Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "max_memory": {
+    "0": 4526435634,
+    "1": 4526435634,
+    "2": 4526435634,
+    "3": 4526435634,
+    "4": 4526435634,
+    "5": 4526435634,
+    "6": 73000000000
+  },
+  "no_split_module_classes": [
+    "LlamaDecoderLayer"
+  ],
+  "pad_token_id": 0,
+  "special_dtypes": {},
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9580886c6c0325ca239e34c76a4053101ebbe0af8b53d17cd00d70a9558e1889
+size 1960

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50ae605a1e6c7d3cd2792d5c961b3f8fd06226a0b20f924325e48b36821a425
+size 9948731029

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3a0cd19ba70f2eb1f001794e926720c44b11c65d8fd4ad4f729381393097e2
+size 9904167687

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886df7e334a8bedb346f869e2ef2e984ab3f5954b86be25a87551b0b98cd1ed7
+size 6178985456

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26031738880
+  },
+  "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-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-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-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-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-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-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-00001-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-00001-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-00002-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-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-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.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.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.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b8b95669e052f3f7acd646c3a2c66ab097011fd1b7108c65e4f1208dc9b38b
+size 15704

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5bab5a8aaa689b744902a64e0b974f78f2d58cfde86cd7d538b61f9ad6b526b
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,2424 @@
+{
+  "best_metric": 41.125,
+  "best_model_checkpoint": "result/Chat-Llama-2-13b-chat-hf-mezo-ft-20000-16-1e-3-1e-1-0/checkpoint-4000",
+  "epoch": 63.492063492063494,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.001,
+      "loss": 31.3156,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.001,
+      "loss": 31.675,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.001,
+      "loss": 31.5031,
+      "step": 30
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.001,
+      "loss": 31.4563,
+      "step": 40
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.001,
+      "loss": 31.4125,
+      "step": 50
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.001,
+      "loss": 31.7234,
+      "step": 60
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.001,
+      "loss": 31.6281,
+      "step": 70
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.001,
+      "loss": 31.6859,
+      "step": 80
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.001,
+      "loss": 31.6109,
+      "step": 90
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.001,
+      "loss": 31.7641,
+      "step": 100
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.001,
+      "loss": 31.7063,
+      "step": 110
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.001,
+      "loss": 31.85,
+      "step": 120
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.001,
+      "loss": 31.975,
+      "step": 130
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.001,
+      "loss": 31.9344,
+      "step": 140
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.001,
+      "loss": 32.0484,
+      "step": 150
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.001,
+      "loss": 32.0344,
+      "step": 160
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.001,
+      "loss": 32.0703,
+      "step": 170
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.001,
+      "loss": 32.0656,
+      "step": 180
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.001,
+      "loss": 32.0734,
+      "step": 190
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.001,
+      "loss": 32.2547,
+      "step": 200
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.001,
+      "loss": 32.1437,
+      "step": 210
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.001,
+      "loss": 32.3672,
+      "step": 220
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.001,
+      "loss": 32.2766,
+      "step": 230
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.001,
+      "loss": 32.3906,
+      "step": 240
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.001,
+      "loss": 32.6156,
+      "step": 250
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 0.001,
+      "loss": 32.5547,
+      "step": 260
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.001,
+      "loss": 32.8094,
+      "step": 270
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.001,
+      "loss": 32.7406,
+      "step": 280
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.001,
+      "loss": 32.9031,
+      "step": 290
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.001,
+      "loss": 32.8188,
