upload model

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "../models/deepseek-7b-instruct-spider",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c6e8b7173fc15a0278b5e5645071746e18d7ede033de850f546cdcf8f9e247
+size 4844590720

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3468611ca05ad4281ded46e3eec4aefe95fca767657e987c247ce288092ec28c
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a454c1995197410535b550a2ae616ef20e8b0f165e9c8f2d40ffbf31f3eeda
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72896018eee630dc0985397c6fb6055a709a5dcbd0a02bde7807ac77af026b44
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a710a86ceec761f938cd0998e98099eb0b712764f1c9e6c7fdff653c77f72ce9
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa87aaf4b62043bc2251d5d94d3469f9f2b2600770c25e812c66d31ee1058708
+size 2688666416

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26962051072
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1509a67408415a601fb41ba5cf5e272a7fbf50b0edbab795c14c2c0b973c0634
+size 26962200769

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4674cf80975f963dc8af8f5b4dc758b3ca71bf419cb48573c86e95bac738bdaa
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44222db69c3f8871290ae698a3ee3978a77b94777f43c4035367d6337f5f61a7
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1497dc200a8fd4322adbee631d75ba29ae5d77e3db54b812130656d4529b0fe0
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c71cfa0980d006041932e786ea8cbaf3051f96f68c18c3a7856c8f8ace4680
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d640f88b2a044019594469bdf65d9d9a252860ba3739e007b849a5da243cfcfa
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f3b53bf76ce4ef7e3e0aed8a3eb9edc90ed0a980d087527018f66c15e7f9eb
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fda04360cc0855a979ca6e1e614d5ae428795e6c5def4df8687af317d84b48
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eaab5b4a9aca74ae3a4fa1d50fccb8159d109df5b892380521202be6e77289
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5405cb513307632d485b2c1d3f1b9834f2f1a6676271295db3c7ec53bb10ac76
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1461 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9634684865515857,
+  "eval_steps": 500,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 42.4441,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 37.1075,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 27.8987,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 24.6867,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 22.6003,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 21.1455,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 21.6205,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999788644103418e-05,
+      "loss": 20.1194,
+      "step": 80
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999809785053594e-05,
+      "loss": 20.1889,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9994716549285312e-05,
+      "loss": 19.7878,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9989645312071867e-05,
+      "loss": 19.5043,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9982884996355248e-05,
+      "loss": 19.2639,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9974436745189444e-05,
+      "loss": 19.0332,
+      "step": 130
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9964301987029523e-05,
+      "loss": 19.3774,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9952482435490094e-05,
+      "loss": 18.8272,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9938980089055565e-05,
+      "loss": 18.9226,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992379723074224e-05,
+      "loss": 19.2136,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9906936427712295e-05,
+      "loss": 18.6037,
+      "step": 180
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9888400530839713e-05,
+      "loss": 18.6965,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.986819267422826e-05,
+      "loss": 18.4695,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9846316274681547e-05,
+      "loss": 18.5388,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982277503112531e-05,
+      "loss": 18.6583,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.979757292398201e-05,
+      "loss": 18.1656,
+      "step": 230
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.977071421449776e-05,
+      "loss": 18.5414,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9742203444021878e-05,
+      "loss": 18.3158,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9712045433238972e-05,
+      "loss": 18.0978,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9680245281353894e-05,
+      "loss": 18.0812,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9646808365229506e-05,
+      "loss": 17.8044,
+      "step": 280
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.961174033847757e-05,
+      "loss": 17.9748,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9575047130502813e-05,
+      "loss": 17.7447,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.953673494550037e-05,
+      "loss": 18.2907,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.949681026140674e-05,
+      "loss": 18.1314,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9455279828804526e-05,
+      "loss": 17.9227,
+      "step": 330
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9412150669780952e-05,
+      "loss": 18.4178,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.936743007674063e-05,
+      "loss": 17.8701,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9321125611172468e-05,
+      "loss": 18.1603,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.92732451023712e-05,
+      "loss": 17.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9223796646113567e-05,
+      "loss": 17.5233,
+      "step": 380
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9172788603289453e-05,
+      "loss": 18.2041,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9120229598488218e-05,
+      "loss": 18.1653,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9066128518540408e-05,
+      "loss": 17.6848,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9010494511015164e-05,
+      "loss": 18.1238,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8953336982673506e-05,
+      "loss": 17.956,
+      "step": 430
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8894665597877824e-05,
+      "loss": 17.699,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8834490276957788e-05,
+      "loss": 17.6947,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8772821194533e-05,
+      "loss": 17.6464,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8709668777792633e-05,
+      "loss": 17.89,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8645043704732367e-05,
+      "loss": 17.6851,
+      "step": 480
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8578956902348945e-05,
