Upload 22 files

v5-3ep-0-0.03-easy-ckpt-402

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/mntcephfs/data/med/zhihong/workspace/LLMZoo/llama_hf_7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

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"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b4417ba841b2fca9b49090df2de411170dd34f945e14eabb2c3c95b9e47bbd
+size 6738451914

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68d030063a885ad01727e55f9e5e2c55a4106357aeae484ac73828d77edc789
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2164b97304f739ebfc4d8347ce244e205c5768e35d5a1677b59d1873d22c678
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba7ea1a18393cbdf7f889ee95f37aee1a1992075b8428982df8c3716513aa3a
+size 7181009913

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3c5cb412e12159a59afe5657ce4b5e0a06e7fb420bedbb5228fe1245702762
+size 14583

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741230672078323886b763e522c728741456a587860909fc529ce815a7aca5ec
+size 14583

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea587886b41579993bb5d20c79047b968ae2d71d22ba4c739b07ce31d7486a6
+size 14583

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab727740f74dd67e60283d27b4339609a1dda888b067cc06520e2f1d7dc17db
+size 14583

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fbffd04f81c5419775f5b8507ac368aa0ff88b146755becf7b9cd26c139501
+size 14583

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfb5fd9b58d3febef1eee1e52cb6997af12bac5fccd4be5e31c38721f4c3410
+size 14583

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f120fd79fe083c8bfcd736e4bd37c6fe37ba8dc492e550f309fb809413a218d
+size 14583

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed17a3c5698176f919ced6408c261f11e642658a3bdc526ead16625e7bb4a6f
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3965a832485f86ed8e3ae39d2832ce4e48ba19abe616b1eca9d77ef9b2d9b31c
+size 627

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

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": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "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": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,2428 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.986072423398329,
+  "global_step": 402,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 3.6566,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 3.7319,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 2.9617,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 2.7649,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 2.8078,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 2.5837,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 2.5011,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 2.3675,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 2.1685,
+      "step": 9
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 2.1721,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 2.1973,
+      "step": 11
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 2.1513,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 2.2307,
+      "step": 13
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999673886943734e-05,
+      "loss": 2.0475,
+      "step": 14
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999869556904488e-05,
+      "loss": 2.2153,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9997065110111884e-05,
+      "loss": 1.8805,
+      "step": 16
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9994782616487538e-05,
+      "loss": 1.9966,
+      "step": 17
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991848237042037e-05,
+      "loss": 2.0823,
+      "step": 18
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9988262163163265e-05,
+      "loss": 2.098,
+      "step": 19
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998402462874433e-05,
+      "loss": 2.0602,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9979135910168292e-05,
+      "loss": 1.9297,
+      "step": 21
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9973596326290136e-05,
+      "loss": 1.9211,
+      "step": 22
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9967406238415998e-05,
+      "loss": 2.0546,
+      "step": 23
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9960566050279568e-05,
+      "loss": 1.9672,
+      "step": 24
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9953076208015772e-05,
+      "loss": 2.0002,
+      "step": 25
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994493720013169e-05,
+      "loss": 2.0499,
+      "step": 26
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9936149557474668e-05,
+      "loss": 2.0324,
+      "step": 27
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9926713853197696e-05,
+      "loss": 1.9641,
+      "step": 28
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.991663070272206e-05,
+      "loss": 1.8782,
+      "step": 29
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9905900763697152e-05,
+      "loss": 2.0222,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9894524735957624e-05,
+      "loss": 1.927,
+      "step": 31
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9882503361477707e-05,
+      "loss": 1.9989,
+      "step": 32
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9869837424322827e-05,
+      "loss": 1.9593,
+      "step": 33
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9856527750598493e-05,
+      "loss": 1.96,
+      "step": 34
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9842575208396374e-05,
+      "loss": 1.9815,
+      "step": 35
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9827980707737704e-05,
+      "loss": 2.001,
+      "step": 36
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9812745200513926e-05,
+      "loss": 1.9909,
+      "step": 37
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.979686968042461e-05,
+      "loss": 1.9635,
+      "step": 38
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9780355182912626e-05,
+      "loss": 2.0265,
+      "step": 39