+      "step": 300
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.001,
+      "loss": 32.9562,
+      "step": 310
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 0.001,
+      "loss": 32.9469,
+      "step": 320
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.001,
+      "loss": 33.0625,
+      "step": 330
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 0.001,
+      "loss": 33.0594,
+      "step": 340
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 0.001,
+      "loss": 33.1031,
+      "step": 350
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.001,
+      "loss": 33.2094,
+      "step": 360
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 0.001,
+      "loss": 33.2906,
+      "step": 370
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.001,
+      "loss": 33.3406,
+      "step": 380
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.001,
+      "loss": 33.2656,
+      "step": 390
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 0.001,
+      "loss": 33.3719,
+      "step": 400
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 0.001,
+      "loss": 33.4844,
+      "step": 410
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.001,
+      "loss": 33.4625,
+      "step": 420
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 0.001,
+      "loss": 33.4438,
+      "step": 430
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 0.001,
+      "loss": 33.5844,
+      "step": 440
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.001,
+      "loss": 33.6281,
+      "step": 450
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 0.001,
+      "loss": 33.7062,
+      "step": 460
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 0.001,
+      "loss": 33.6719,
+      "step": 470
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 0.001,
+      "loss": 33.7156,
+      "step": 480
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 0.001,
+      "loss": 33.75,
+      "step": 490
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 0.001,
+      "loss": 33.8344,
+      "step": 500
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.001,
+      "loss": 33.725,
+      "step": 510
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 0.001,
+      "loss": 33.9688,
+      "step": 520
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 0.001,
+      "loss": 33.9344,
+      "step": 530
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.001,
+      "loss": 34.1,
+      "step": 540
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 0.001,
+      "loss": 34.0719,
+      "step": 550
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 0.001,
+      "loss": 34.2563,
+      "step": 560
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 0.001,
+      "loss": 34.0438,
+      "step": 570
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 0.001,
+      "loss": 34.3094,
+      "step": 580
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 0.001,
+      "loss": 34.3687,
+      "step": 590
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 0.001,
+      "loss": 34.4406,
+      "step": 600
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 0.001,
+      "loss": 34.3531,
+      "step": 610
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 0.001,
+      "loss": 34.3344,
+      "step": 620
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.001,
+      "loss": 34.4125,
+      "step": 630
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 0.001,
+      "loss": 34.4,
+      "step": 640
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 0.001,
+      "loss": 34.4906,
+      "step": 650
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 0.001,
+      "loss": 34.5125,
+      "step": 660
+    },
+    {
+      "epoch": 10.63,
+      "learning_rate": 0.001,
+      "loss": 34.5875,
+      "step": 670
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 0.001,
+      "loss": 34.7281,
+      "step": 680
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 0.001,
+      "loss": 34.825,
+      "step": 690
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 0.001,
+      "loss": 34.7437,
+      "step": 700
+    },
+    {
+      "epoch": 11.27,
+      "learning_rate": 0.001,
+      "loss": 34.6531,
+      "step": 710
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.001,
+      "loss": 34.8531,
+      "step": 720
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 0.001,
+      "loss": 34.8438,
+      "step": 730
+    },
+    {
+      "epoch": 11.75,
+      "learning_rate": 0.001,
+      "loss": 35.0,
+      "step": 740
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.001,
+      "loss": 34.9562,
+      "step": 750
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 0.001,
+      "loss": 34.9781,
+      "step": 760
+    },
+    {
+      "epoch": 12.22,
+      "learning_rate": 0.001,
+      "loss": 35.0625,
+      "step": 770
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 0.001,
+      "loss": 35.1063,
+      "step": 780
+    },
+    {
+      "epoch": 12.54,
+      "learning_rate": 0.001,
+      "loss": 35.1594,
+      "step": 790
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 0.001,
