add chechpoint

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "models/wizard-vicuna-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

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:fd6d20e91e990759bb0dcdf3ce4f87229ca5847c7a4b6e8236ebbb52ffecb4fe
+size 9956542859

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd95ea3f3e5f3e101282627b0737332d70f1b7e78e62759d4b2bef99b481dbef
+size 9940855489

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a07ea575ad05d172e792e7614e36b481e97f991b9045fbdf2d376ea8ca4212
+size 9940855919

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c814527c14623b590e88472bf753840a4557c7bb841c50ebae492722cc2e02
+size 9867414329

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30224b7359ee428e4a490c48566fce6d09bfc51a66b380f7504fa83955fa14ef
+size 9867456001

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bb2cce8f3fe67a0e3bf4c7994bf116ddce2ddc74c3c4a2ea8b0a08748c637d
+size 2490476143

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063462400
+  },
+  "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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1537 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.991097922848665,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.1553,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.1604,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.0248,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.9345,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.8861,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.8385,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.806,
+      "step": 7
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.7936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.752,
+      "step": 9
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.7385,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2e-05,
+      "loss": 0.7177,
+      "step": 11
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9999150370633987e-05,
+      "loss": 0.7116,
+      "step": 12
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9996601626909962e-05,
+      "loss": 0.697,
+      "step": 13
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9992354201925427e-05,
+      "loss": 0.6884,
+      "step": 14
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.998640881742778e-05,
+      "loss": 0.6752,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.997876648369168e-05,
+      "loss": 0.6808,
+      "step": 16
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.996942849934735e-05,
+      "loss": 0.6427,
+      "step": 17
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9958396451159937e-05,
+      "loss": 0.6587,
+      "step": 18
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9945672213759872e-05,
+      "loss": 0.6427,
+      "step": 19
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.993125794932429e-05,
+      "loss": 0.6251,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9915156107209673e-05,
+      "loss": 0.6257,
+      "step": 21
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.98973694235356e-05,
+      "loss": 0.6167,
+      "step": 22
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9877900920719825e-05,
+      "loss": 0.596,
+      "step": 23
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9856753906964686e-05,
+      "loss": 0.6116,
+      "step": 24
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.983393197569497e-05,
+      "loss": 0.6072,
+      "step": 25
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.980943900494727e-05,
+      "loss": 0.599,
+      "step": 26
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9783279156711022e-05,
+      "loss": 0.5904,
+      "step": 27
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.975545687622129e-05,
+      "loss": 0.5887,
+      "step": 28
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.972597689120338e-05,
+      "loss": 0.585,
+      "step": 29
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9694844211069477e-05,
+      "loss": 0.5813,
+      "step": 30
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.966206412606745e-05,
+      "loss": 0.5847,
+      "step": 31
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9627642206381864e-05,
+      "loss": 0.5883,
+      "step": 32
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9591584301187477e-05,
+      "loss": 0.5879,
+      "step": 33
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9553896537655317e-05,
+      "loss": 0.5753,
+      "step": 34
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.951458531991151e-05,
+      "loss": 0.5601,
+      "step": 35
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9473657327949055e-05,
+      "loss": 0.5665,
+      "step": 36
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9431119516492725e-05,
+      "loss": 0.5651,
+      "step": 37
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9386979113817283e-05,
+      "loss": 0.5695,
+      "step": 38
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.934124362051919e-05,
+      "loss": 0.5712,
+      "step": 39
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9293920808242084e-05,
+      "loss": 0.5486,
+      "step": 40
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.924501871835616e-05,
+      "loss": 0.5547,
+      "step": 41
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9194545660591753e-05,
+      "loss": 0.55,
+      "step": 42
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9142510211627264e-05,
+      "loss": 0.5454,
+      "step": 43
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9088921213631803e-05,
+      "loss": 0.5496,
+      "step": 44
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9033787772762647e-05,
+      "loss": 0.551,
+      "step": 45
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8977119257617878e-05,
+      "loss": 0.5534,
+      "step": 46
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8918925297644418e-05,
+      "loss": 0.5368,
+      "step": 47