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.976320278509663e-05,
+      "loss": 1.7656,
+      "step": 40
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974541360570079e-05,
+      "loss": 1.9266,
+      "step": 41
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9726988804981847e-05,
+      "loss": 1.9298,
+      "step": 42
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.970792958465341e-05,
+      "loss": 2.0026,
+      "step": 43
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9688237187807594e-05,
+      "loss": 2.0285,
+      "step": 44
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9667912898833953e-05,
+      "loss": 1.9038,
+      "step": 45
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9646958043335678e-05,
+      "loss": 1.8253,
+      "step": 46
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9625373988043167e-05,
+      "loss": 1.8563,
+      "step": 47
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9603162140724863e-05,
+      "loss": 1.9414,
+      "step": 48
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.958032395009545e-05,
+      "loss": 1.8428,
+      "step": 49
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9556860905721363e-05,
+      "loss": 1.9282,
+      "step": 50
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9532774537923617e-05,
+      "loss": 2.091,
+      "step": 51
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.950806641767802e-05,
+      "loss": 1.925,
+      "step": 52
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9482738156512694e-05,
+      "loss": 1.9726,
+      "step": 53
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9456791406402964e-05,
+      "loss": 1.9473,
+      "step": 54
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9430227859663634e-05,
+      "loss": 1.9427,
+      "step": 55
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.940304924883858e-05,
+      "loss": 1.835,
+      "step": 56
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9375257346587776e-05,
+      "loss": 1.9231,
+      "step": 57
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.934685396557165e-05,
+      "loss": 1.9197,
+      "step": 58
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.931784095833289e-05,
+      "loss": 1.9501,
+      "step": 59
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9288220217175583e-05,
+      "loss": 1.9518,
+      "step": 60
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9257993674041814e-05,
+      "loss": 1.9073,
+      "step": 61
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9227163300385662e-05,
+      "loss": 1.8463,
+      "step": 62
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9195731107044596e-05,
+      "loss": 1.8878,
+      "step": 63
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9163699144108343e-05,
+      "loss": 1.8452,
+      "step": 64
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9131069500785173e-05,
+      "loss": 1.9069,
+      "step": 65
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9097844305265625e-05,
+      "loss": 1.9706,
+      "step": 66
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.906402572458371e-05,
+      "loss": 1.8499,
+      "step": 67
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9029615964475572e-05,
+      "loss": 1.8589,
+      "step": 68
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8994617269235615e-05,
+      "loss": 1.7905,
+      "step": 69
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8959031921570136e-05,
+      "loss": 1.8836,
+      "step": 70
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.892286224244843e-05,
+      "loss": 1.8668,
+      "step": 71
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8886110590951417e-05,
+      "loss": 2.0072,
+      "step": 72
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8848779364117774e-05,
+      "loss": 1.9274,
+      "step": 73
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.88108709967876e-05,
+      "loss": 1.9034,
+      "step": 74
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.87723879614436e-05,
+      "loss": 1.8714,
+      "step": 75
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.873333276804983e-05,
+      "loss": 1.8106,
+      "step": 76
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.869370796388798e-05,
+      "loss": 1.9745,
+      "step": 77
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.865351613339125e-05,
+      "loss": 1.8142,
+      "step": 78
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.861275989797578e-05,
+      "loss": 1.906,
+      "step": 79
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8571441915869663e-05,
+      "loss": 1.7411,
+      "step": 80
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.852956488193959e-05,
+      "loss": 1.9871,
+      "step": 81
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.848713152751506e-05,
+      "loss": 1.8511,
+      "step": 82
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8444144620210255e-05,
+      "loss": 2.0191,
+      "step": 83
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8400606963743517e-05,
+      "loss": 1.9095,
+      "step": 84
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8356521397754495e-05,
+      "loss": 1.7602,
+      "step": 85
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8311890797618918e-05,
+      "loss": 1.9675,
+      "step": 86
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8266718074261064e-05,
+      "loss": 1.8566,
+      "step": 87
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.822100617396391e-05,
+      "loss": 1.7544,
+      "step": 88
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8174758078176963e-05,
+      "loss": 1.8744,
+      "step": 89
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8127976803321793e-05,
+      "loss": 1.9445,
+      "step": 90
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8080665400595303e-05,
+      "loss": 1.9952,
+      "step": 91
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8032826955770723e-05,