+      "loss": 17.3849,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.851141954479256e-05,
+      "loss": 17.8666,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.844244305147755e-05,
+      "loss": 17.4788,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8372039085151537e-05,
+      "loss": 17.4202,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.830021954992345e-05,
+      "loss": 17.2379,
+      "step": 530
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8226996589250775e-05,
+      "loss": 17.5357,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8152382583886272e-05,
+      "loss": 17.9992,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8076390149784622e-05,
+      "loss": 17.7149,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7999032135969265e-05,
+      "loss": 17.5005,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7920321622359876e-05,
+      "loss": 17.4384,
+      "step": 580
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.784027191756075e-05,
+      "loss": 17.0999,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7758896556610547e-05,
+      "loss": 17.203,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7676209298693765e-05,
+      "loss": 17.3599,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.759222412481428e-05,
+      "loss": 17.7387,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.75069552354314e-05,
+      "loss": 17.4499,
+      "step": 630
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7420417048058816e-05,
+      "loss": 17.396,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7332624194826847e-05,
+      "loss": 17.441,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7243591520008384e-05,
+      "loss": 17.0808,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7153334077508983e-05,
+      "loss": 17.1419,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7061867128321524e-05,
+      "loss": 17.3086,
+      "step": 680
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6969206137945797e-05,
+      "loss": 17.3577,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6875366773773604e-05,
+      "loss": 17.6731,
+      "step": 700
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.678036490243962e-05,
+      "loss": 17.3216,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6684216587138647e-05,
+      "loss": 17.3844,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.658693808490959e-05,
+      "loss": 17.4103,
+      "step": 730
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6488545843886677e-05,
+      "loss": 17.0814,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6389056500518343e-05,
+      "loss": 17.3081,
+      "step": 750
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6288486876754314e-05,
+      "loss": 17.148,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.618685397720128e-05,
+      "loss": 16.8685,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6084174986247738e-05,
+      "loss": 17.4187,
+      "step": 780
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.598046726515836e-05,
+      "loss": 17.4885,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5875748349138533e-05,
+      "loss": 17.2386,
+      "step": 800
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5770035944369456e-05,
+      "loss": 16.9695,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5663347925014302e-05,
+      "loss": 17.3497,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 16.9592,
+      "step": 830
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5447117360947244e-05,
+      "loss": 17.5106,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5337611377132757e-05,
+      "loss": 17.2786,
+      "step": 850
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.522720289434521e-05,
+      "loss": 17.4009,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.511591058077441e-05,
+      "loss": 17.2044,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.500375325405087e-05,
+      "loss": 17.1285,
+      "step": 880
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.489074987806406e-05,
+      "loss": 17.3726,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.477691955975594e-05,
+      "loss": 17.1684,
+      "step": 900
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.46622815458903e-05,
+      "loss": 17.2715,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.454685521979846e-05,
+      "loss": 17.3633,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.443066009810188e-05,
+      "loss": 17.1012,
+      "step": 930
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4313715827412243e-05,
+      "loss": 16.7467,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4196042181009525e-05,
+      "loss": 16.741,
+      "step": 950
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4077659055498695e-05,
+      "loss": 17.0569,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3958586467445532e-05,
+      "loss": 17.0277,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.383884454999215e-05,
+      "loss": 16.8944,
+      "step": 980
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3718453549452843e-05,
+      "loss": 17.1323,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3597433821890787e-05,
+      "loss": 16.9379,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3475805829676149e-05,
+      "loss": 16.9814,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3353590138026273e-05,
+      "loss": 17.1369,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.323080741152845e-05,
+      "loss": 16.8629,
+      "step": 1030
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3107478410645875e-05,
+      "loss": 16.8607,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2983623988207432e-05,
+      "loss": 16.6911,
+      "step": 1050
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.28592650858818e-05,
+      "loss": 16.9764,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2734422730636617e-05,
+      "loss": 16.8255,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2609118031183144e-05,
+      "loss": 16.8564,
+      "step": 1080
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2483372174407155e-05,
+      "loss": 16.9249,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2357206421786611e-05,
+      "loss": 16.8046,
+      "step": 1100
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2230642105796674e-05,
+      "loss": 17.0138,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2103700626302784e-05,
+      "loss": 16.8029,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.197640344694228e-05,
+      "loss": 16.7554,
+      "step": 1130
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1848772091495287e-05,
+      "loss": 16.62,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1720828140245393e-05,
+      "loss": 16.8458,
+      "step": 1150