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8859215781501727e-05,
+      "loss": 0.5219,
+      "step": 48
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8798000855381472e-05,
+      "loss": 0.5389,
+      "step": 49
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.873529092128343e-05,
+      "loss": 0.5252,
+      "step": 50
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8671096635247914e-05,
+      "loss": 0.5377,
+      "step": 51
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.860542890554503e-05,
+      "loss": 0.5206,
+      "step": 52
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.853829889082109e-05,
+      "loss": 0.5387,
+      "step": 53
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8469717998202464e-05,
+      "loss": 0.5224,
+      "step": 54
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8399697881357214e-05,
+      "loss": 0.523,
+      "step": 55
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8328250438514837e-05,
+      "loss": 0.5122,
+      "step": 56
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8255387810444447e-05,
+      "loss": 0.5245,
+      "step": 57
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.818112237839174e-05,
+      "loss": 0.5251,
+      "step": 58
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.810546676197511e-05,
+      "loss": 0.524,
+      "step": 59
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8028433817041237e-05,
+      "loss": 0.5161,
+      "step": 60
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7950036633480557e-05,
+      "loss": 0.5339,
+      "step": 61
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.787028853300294e-05,
+      "loss": 0.5087,
+      "step": 62
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7789203066874e-05,
+      "loss": 0.5284,
+      "step": 63
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7706794013612367e-05,
+      "loss": 0.5052,
+      "step": 64
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7623075376648374e-05,
+      "loss": 0.5093,
+      "step": 65
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7538061381944524e-05,
+      "loss": 0.5005,
+      "step": 66
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.745176647557809e-05,
+      "loss": 0.5097,
+      "step": 67
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7364205321286393e-05,
+      "loss": 0.516,
+      "step": 68
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7275392797975034e-05,
+      "loss": 0.51,
+      "step": 69
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.718534399718959e-05,
+      "loss": 0.5025,
+      "step": 70
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.709407422055116e-05,
+      "loss": 0.4973,
+      "step": 71
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.700159897715624e-05,
+      "loss": 0.4971,
+      "step": 72
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6907933980941312e-05,
+      "loss": 0.4964,
+      "step": 73
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.681309514801265e-05,
+      "loss": 0.5095,
+      "step": 74
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6717098593941753e-05,
+      "loss": 0.5021,
+      "step": 75
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.661996063102689e-05,
+      "loss": 0.5028,
+      "step": 76
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6521697765521232e-05,
+      "loss": 0.4901,
+      "step": 77
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.642232669482801e-05,
+      "loss": 0.4853,
+      "step": 78
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6321864304663174e-05,
+      "loss": 0.4929,
+      "step": 79
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.62203276661861e-05,
+      "loss": 0.4962,
+      "step": 80
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6117734033098744e-05,
+      "loss": 0.4898,
+      "step": 81
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6014100838713796e-05,
+      "loss": 0.4684,
+      "step": 82
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.59094456929923e-05,
+      "loss": 0.4905,
+      "step": 83
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.580378637955128e-05,
+      "loss": 0.4744,
+      "step": 84
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5697140852641835e-05,
+      "loss": 0.4604,
+      "step": 85
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5589527234098247e-05,
+      "loss": 0.4802,
+      "step": 86
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5480963810258614e-05,
+      "loss": 0.4716,
+      "step": 87
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5371469028857534e-05,
+      "loss": 0.4654,
+      "step": 88
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5261061495891345e-05,
+      "loss": 0.4869,
+      "step": 89
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.514975997245649e-05,
+      "loss": 0.4659,
+      "step": 90
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5037583371561538e-05,
+      "loss": 0.4681,
+      "step": 91
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4924550754913341e-05,
+      "loss": 0.4534,
+      "step": 92
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4810681329677988e-05,
+      "loss": 0.4569,
+      "step": 93
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4695994445216985e-05,
+      "loss": 0.4659,
+      "step": 94
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.458050958979933e-05,
+      "loss": 0.4657,
+      "step": 95
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4464246387289913e-05,
+      "loss": 0.4735,
+      "step": 96
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4347224593814946e-05,
+      "loss": 0.4599,
+      "step": 97
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4229464094404866e-05,
+      "loss": 0.4519,
+      "step": 98
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4110984899615367e-05,
+      "loss": 0.4484,
+      "step": 99
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3991807142127082e-05,