+      "loss": 1.8672,
+      "step": 92
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7984464588996342e-05,
+      "loss": 1.8689,
+      "step": 93
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7935581454592005e-05,
+      "loss": 1.7157,
+      "step": 94
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7886180740843385e-05,
+      "loss": 1.9338,
+      "step": 95
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7836265669794032e-05,
+      "loss": 1.8889,
+      "step": 96
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7785839497035222e-05,
+      "loss": 1.7935,
+      "step": 97
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7734905511493614e-05,
+      "loss": 1.955,
+      "step": 98
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.768346703521675e-05,
+      "loss": 1.8675,
+      "step": 99
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.763152742315637e-05,
+      "loss": 1.891,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.75790900629496e-05,
+      "loss": 1.921,
+      "step": 101
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7526158374697997e-05,
+      "loss": 1.9667,
+      "step": 102
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7472735810744496e-05,
+      "loss": 1.8718,
+      "step": 103
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7418825855448208e-05,
+      "loss": 1.8478,
+      "step": 104
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7364432024957192e-05,
+      "loss": 1.8649,
+      "step": 105
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7309557866979113e-05,
+      "loss": 1.8813,
+      "step": 106
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7254206960549844e-05,
+      "loss": 1.954,
+      "step": 107
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7198382915800034e-05,
+      "loss": 1.814,
+      "step": 108
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7142089373719654e-05,
+      "loss": 1.8448,
+      "step": 109
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7085330005920516e-05,
+      "loss": 1.8477,
+      "step": 110
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.70281085143968e-05,
+      "loss": 1.7807,
+      "step": 111
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6970428631283602e-05,
+      "loss": 1.8641,
+      "step": 112
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6912294118613518e-05,
+      "loss": 1.906,
+      "step": 113
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6853708768071265e-05,
+      "loss": 1.8747,
+      "step": 114
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.679467640074639e-05,
+      "loss": 1.9149,
+      "step": 115
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6735200866884037e-05,
+      "loss": 1.8116,
+      "step": 116
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.667528604563383e-05,
+      "loss": 2.0109,
+      "step": 117
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6614935844796863e-05,
+      "loss": 1.8141,
+      "step": 118
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6554154200570828e-05,
+      "loss": 1.9185,
+      "step": 119
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.649294507729327e-05,
+      "loss": 1.892,
+      "step": 120
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.643131246718305e-05,
+      "loss": 1.8075,
+      "step": 121
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6369260390079933e-05,
+      "loss": 1.8891,
+      "step": 122
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6306792893182422e-05,
+      "loss": 1.8502,
+      "step": 123
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6243914050783783e-05,
+      "loss": 1.9021,
+      "step": 124
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6180627964006313e-05,
+      "loss": 1.694,
+      "step": 125
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6116938760533843e-05,
+      "loss": 1.8065,
+      "step": 126
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6052850594342534e-05,
+      "loss": 1.8479,
+      "step": 127
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5988367645429938e-05,
+      "loss": 1.9265,
+      "step": 128
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.592349411954236e-05,
+      "loss": 1.8542,
+      "step": 129
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.585823424790056e-05,
+      "loss": 1.7848,
+      "step": 130
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.579259228692378e-05,
+      "loss": 1.9324,
+      "step": 131
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5726572517952122e-05,
+      "loss": 1.773,
+      "step": 132
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.566017924696731e-05,
+      "loss": 1.8328,
+      "step": 133
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.559341680431185e-05,
+      "loss": 1.8331,
+      "step": 134
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5526289544406585e-05,
+      "loss": 1.8482,
+      "step": 135
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.545880184546669e-05,
+      "loss": 1.5427,
+      "step": 136
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.539095810921612e-05,
+      "loss": 1.5302,
+      "step": 137
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.532276276060051e-05,
+      "loss": 1.6252,
+      "step": 138
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5254220247498572e-05,
+      "loss": 1.5662,
+      "step": 139
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.518533504043199e-05,
+      "loss": 1.5451,
+      "step": 140
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5116111632273848e-05,
+      "loss": 1.6063,
+      "step": 141
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5046554537955587e-05,
+      "loss": 1.5512,
+      "step": 142
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4976668294172528e-05,
+      "loss": 1.5608,
+      "step": 143
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4906457459087977e-05,