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1592593226330802e-05,
+      "loss": 17.1714,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1464089032086547e-05,
+      "loss": 17.0085,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1335337285378359e-05,
+      "loss": 16.8423,
+      "step": 1180
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1206359755928865e-05,
+      "loss": 16.8152,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1077178251636702e-05,
+      "loss": 16.619,
+      "step": 1200
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0947814614889174e-05,
+      "loss": 16.7087,
+      "step": 1210
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0818290718869068e-05,
+      "loss": 16.7935,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0688628463856287e-05,
+      "loss": 17.4941,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.055884977352487e-05,
+      "loss": 17.0523,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0428976591236082e-05,
+      "loss": 16.7451,
+      "step": 1250
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.029903087632817e-05,
+      "loss": 16.8536,
+      "step": 1260
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0169034600403404e-05,
+      "loss": 16.6058,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.003900974361306e-05,
+      "loss": 16.6489,
+      "step": 1280
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.908978290940948e-06,
+      "loss": 16.989,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.778962228486138e-06,
+      "loss": 16.885,
+      "step": 1300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.648983539745468e-06,
+      "loss": 16.9012,
+      "step": 1310
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.51906420189652e-06,
+      "loss": 16.8678,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.38922618208166e-06,
+      "loss": 16.7718,
+      "step": 1330
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.259491433693751e-06,
+      "loss": 16.7869,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.129881892664232e-06,
+      "loss": 16.9432,
+      "step": 1350
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.00041947375411e-06,
+      "loss": 16.8835,
+      "step": 1360
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.871126066848552e-06,
+      "loss": 16.8081,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.742023533255677e-06,
+      "loss": 16.6375,
+      "step": 1380
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.613133702010196e-06,
+      "loss": 16.7379,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.484478366182472e-06,
+      "loss": 16.5849,
+      "step": 1400
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.356079279193703e-06,
+      "loss": 16.6192,
+      "step": 1410
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.227958151137773e-06,
+      "loss": 16.4591,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.10013664511047e-06,
+      "loss": 16.5343,
+      "step": 1430
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.9726363735466e-06,
+      "loss": 16.9542,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.84547889456571e-06,
+      "loss": 16.8205,
+      "step": 1450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.718685708326965e-06,
+      "loss": 16.5807,
+      "step": 1460
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.592278253393859e-06,
+      "loss": 16.5174,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.466277903109291e-06,
+      "loss": 16.6076,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.340705961981722e-06,
+      "loss": 16.7884,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.215583662082939e-06,
+      "loss": 16.8359,
+      "step": 1500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.090932159458067e-06,
+      "loss": 16.5588,
+      "step": 1510
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.966772530548448e-06,
+      "loss": 16.6256,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.843125768627983e-06,
+      "loss": 16.7764,
+      "step": 1530
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.720012780253509e-06,
+      "loss": 16.9245,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.597454381729873e-06,
+      "loss": 16.5384,
+      "step": 1550
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.475471295590248e-06,
+      "loss": 16.6298,
+      "step": 1560
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.354084147092296e-06,
+      "loss": 16.752,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.2333134607308e-06,
+      "loss": 16.6684,
+      "step": 1580
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.113179656767319e-06,
+      "loss": 16.4827,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.993703047777468e-06,
+      "loss": 16.5697,
+      "step": 1600
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.874903835216417e-06,
+      "loss": 16.4795,
+      "step": 1610
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.756802106003148e-06,
+      "loss": 16.8255,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.639417829124132e-06,
+      "loss": 16.6714,
+      "step": 1630
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.52277085225688e-06,
+      "loss": 16.7242,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.406880898414069e-06,
+      "loss": 16.4696,
+      "step": 1650
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.291767562608705e-06,
+      "loss": 16.5084,
+      "step": 1660
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.177450308540928e-06,
+      "loss": 16.5646,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.0639484653070535e-06,
+      "loss": 16.4026,
+      "step": 1680
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.95128122413135e-06,
+      "loss": 16.3032,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.83946763512111e-06,
+      "loss": 16.5088,
+      "step": 1700
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7285266040456255e-06,
+      "loss": 16.3905,
+      "step": 1710
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.618476889139538e-06,
+      "loss": 16.4207,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.50933709793113e-06,
+      "loss": 16.5308,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.401125684096124e-06,
+      "loss": 16.521,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.293860944337482e-06,
+      "loss": 16.3123,
+      "step": 1750
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1875610152917225e-06,
+      "loss": 16.6079,
+      "step": 1760
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.082243870462362e-06,
+      "loss": 16.5056,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.977927317180864e-06,
+      "loss": 16.4315,
+      "step": 1780
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.87462899359575e-06,