+      "loss": 0.4454,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3871951073324508e-05,
+      "loss": 0.4548,
+      "step": 101
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3751437059854809e-05,
+      "loss": 0.4573,
+      "step": 102
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3630285580166946e-05,
+      "loss": 0.4429,
+      "step": 103
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3508517221031898e-05,
+      "loss": 0.463,
+      "step": 104
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3386152674044421e-05,
+      "loss": 0.4579,
+      "step": 105
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3263212732107014e-05,
+      "loss": 0.441,
+      "step": 106
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3139718285896657e-05,
+      "loss": 0.4566,
+      "step": 107
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3015690320314952e-05,
+      "loss": 0.4614,
+      "step": 108
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2891149910922267e-05,
+      "loss": 0.4564,
+      "step": 109
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.276611822035641e-05,
+      "loss": 0.4416,
+      "step": 110
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.264061649473657e-05,
+      "loss": 0.4506,
+      "step": 111
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2514666060053075e-05,
+      "loss": 0.4343,
+      "step": 112
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2388288318543513e-05,
+      "loss": 0.4395,
+      "step": 113
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2261504745055963e-05,
+      "loss": 0.4525,
+      "step": 114
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2134336883399855e-05,
+      "loss": 0.4418,
+      "step": 115
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.2006806342685127e-05,
+      "loss": 0.4421,
+      "step": 116
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1878934793650273e-05,
+      "loss": 0.4347,
+      "step": 117
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1750743964979919e-05,
+      "loss": 0.4375,
+      "step": 118
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1622255639612553e-05,
+      "loss": 0.4395,
+      "step": 119
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1493491651039077e-05,
+      "loss": 0.4325,
+      "step": 120
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1364473879592674e-05,
+      "loss": 0.4393,
+      "step": 121
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1235224248730821e-05,
+      "loss": 0.4385,
+      "step": 122
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.11057647213099e-05,
+      "loss": 0.4364,
+      "step": 123
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0976117295853155e-05,
+      "loss": 0.4499,
+      "step": 124
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0846304002812564e-05,
+      "loss": 0.428,
+      "step": 125
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0716346900825298e-05,
+      "loss": 0.4225,
+      "step": 126
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0586268072965395e-05,
+      "loss": 0.4303,
+      "step": 127
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0456089622991264e-05,
+      "loss": 0.4216,
+      "step": 128
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0325833671589687e-05,
+      "loss": 0.4241,
+      "step": 129
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0195522352616942e-05,
+      "loss": 0.444,
+      "step": 130
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0065177809337703e-05,
+      "loss": 0.4296,
+      "step": 131
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.934822190662299e-06,
+      "loss": 0.4177,
+      "step": 132
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.804477647383061e-06,
+      "loss": 0.4342,
+      "step": 133
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.674166328410318e-06,
+      "loss": 0.4281,
+      "step": 134
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.543910377008741e-06,
+      "loss": 0.4379,
+      "step": 135
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.413731927034607e-06,
+      "loss": 0.4059,
+      "step": 136
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.283653099174704e-06,
+      "loss": 0.4263,
+      "step": 137
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.15369599718744e-06,
+      "loss": 0.4219,
+      "step": 138
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.023882704146848e-06,
+      "loss": 0.4231,
+      "step": 139
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.894235278690104e-06,
+      "loss": 0.406,
+      "step": 140
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.764775751269184e-06,
+      "loss": 0.4154,
+      "step": 141
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.63552612040733e-06,
+      "loss": 0.4025,
+      "step": 142
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.506508348960924e-06,
+      "loss": 0.4263,
+      "step": 143
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.377744360387447e-06,
+      "loss": 0.4104,
+      "step": 144
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.249256035020086e-06,
+      "loss": 0.4046,
+      "step": 145
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.12106520634973e-06,
+      "loss": 0.4109,
+      "step": 146
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.993193657314874e-06,
+      "loss": 0.4103,
+      "step": 147
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.865663116600149e-06,
+      "loss": 0.407,
+      "step": 148
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.738495254944042e-06,
+      "loss": 0.4135,
+      "step": 149
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.611711681456493e-06,
+      "loss": 0.4103,
+      "step": 150
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.485333939946926e-06,
+      "loss": 0.4002,
+      "step": 151
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.359383505263431e-06,
+      "loss": 0.4108,
+      "step": 152