+      "loss": 1.5362,
+      "step": 144
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4835926612035944e-05,
+      "loss": 1.6489,
+      "step": 145
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4765080353222447e-05,
+      "loss": 1.6442,
+      "step": 146
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4693923303425479e-05,
+      "loss": 1.5944,
+      "step": 147
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.462246010369364e-05,
+      "loss": 1.5571,
+      "step": 148
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4550695415043421e-05,
+      "loss": 1.5987,
+      "step": 149
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4478633918155216e-05,
+      "loss": 1.5843,
+      "step": 150
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4406280313068019e-05,
+      "loss": 1.51,
+      "step": 151
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4333639318872891e-05,
+      "loss": 1.5727,
+      "step": 152
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4260715673405157e-05,
+      "loss": 1.6347,
+      "step": 153
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4187514132935393e-05,
+      "loss": 1.5709,
+      "step": 154
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4114039471859221e-05,
+      "loss": 1.6186,
+      "step": 155
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4040296482385893e-05,
+      "loss": 1.5457,
+      "step": 156
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3966289974225751e-05,
+      "loss": 1.4672,
+      "step": 157
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3892024774276496e-05,
+      "loss": 1.5874,
+      "step": 158
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3817505726308402e-05,
+      "loss": 1.5051,
+      "step": 159
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3742737690648362e-05,
+      "loss": 1.5036,
+      "step": 160
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3667725543862906e-05,
+      "loss": 1.5277,
+      "step": 161
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3592474178440116e-05,
+      "loss": 1.4715,
+      "step": 162
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.351698850247055e-05,
+      "loss": 1.5668,
+      "step": 163
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.34412734393271e-05,
+      "loss": 1.578,
+      "step": 164
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3365333927343906e-05,
+      "loss": 1.5374,
+      "step": 165
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3289174919494228e-05,
+      "loss": 1.5562,
+      "step": 166
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3212801383067431e-05,
+      "loss": 1.5418,
+      "step": 167
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3136218299344993e-05,
+      "loss": 1.4952,
+      "step": 168
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.305943066327561e-05,
+      "loss": 1.5251,
+      "step": 169
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.2982443483149423e-05,
+      "loss": 1.5562,
+      "step": 170
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2905261780271345e-05,
+      "loss": 1.535,
+      "step": 171
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2827890588633589e-05,
+      "loss": 1.474,
+      "step": 172
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2750334954587297e-05,
+      "loss": 1.5725,
+      "step": 173
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.267259993651345e-05,
+      "loss": 1.4509,
+      "step": 174
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2594690604492906e-05,
+      "loss": 1.5969,
+      "step": 175
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2516612039975745e-05,
+      "loss": 1.477,
+      "step": 176
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2438369335449822e-05,
+      "loss": 1.4507,
+      "step": 177
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2359967594108643e-05,
+      "loss": 1.5572,
+      "step": 178
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.22814119295185e-05,
+      "loss": 1.5147,
+      "step": 179
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2202707465284973e-05,
+      "loss": 1.5563,
+      "step": 180
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2123859334718732e-05,
+      "loss": 1.5903,
+      "step": 181
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2044872680500743e-05,
+      "loss": 1.5443,
+      "step": 182
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1965752654346853e-05,
+      "loss": 1.6039,
+      "step": 183
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.188650441667177e-05,
+      "loss": 1.48,
+      "step": 184
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1807133136252491e-05,
+      "loss": 1.5275,
+      "step": 185
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.172764398989118e-05,
+      "loss": 1.6416,
+      "step": 186
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1648042162077536e-05,
+      "loss": 1.6704,
+      "step": 187
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1568332844650623e-05,
+      "loss": 1.4922,
+      "step": 188
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1488521236460266e-05,
+      "loss": 1.5443,
+      "step": 189
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1408612543027963e-05,
+      "loss": 1.5277,
+      "step": 190
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1328611976207358e-05,
+      "loss": 1.5198,
+      "step": 191
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1248524753844325e-05,
+      "loss": 1.4403,
+      "step": 192
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.116835609943663e-05,
+      "loss": 1.4591,
+      "step": 193
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1088111241793258e-05,
+      "loss": 1.5585,
+      "step": 194
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1007795414693361e-05,
+      "loss": 1.6089,
+      "step": 195
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0927413856544906e-05,
+      "loss": 1.6047,