+      "loss": 16.1708,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.772366365690283e-06,
+      "loss": 16.3817,
+      "step": 1800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6711567243292547e-06,
+      "loss": 16.5455,
+      "step": 1810
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5710171823354145e-06,
+      "loss": 16.3721,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4719646715959777e-06,
+      "loss": 16.4659,
+      "step": 1830
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3740159401997173e-06,
+      "loss": 16.5392,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2771875496051743e-06,
+      "loss": 16.6646,
+      "step": 1850
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.181495871840379e-06,
+      "loss": 16.3682,
+      "step": 1860
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0869570867346167e-06,
+      "loss": 16.5935,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9935871791827166e-06,
+      "loss": 16.539,
+      "step": 1880
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9014019364422606e-06,
+      "loss": 16.1143,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8104169454642293e-06,
+      "loss": 16.5375,
+      "step": 1900
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7206475902575225e-06,
+      "loss": 16.3927,
+      "step": 1910
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6321090492877823e-06,
+      "loss": 16.3639,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.544816292910962e-06,
+      "loss": 16.3929,
+      "step": 1930
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.458784080842127e-06,
+      "loss": 16.3984,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3740269596597943e-06,
+      "loss": 16.3938,
+      "step": 1950
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2905592603463888e-06,
+      "loss": 16.3884,
+      "step": 1960
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2083950958651103e-06,
+      "loss": 16.3289,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1275483587736577e-06,
+      "loss": 16.3735,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.048032718875255e-06,
+      "loss": 16.4073,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.969861620907314e-06,
+      "loss": 16.4259,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8930482822681473e-06,
+      "loss": 16.3312,
+      "step": 2010
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8176056907821482e-06,
+      "loss": 16.2809,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7435466025037684e-06,
+      "loss": 16.2617,
+      "step": 2030
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6708835395606704e-06,
+      "loss": 16.6299,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5996287880364736e-06,
+      "loss": 16.2559,
+      "step": 2050
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5297943958933748e-06,
+      "loss": 16.4145,
+      "step": 2060
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4613921709350342e-06,
+      "loss": 16.3823,
+      "step": 2070
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3944336788100976e-06,
+      "loss": 16.3725,
+      "step": 2080
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3289302410566318e-06,
+      "loss": 16.2138,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2648929331878423e-06,
+      "loss": 16.2873,
+      "step": 2100
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.202332582819402e-06,
+      "loss": 16.4605,
+      "step": 2110
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.141259767838675e-06,
+      "loss": 16.1904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0816848146161895e-06,
+      "loss": 16.4713,
+      "step": 2130
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0236177962596173e-06,
+      "loss": 16.143,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.670685309105786e-07,
+      "loss": 16.2049,
+      "step": 2150
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.120465800845723e-07,
+      "loss": 16.3906,
+      "step": 2160
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.585612470542859e-07,
+      "loss": 16.1819,
+      "step": 2170
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.06621575276556e-07,
+      "loss": 16.2495,
+      "step": 2180
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.562363468632949e-07,
+      "loss": 16.3325,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.074140810965724e-07,
+      "loss": 16.3265,
+      "step": 2200
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.601630329881525e-07,
+      "loss": 16.3694,
+      "step": 2210
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.14491191883716e-07,
+      "loss": 16.2883,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.704062801119947e-07,
+      "loss": 16.2978,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.279157516790545e-07,
+      "loss": 16.2589,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.870267910079618e-07,
+      "loss": 16.6149,
+      "step": 2250
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4774631172400663e-07,
+      "loss": 16.2879,
+      "step": 2260
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.100809554857343e-07,
+      "loss": 16.2822,
+      "step": 2270
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.740370908619528e-07,
+      "loss": 16.3097,
+      "step": 2280
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.396208122549194e-07,
+      "loss": 16.3474,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0683793886986943e-07,
+      "loss": 16.2617,
+      "step": 2300
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7569401373110595e-07,
+      "loss": 16.1619,
+      "step": 2310
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.461943027447555e-07,
+      "loss": 16.2584,
+      "step": 2320
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1834379380839655e-07,
+      "loss": 16.1723,
+      "step": 2330
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 16.2365,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.676089386201818e-07,
+      "loss": 16.2976,
+      "step": 2350
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4473317076631355e-07,
+      "loss": 16.3046,
+      "step": 2360
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2352376030795753e-07,
+      "loss": 16.2992,
+      "step": 2370
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0398429339438353e-07,
+      "loss": 16.2474,
+      "step": 2380
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.61180738159173e-08,
+      "loss": 16.2852,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.992812244532188e-08,
+      "loss": 16.3501,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2491,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e461913d14006955a6349c0ee521da3252656211ab6e99ebc16228c210e0212f
+size 5176