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.233881779643595e-06,
+      "loss": 0.4185,
+      "step": 153
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.108850089077736e-06,
+      "loss": 0.4168,
+      "step": 154
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.984309679685049e-06,
+      "loss": 0.4153,
+      "step": 155
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.86028171410335e-06,
+      "loss": 0.3995,
+      "step": 156
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.736787267892991e-06,
+      "loss": 0.4058,
+      "step": 157
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.613847325955578e-06,
+      "loss": 0.3968,
+      "step": 158
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.491482778968103e-06,
+      "loss": 0.4005,
+      "step": 159
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.369714419833056e-06,
+      "loss": 0.4184,
+      "step": 160
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.2485629401451954e-06,
+      "loss": 0.3958,
+      "step": 161
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.128048926675494e-06,
+      "loss": 0.4159,
+      "step": 162
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.0081928578729235e-06,
+      "loss": 0.4051,
+      "step": 163
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.889015100384636e-06,
+      "loss": 0.3841,
+      "step": 164
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.770535905595138e-06,
+      "loss": 0.3989,
+      "step": 165
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.652775406185056e-06,
+      "loss": 0.3979,
+      "step": 166
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.535753612710091e-06,
+      "loss": 0.402,
+      "step": 167
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.419490410200675e-06,
+      "loss": 0.4114,
+      "step": 168
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.304005554783015e-06,
+      "loss": 0.3852,
+      "step": 169
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.189318670322016e-06,
+      "loss": 0.4014,
+      "step": 170
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.075449245086661e-06,
+      "loss": 0.3757,
+      "step": 171
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.962416628438466e-06,
+      "loss": 0.3987,
+      "step": 172
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.850240027543509e-06,
+      "loss": 0.3715,
+      "step": 173
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.738938504108659e-06,
+      "loss": 0.3829,
+      "step": 174
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.6285309711424706e-06,
+      "loss": 0.3853,
+      "step": 175
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.519036189741386e-06,
+      "loss": 0.3796,
+      "step": 176
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.410472765901755e-06,
+      "loss": 0.3854,
+      "step": 177
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.302859147358168e-06,
+      "loss": 0.373,
+      "step": 178
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.196213620448724e-06,
+      "loss": 0.3872,
+      "step": 179
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.0905543070077036e-06,
+      "loss": 0.3873,
+      "step": 180
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.985899161286205e-06,
+      "loss": 0.3743,
+      "step": 181
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.882265966901257e-06,
+      "loss": 0.3845,
+      "step": 182
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.7796723338138995e-06,
+      "loss": 0.3705,
+      "step": 183
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6781356953368286e-06,
+      "loss": 0.3892,
+      "step": 184
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.5776733051719935e-06,
+      "loss": 0.3832,
+      "step": 185
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4783022344787698e-06,
+      "loss": 0.3597,
+      "step": 186
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.380039368973115e-06,
+      "loss": 0.3861,
+      "step": 187
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.2829014060582498e-06,
+      "loss": 0.3847,
+      "step": 188
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1869048519873514e-06,
+      "loss": 0.3665,
+      "step": 189
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0920660190586893e-06,
+      "loss": 0.3695,
+      "step": 190
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.998401022843761e-06,
+      "loss": 0.3818,
+      "step": 191
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.9059257794488428e-06,
+      "loss": 0.3738,
+      "step": 192
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8146560028104155e-06,
+      "loss": 0.3733,
+      "step": 193
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.724607202024969e-06,
+      "loss": 0.3745,
+      "step": 194
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.635794678713611e-06,
+      "loss": 0.387,
+      "step": 195
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.5482335244219114e-06,
+      "loss": 0.3644,
+      "step": 196
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4619386180554783e-06,
+      "loss": 0.3686,
+      "step": 197
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3769246233516243e-06,
+      "loss": 0.3674,
+      "step": 198
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.2932059863876364e-06,
+      "loss": 0.3723,
+      "step": 199
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.210796933126005e-06,
+      "loss": 0.3715,
+      "step": 200
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.129711466997062e-06,
+      "loss": 0.3498,
+      "step": 201
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.049963366519446e-06,
+      "loss": 0.3688,
+      "step": 202
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9715661829587653e-06,
+      "loss": 0.3791,
+      "step": 203
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.8945332380248914e-06,
+      "loss": 0.3668,
+      "step": 204