+      "step": 196
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0846971810043017e-05,
+      "loss": 1.5849,
+      "step": 197
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0766474521828022e-05,
+      "loss": 1.495,
+      "step": 198
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0685927242143248e-05,
+      "loss": 1.5816,
+      "step": 199
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0605335224492617e-05,
+      "loss": 1.4354,
+      "step": 200
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0524703725297957e-05,
+      "loss": 1.6279,
+      "step": 201
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0444038003556201e-05,
+      "loss": 1.4828,
+      "step": 202
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0363343320496358e-05,
+      "loss": 1.4755,
+      "step": 203
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0282624939236367e-05,
+      "loss": 1.5889,
+      "step": 204
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0201888124439836e-05,
+      "loss": 1.583,
+      "step": 205
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0121138141972649e-05,
+      "loss": 1.6678,
+      "step": 206
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.004038025855952e-05,
+      "loss": 1.467,
+      "step": 207
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.959619741440486e-06,
+      "loss": 1.4655,
+      "step": 208
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.878861858027355e-06,
+      "loss": 1.4602,
+      "step": 209
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.798111875560167e-06,
+      "loss": 1.6014,
+      "step": 210
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.717375060763636e-06,
+      "loss": 1.5798,
+      "step": 211
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.636656679503647e-06,
+      "loss": 1.6139,
+      "step": 212
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.555961996443802e-06,
+      "loss": 1.6,
+      "step": 213
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.475296274702044e-06,
+      "loss": 1.4852,
+      "step": 214
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.394664775507386e-06,
+      "loss": 1.568,
+      "step": 215
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.314072757856752e-06,
+      "loss": 1.6171,
+      "step": 216
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.233525478171985e-06,
+      "loss": 1.5977,
+      "step": 217
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.153028189956986e-06,
+      "loss": 1.5454,
+      "step": 218
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.072586143455096e-06,
+      "loss": 1.6758,
+      "step": 219
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 8.99220458530664e-06,
+      "loss": 1.5476,
+      "step": 220
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.911888758206747e-06,
+      "loss": 1.569,
+      "step": 221
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.831643900563372e-06,
+      "loss": 1.5424,
+      "step": 222
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.751475246155678e-06,
+      "loss": 1.5137,
+      "step": 223
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.671388023792642e-06,
+      "loss": 1.4392,
+      "step": 224
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.59138745697204e-06,
+      "loss": 1.5653,
+      "step": 225
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.511478763539737e-06,
+      "loss": 1.4838,
+      "step": 226
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.43166715534938e-06,
+      "loss": 1.5887,
+      "step": 227
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.351957837922467e-06,
+      "loss": 1.5384,
+      "step": 228
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.27235601010882e-06,
+      "loss": 1.4996,
+      "step": 229
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.192866863747516e-06,
+      "loss": 1.6276,
+      "step": 230
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.113495583328234e-06,
+      "loss": 1.5748,
+      "step": 231
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.034247345653148e-06,
+      "loss": 1.4351,
+      "step": 232
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.955127319499259e-06,
+      "loss": 1.4449,
+      "step": 233
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.876140665281273e-06,
+      "loss": 1.3847,
+      "step": 234
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.79729253471503e-06,
+      "loss": 1.5532,
+      "step": 235
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.718588070481501e-06,
+      "loss": 1.48,
+      "step": 236
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.64003240589136e-06,
+      "loss": 1.4335,
+      "step": 237
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.561630664550179e-06,
+      "loss": 1.5568,
+      "step": 238
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.483387960024261e-06,
+      "loss": 1.577,
+      "step": 239
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.405309395507098e-06,
+      "loss": 1.4819,
+      "step": 240
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.327400063486554e-06,
+      "loss": 1.4613,
+      "step": 241
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.249665045412704e-06,
+      "loss": 1.585,
+      "step": 242
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.172109411366417e-06,
+      "loss": 1.5929,
+      "step": 243
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.0947382197286566e-06,
+      "loss": 1.4685,
+      "step": 244
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.017556516850581e-06,
+      "loss": 1.5956,
+      "step": 245
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.94056933672439e-06,
+      "loss": 1.5801,
+      "step": 246
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.863781700655013e-06,
+      "loss": 1.5173,
+      "step": 247
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.787198616932571e-06,
+      "loss": 1.6037,
