06,
+      "loss": 0.2668,
+      "step": 332
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.3259999488850473e-06,
+      "loss": 0.2896,
+      "step": 333
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2851575637272262e-06,
+      "loss": 0.2762,
+      "step": 334
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2449108264735721e-06,
+      "loss": 0.2644,
+      "step": 335
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.2785,
+      "step": 336
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1662152580231145e-06,
+      "loss": 0.2992,
+      "step": 337
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.127771805563882e-06,
+      "loss": 0.2974,
+      "step": 338
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.2813,
+      "step": 339
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0527067017923654e-06,
+      "loss": 0.2929,
+      "step": 340
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0160901810802114e-06,
+      "loss": 0.27,
+      "step": 341
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.800876986704111e-07,
+      "loss": 0.2945,
+      "step": 342
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.447017152848126e-07,
+      "loss": 0.2761,
+      "step": 343
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.09934649508375e-07,
+      "loss": 0.2895,
+      "step": 344
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.757888776238621e-07,
+      "loss": 0.2921,
+      "step": 345
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.42266733449425e-07,
+      "loss": 0.2847,
+      "step": 346
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.093705081790892e-07,
+      "loss": 0.2773,
+      "step": 347
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.771024502261526e-07,
+      "loss": 0.2861,
+      "step": 348
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.454647650695157e-07,
+      "loss": 0.2662,
+      "step": 349
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.144596151029304e-07,
+      "loss": 0.285,
+      "step": 350
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.840891194872112e-07,
+      "loss": 0.2989,
+      "step": 351
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.543553540053926e-07,
+      "loss": 0.2809,
+      "step": 352
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.252603509208466e-07,
+      "loss": 0.2923,
+      "step": 353
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.968060988383884e-07,
+      "loss": 0.2738,
+      "step": 354
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.689945425683474e-07,
+      "loss": 0.274,
+      "step": 355
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.2899,
+      "step": 356
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.15307076939906e-07,
+      "loss": 0.2874,
+      "step": 357
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.2747,
+      "step": 358
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.642126316525586e-07,
+      "loss": 0.293,
+      "step": 359
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.396421846564236e-07,
+      "loss": 0.2835,
+      "step": 360
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.1572517541747294e-07,
+      "loss": 0.2714,
+      "step": 361
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.924632386315186e-07,
+      "loss": 0.2856,
+      "step": 362
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.698579642210398e-07,
+      "loss": 0.285,
+      "step": 363
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.4791089722651437e-07,
+      "loss": 0.2772,
+      "step": 364
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.2662353770081755e-07,
+      "loss": 0.2763,
+      "step": 365
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.059973406066963e-07,
+      "loss": 0.2934,
+      "step": 366
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.860337157173243e-07,
+      "loss": 0.3004,
+      "step": 367
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.667340275199426e-07,
+      "loss": 0.2779,
+      "step": 368
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.4809959512260285e-07,
+      "loss": 0.2934,
+      "step": 369
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.3013169216400732e-07,
+      "loss": 0.2791,
+      "step": 370
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.1283154672645522e-07,
+      "loss": 0.2807,
+      "step": 371
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9620034125190645e-07,
+      "loss": 0.2775,
+      "step": 372
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.8023921246116405e-07,
+      "loss": 0.2835,
+      "step": 373
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.6494925127617632e-07,
+      "loss": 0.2821,
+      "step": 374
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.5033150274548325e-07,
+      "loss": 0.2876,
+      "step": 375
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.2921,
+      "step": 376
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.283,
+      "step": 377
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1052129398531508e-07,
+      "loss": 0.2879,
+      "step": 378
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.86019266548821e-08,
+      "loss": 0.2763,
+      "step": 379
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.735930673024806e-08,
+      "loss": 0.2684,
+      "step": 380
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.679420262954984e-08,
+      "loss": 0.2827,
+      "step": 381
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.690733646361858e-08,
+      "loss": 0.2894,
+      "step": 382
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.769938398662356e-08,
+      "loss": 0.2813,
+      "step": 383
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 4.9170974549885844e-08,
+      "loss": 0.2731,
+      "step": 384
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.132269105886155e-08,
+      "loss": 0.286,
+      "step": 385
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.4155069933301535e-08,
+      "loss": 0.2863,
+      "step": 386
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.766860107058844e-08,
+      "loss": 0.2895,
+      "step": 387
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.1863727812254653e-08,
+      "loss": 0.2779,
+      "step": 388
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.674084691367428e-08,
+      "loss": 0.2736,
+      "step": 389
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.230030851695263e-08,
+      "loss": 0.2897,
+      "step": 390
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.542416126989805e-09,
+      "loss": 0.291,
+      "step": 391
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.467426590739511e-09,
+      "loss": 0.2785,
+      "step": 392
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.0755500796531e-09,
+      "loss": 0.2855,
+      "step": 393
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.3669500753099586e-09,
+      "loss": 0.2707,
+      "step": 394
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.4174335825420955e-10,
+      "loss": 0.2936,
+      "step": 395
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0,
+      "loss": 0.2833,
+      "step": 396
+    },
+    {
+      "epoch": 2.99,
+      "step": 396,
+      "total_flos": 4.052532987894432e+18,
+      "train_loss": 0.15283302684323957,
+      "train_runtime": 60602.7591,
+      "train_samples_per_second": 1.678,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "max_steps": 396,
+  "num_train_epochs": 3,
+  "total_flos": 4.052532987894432e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a32968961c2cdae79ec68dff0214eac20a47ce0180721b2805cd5ea0c59966
+oid sha256:24be371cf21eb67b5e97a910293513b1f90d6b8cde5191e5c6849e68c46b2ff6
 size 3835