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8188776216082604e-06,
+      "loss": 0.3626,
+      "step": 205
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7446121895555556e-06,
+      "loss": 0.3623,
+      "step": 206
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6717495614851654e-06,
+      "loss": 0.3736,
+      "step": 207
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6003021186427892e-06,
+      "loss": 0.3863,
+      "step": 208
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5302820017975396e-06,
+      "loss": 0.3607,
+      "step": 209
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4617011091789135e-06,
+      "loss": 0.3533,
+      "step": 210
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.3945710944549705e-06,
+      "loss": 0.3613,
+      "step": 211
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.3289033647520878e-06,
+      "loss": 0.3776,
+      "step": 212
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2647090787165694e-06,
+      "loss": 0.3623,
+      "step": 213
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.201999144618531e-06,
+      "loss": 0.36,
+      "step": 214
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1407842184982786e-06,
+      "loss": 0.3683,
+      "step": 215
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.0810747023555879e-06,
+      "loss": 0.3642,
+      "step": 216
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0228807423821262e-06,
+      "loss": 0.3586,
+      "step": 217
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.662122272373574e-07,
+      "loss": 0.3667,
+      "step": 218
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.110787863682002e-07,
+      "loss": 0.3698,
+      "step": 219
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.574897883727384e-07,
+      "loss": 0.3607,
+      "step": 220
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.054543394082503e-07,
+      "loss": 0.3726,
+      "step": 221
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.549812816438395e-07,
+      "loss": 0.3602,
+      "step": 222
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.06079191757918e-07,
+      "loss": 0.3668,
+      "step": 223
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.587563794808127e-07,
+      "loss": 0.3639,
+      "step": 224
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.130208861827203e-07,
+      "loss": 0.3545,
+      "step": 225
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.688804835072748e-07,
+      "loss": 0.3713,
+      "step": 226
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.263426720509469e-07,
+      "loss": 0.3577,
+      "step": 227
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.854146800884929e-07,
+      "loss": 0.3818,
+      "step": 228
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.461034623446847e-07,
+      "loss": 0.3567,
+      "step": 229
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.084156988125232e-07,
+      "loss": 0.3596,
+      "step": 230
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.723577936181366e-07,
+      "loss": 0.354,
+      "step": 231
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.3793587393255e-07,
+      "loss": 0.3471,
+      "step": 232
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.0515578893052343e-07,
+      "loss": 0.3472,
+      "step": 233
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.7402310879662497e-07,
+      "loss": 0.3677,
+      "step": 234
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.4454312377871105e-07,
+      "loss": 0.3658,
+      "step": 235
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.167208432889789e-07,
+      "loss": 0.345,
+      "step": 236
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9056099505273428e-07,
+      "loss": 0.3525,
+      "step": 237
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.6606802430503166e-07,
+      "loss": 0.3687,
+      "step": 238
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.43246093035313e-07,
+      "loss": 0.3668,
+      "step": 239
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.2209907928017794e-07,
+      "loss": 0.3622,
+      "step": 240
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.02630576464402e-07,
+      "loss": 0.3723,
+      "step": 241
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.484389279032835e-08,
+      "loss": 0.3619,
+      "step": 242
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 6.874205067571082e-08,
+      "loss": 0.3743,
+      "step": 243
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.4327786240132576e-08,
+      "loss": 0.3619,
+      "step": 244
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.1603548840062344e-08,
+      "loss": 0.3658,
+      "step": 245
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.0571500652651906e-08,
+      "loss": 0.3573,
+      "step": 246
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.1233516308323266e-08,
+      "loss": 0.3577,
+      "step": 247
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.3591182572219031e-08,
+      "loss": 0.3602,
+      "step": 248
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.645798074572552e-09,
+      "loss": 0.3601,
+      "step": 249
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.3983730900377654e-09,
+      "loss": 0.3694,
+      "step": 250
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.496293660120725e-10,
+      "loss": 0.3598,
+      "step": 251
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0,
+      "loss": 0.3427,
+      "step": 252
+    },
+    {
+      "epoch": 2.99,
+      "step": 252,
+      "total_flos": 6.286385791107072e+17,
+      "train_loss": 0.46650314425665235,
+      "train_runtime": 17988.2658,
+      "train_samples_per_second": 1.798,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "max_steps": 252,
+  "num_train_epochs": 3,
+  "total_flos": 6.286385791107072e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ac83d17c0b1c068061ef4a810c7898692914dc89c366a17d81386ba6e72a48
+size 3707