+      "step": 248
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.710825080505775e-06,
+      "loss": 1.536,
+      "step": 249
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.634666072656097e-06,
+      "loss": 1.5086,
+      "step": 250
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.558726560672899e-06,
+      "loss": 1.4448,
+      "step": 251
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.483011497529457e-06,
+      "loss": 1.4841,
+      "step": 252
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.4075258215598875e-06,
+      "loss": 1.418,
+      "step": 253
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.332274456137097e-06,
+      "loss": 1.5594,
+      "step": 254
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.257262309351637e-06,
+      "loss": 1.5807,
+      "step": 255
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.182494273691602e-06,
+      "loss": 1.5188,
+      "step": 256
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.107975225723506e-06,
+      "loss": 1.4614,
+      "step": 257
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.033710025774253e-06,
+      "loss": 1.5837,
+      "step": 258
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 5.959703517614107e-06,
+      "loss": 1.5286,
+      "step": 259
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.885960528140784e-06,
+      "loss": 1.4598,
+      "step": 260
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.812485867064608e-06,
+      "loss": 1.5025,
+      "step": 261
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.739284326594845e-06,
+      "loss": 1.5862,
+      "step": 262
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.666360681127109e-06,
+      "loss": 1.418,
+      "step": 263
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.59371968693198e-06,
+      "loss": 1.4598,
+      "step": 264
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.521366081844788e-06,
+      "loss": 1.4986,
+      "step": 265
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.449304584956582e-06,
+      "loss": 1.4822,
+      "step": 266
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.377539896306363e-06,
+      "loss": 1.5696,
+      "step": 267
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.306076696574522e-06,
+      "loss": 1.5305,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.234919646777557e-06,
+      "loss": 1.5481,
+      "step": 269
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.164073387964057e-06,
+      "loss": 1.3277,
+      "step": 270
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.093542540912024e-06,
+      "loss": 1.2237,
+      "step": 271
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.023331705827477e-06,
+      "loss": 1.3044,
+      "step": 272
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.953445462044415e-06,
+      "loss": 1.3071,
+      "step": 273
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.883888367726153e-06,
+      "loss": 1.273,
+      "step": 274
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.8146649595680104e-06,
+      "loss": 1.2474,
+      "step": 275
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.74577975250143e-06,
+      "loss": 1.1685,
+      "step": 276
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.6772372393994895e-06,
+      "loss": 1.2536,
+      "step": 277
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.609041890783882e-06,
+      "loss": 1.3136,
+      "step": 278
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.541198154533312e-06,
+      "loss": 1.2524,
+      "step": 279
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.473710455593416e-06,
+      "loss": 1.4121,
+      "step": 280
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.40658319568815e-06,
+      "loss": 1.2505,
+      "step": 281
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.339820753032692e-06,
+      "loss": 1.1917,
+      "step": 282
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.27342748204788e-06,
+      "loss": 1.1752,
+      "step": 283
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.207407713076221e-06,
+      "loss": 1.3431,
+      "step": 284
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.14176575209944e-06,
+      "loss": 1.2406,
+      "step": 285
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.076505880457642e-06,
+      "loss": 1.1902,
+      "step": 286
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.011632354570068e-06,
+      "loss": 1.388,
+      "step": 287
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.947149405657469e-06,
+      "loss": 1.1345,
+      "step": 288
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.88306123946616e-06,
+      "loss": 1.2937,
+      "step": 289
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.8193720359936905e-06,
+      "loss": 1.2492,
+      "step": 290
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.7560859492162184e-06,
+      "loss": 1.4007,
+      "step": 291
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.69320710681758e-06,
+      "loss": 1.32,
+      "step": 292
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6307396099200686e-06,
+      "loss": 1.2589,
+      "step": 293
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.5686875328169513e-06,
+      "loss": 1.2508,
+      "step": 294
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.507054922706733e-06,
+      "loss": 1.2725,
+      "step": 295
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.4458457994291763e-06,
+      "loss": 1.275,
+      "step": 296
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.385064155203138e-06,
+      "loss": 1.2923,
+      "step": 297
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.324713954366171e-06,
+      "loss": 1.2513,
+      "step": 298
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.2647991331159632e-06,
+      "loss": 1.2202,
+      "step": 299
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.2053235992536137e-06,
+      "loss": 1.1305,
+      "step": 300
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.1462912319287376e-06,
+      "loss": 1.3371,
+      "step": 301
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.0877058813864856e-06,
+      "loss": 1.257,
+      "step": 302
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.0295713687164006e-06,
+      "loss": 1.1057,
+      "step": 303
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.9718914856032033e-06,
+      "loss": 1.3259,
+      "step": 304
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9146699940794864e-06,
+      "loss": 1.3001,
+      "step": 305
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.8579106262803467e-06,
+      "loss": 1.2887,
+      "step": 306
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.801617084199967e-06,
+      "loss": 1.2804,
+      "step": 307
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.7457930394501564e-06,
+      "loss": 1.3318,
+      "step": 308
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.6904421330208886e-06,
+      "loss": 1.2538,
+      "step": 309
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.635567975042809e-06,
+      "loss": 1.2637,
+      "step": 310
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.5811741445517947e-06,
+      "loss": 1.251,
+      "step": 311
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.527264189255507e-06,
+      "loss": 1.3331,
+      "step": 312
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.473841625302006e-06,
+      "loss": 1.3239,
+      "step": 313
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.420909937050405e-06,
+      "loss": 1.385,
+      "step": 314
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.3684725768436333e-06,
+      "loss": 1.2563,
+      "step": 315
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3165329647832525e-06,
+      "loss": 1.2487,
+      "step": 316
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.26509448850639e-06,
+      "loss": 1.2652,
+      "step": 317
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.214160502964783e-06,
+      "loss": 1.3718,
+      "step": 318
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.163734330205971e-06,
+      "loss": 1.1692,
+      "step": 319
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1138192591566177e-06,
+      "loss": 1.2578,
+      "step": 320
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.064418545407998e-06,
+      "loss": 1.1949,
+      "step": 321
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.0155354110036607e-06,
+      "loss": 1.2732,
+      "step": 322
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.967173044229278e-06,
+      "loss": 1.2938,
+      "step": 323
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9193345994046965e-06,
+      "loss": 1.2665,
+      "step": 324
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.8720231966782065e-06,
+      "loss": 1.3421,
+      "step": 325
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.8252419218230389e-06,
+      "loss": 1.3351,
+      "step": 326
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7789938260360907e-06,
+      "loss": 1.2473,
+      "step": 327
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7332819257389388e-06,
+      "loss": 1.2964,
+      "step": 328
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.6881092023810853e-06,
+      "loss": 1.1983,
+      "step": 329
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.6434786022455073e-06,
+      "loss": 1.2549,
+      "step": 330
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.5993930362564835e-06,
+      "loss": 1.2283,
+      "step": 331
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5558553797897469e-06,
+      "loss": 1.1693,
+      "step": 332
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.512868472484943e-06,
+      "loss": 1.2312,
+      "step": 333
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.4704351180604126e-06,
+      "loss": 1.253,
+      "step": 334
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4285580841303382e-06,
+      "loss": 1.2178,
+      "step": 335
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.3872401020242222e-06,
+      "loss": 1.2663,
+      "step": 336
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.346483866608751e-06,
+      "loss": 1.2452,
+      "step": 337
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3062920361120224e-06,
+      "loss": 1.2539,
+      "step": 338
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2666672319501737e-06,
+      "loss": 1.1804,
+      "step": 339
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2276120385564006e-06,
+      "loss": 1.1672,
+      "step": 340
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1891290032124003e-06,
+      "loss": 1.2853,
+      "step": 341
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1512206358822264e-06,
+      "loss": 1.2424,
+      "step": 342
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1138894090485863e-06,
+      "loss": 1.2441,
+      "step": 343
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.077137757551573e-06,
+      "loss": 1.2049,
+      "step": 344
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.040968078429866e-06,
+      "loss": 1.2567,
+      "step": 345
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.005382730764386e-06,
+      "loss": 1.2805,
+      "step": 346
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.703840355244287e-07,
+      "loss": 1.2225,
+      "step": 347
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.359742754162926e-07,
+      "loss": 1.3789,
+      "step": 348
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.021556947343791e-07,
+      "loss": 1.2516,
+      "step": 349
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.689304992148285e-07,
+      "loss": 1.3251,
+      "step": 350
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.363008558916575e-07,
+      "loss": 1.263,
+      "step": 351
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.042688929554076e-07,
+      "loss": 1.3264,
+      "step": 352
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.728366996143399e-07,
+      "loss": 1.3477,
+      "step": 353
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.420063259581856e-07,
+      "loss": 1.2613,
+      "step": 354
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.117797828244177e-07,
+      "loss": 1.2239,
+      "step": 355
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.821590416671108e-07,
+      "loss": 1.2255,
+      "step": 356
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.531460344283513e-07,
+      "loss": 1.2252,
+      "step": 357
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.247426534122292e-07,
+      "loss": 1.3576,
+      "step": 358
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.969507511614225e-07,
+      "loss": 1.2192,
+      "step": 359
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.697721403363699e-07,
+      "loss": 1.3762,
+      "step": 360
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.432085935970388e-07,
+      "loss": 1.301,
+      "step": 361
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.172618434873112e-07,
+      "loss": 1.319,
+      "step": 362
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.919335823219817e-07,
+      "loss": 1.1958,
+      "step": 363
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.672254620763839e-07,
+      "loss": 1.1333,
+      "step": 364
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.4313909427863957e-07,
+      "loss": 1.3401,
+      "step": 365
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.196760499045505e-07,
+      "loss": 1.1234,
+      "step": 366
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.968378592751399e-07,
+      "loss": 1.2775,
+      "step": 367
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.746260119568368e-07,
+      "loss": 1.3351,
+      "step": 368
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.5304195666432396e-07,
+      "loss": 1.1144,
+      "step": 369
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.320871011660498e-07,
+      "loss": 1.1784,
+      "step": 370
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.1176281219240657e-07,
+      "loss": 1.2739,
+      "step": 371
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.920704153465936e-07,
+      "loss": 1.1408,
+      "step": 372
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.7301119501815464e-07,
+      "loss": 1.2877,
+      "step": 373
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.5458639429921105e-07,
+      "loss": 1.2526,
+      "step": 374
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.3679721490337258e-07,
+      "loss": 1.2956,
+      "step": 375
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.196448170873755e-07,
+      "loss": 1.2416,
+      "step": 376
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.0313031957539198e-07,
+      "loss": 1.2028,
+      "step": 377
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.8725479948607515e-07,
+      "loss": 1.2249,
+      "step": 378
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.7201929226229873e-07,
+      "loss": 1.2774,
+      "step": 379
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.5742479160362978e-07,
+      "loss": 1.3433,
+      "step": 380
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.434722494015084e-07,
+      "loss": 1.4227,
+      "step": 381
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.3016257567717295e-07,
+      "loss": 1.2546,
+      "step": 382
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.1749663852229864e-07,
+      "loss": 1.3226,
+      "step": 383
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.054752640423784e-07,
+      "loss": 1.3051,
+      "step": 384
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.409923630284812e-08,
+      "loss": 1.353,
+      "step": 385
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.336929727794318e-08,
+      "loss": 1.2531,
+      "step": 386
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 7.328614680230495e-08,
+      "loss": 1.2814,
+      "step": 387
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 6.385044252533723e-08,
+      "loss": 1.2351,
+      "step": 388
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.506279986831065e-08,
+      "loss": 1.3189,
+      "step": 389
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 4.692379198422803e-08,
+      "loss": 1.2508,
+      "step": 390
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.9433949720435464e-08,
+      "loss": 1.3068,
+      "step": 391
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.259376158400329e-08,
+      "loss": 1.3143,
+      "step": 392
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.6403673709863854e-08,
+      "loss": 1.3058,
+      "step": 393
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.0864089831711398e-08,
+      "loss": 1.2946,
+      "step": 394
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.5975371255672056e-08,
+      "loss": 1.3232,
+      "step": 395
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.1737836836737126e-08,
+      "loss": 1.2446,
+      "step": 396
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.15176295796638e-09,
+      "loss": 1.2853,
+      "step": 397
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.217383512463592e-09,
+      "loss": 1.2427,
+      "step": 398
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.934889888116521e-09,
+      "loss": 1.3966,
+      "step": 399
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.3044309551213385e-09,
+      "loss": 1.2288,
+      "step": 400
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.2611305626706336e-10,
+      "loss": 1.2406,
+      "step": 401
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0,
+      "loss": 1.2031,
+      "step": 402
+    }
+  ],
+  "max_steps": 402,
+  "num_train_epochs": 3,
+  "total_flos": 1.0404875099533476e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc3fafaa0f2962c4c9cf2344e04c5a26aedae21373b5711262f2f689ecf0a28
+size 3771