+      "loss": 35.2,
+      "step": 800
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 0.001,
+      "loss": 35.1281,
+      "step": 810
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 0.001,
+      "loss": 35.3563,
+      "step": 820
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 0.001,
+      "loss": 35.1688,
+      "step": 830
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 0.001,
+      "loss": 35.3625,
+      "step": 840
+    },
+    {
+      "epoch": 13.49,
+      "learning_rate": 0.001,
+      "loss": 35.5438,
+      "step": 850
+    },
+    {
+      "epoch": 13.65,
+      "learning_rate": 0.001,
+      "loss": 35.3937,
+      "step": 860
+    },
+    {
+      "epoch": 13.81,
+      "learning_rate": 0.001,
+      "loss": 35.3937,
+      "step": 870
+    },
+    {
+      "epoch": 13.97,
+      "learning_rate": 0.001,
+      "loss": 35.5938,
+      "step": 880
+    },
+    {
+      "epoch": 14.13,
+      "learning_rate": 0.001,
+      "loss": 35.3781,
+      "step": 890
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 0.001,
+      "loss": 35.775,
+      "step": 900
+    },
+    {
+      "epoch": 14.44,
+      "learning_rate": 0.001,
+      "loss": 35.7594,
+      "step": 910
+    },
+    {
+      "epoch": 14.6,
+      "learning_rate": 0.001,
+      "loss": 35.5438,
+      "step": 920
+    },
+    {
+      "epoch": 14.76,
+      "learning_rate": 0.001,
+      "loss": 35.8406,
+      "step": 930
+    },
+    {
+      "epoch": 14.92,
+      "learning_rate": 0.001,
+      "loss": 35.6,
+      "step": 940
+    },
+    {
+      "epoch": 15.08,
+      "learning_rate": 0.001,
+      "loss": 35.8844,
+      "step": 950
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 0.001,
+      "loss": 35.9594,
+      "step": 960
+    },
+    {
+      "epoch": 15.4,
+      "learning_rate": 0.001,
+      "loss": 35.8281,
+      "step": 970
+    },
+    {
+      "epoch": 15.56,
+      "learning_rate": 0.001,
+      "loss": 36.0125,
+      "step": 980
+    },
+    {
+      "epoch": 15.71,
+      "learning_rate": 0.001,
+      "loss": 36.1313,
+      "step": 990
+    },
+    {
+      "epoch": 15.87,
+      "learning_rate": 0.001,
+      "loss": 36.0656,
+      "step": 1000
+    },
+    {
+      "epoch": 16.03,
+      "learning_rate": 0.001,
+      "loss": 36.1938,
+      "step": 1010
+    },
+    {
+      "epoch": 16.19,
+      "learning_rate": 0.001,
+      "loss": 36.2031,
+      "step": 1020
+    },
+    {
+      "epoch": 16.35,
+      "learning_rate": 0.001,
+      "loss": 36.1688,
+      "step": 1030
+    },
+    {
+      "epoch": 16.51,
+      "learning_rate": 0.001,
+      "loss": 36.3156,
+      "step": 1040
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 0.001,
+      "loss": 36.2719,
+      "step": 1050
+    },
+    {
+      "epoch": 16.83,
+      "learning_rate": 0.001,
+      "loss": 36.4656,
+      "step": 1060
+    },
+    {
+      "epoch": 16.98,
+      "learning_rate": 0.001,
+      "loss": 36.3687,
+      "step": 1070
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 0.001,
+      "loss": 36.4031,
+      "step": 1080
+    },
+    {
+      "epoch": 17.3,
+      "learning_rate": 0.001,
+      "loss": 36.5469,
+      "step": 1090
+    },
+    {
+      "epoch": 17.46,
+      "learning_rate": 0.001,
+      "loss": 36.5094,
+      "step": 1100
+    },
+    {
+      "epoch": 17.62,
+      "learning_rate": 0.001,
+      "loss": 36.6156,
+      "step": 1110
+    },
+    {
+      "epoch": 17.78,
+      "learning_rate": 0.001,
+      "loss": 36.5531,
+      "step": 1120
+    },
+    {
+      "epoch": 17.94,
+      "learning_rate": 0.001,
+      "loss": 36.525,
+      "step": 1130
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 0.001,
+      "loss": 36.6562,
+      "step": 1140
+    },
+    {
+      "epoch": 18.25,
+      "learning_rate": 0.001,
+      "loss": 36.5812,
+      "step": 1150
+    },
+    {
+      "epoch": 18.41,
+      "learning_rate": 0.001,
+      "loss": 36.6625,
+      "step": 1160
+    },
+    {
+      "epoch": 18.57,
+      "learning_rate": 0.001,
+      "loss": 36.625,
+      "step": 1170
+    },
+    {
+      "epoch": 18.73,
+      "learning_rate": 0.001,
+      "loss": 36.8719,
+      "step": 1180
+    },
+    {
+      "epoch": 18.89,
+      "learning_rate": 0.001,
+      "loss": 36.9219,
+      "step": 1190
+    },
+    {
+      "epoch": 19.05,
+      "learning_rate": 0.001,
+      "loss": 36.8875,
+      "step": 1200
+    },
+    {
+      "epoch": 19.21,
+      "learning_rate": 0.001,
+      "loss": 36.7344,
+      "step": 1210
+    },
+    {
+      "epoch": 19.37,
+      "learning_rate": 0.001,
+      "loss": 36.9562,
+      "step": 1220
+    },
+    {
+      "epoch": 19.52,
+      "learning_rate": 0.001,
+      "loss": 37.1688,
+      "step": 1230
+    },
+    {
+      "epoch": 19.68,
+      "learning_rate": 0.001,
+      "loss": 37.2156,
+      "step": 1240
+    },
+    {
+      "epoch": 19.84,
+      "learning_rate": 0.001,
+      "loss": 37.1719,
+      "step": 1250
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.001,
+      "loss": 37.2594,
+      "step": 1260
+    },
+    {
+      "epoch": 20.16,
+      "learning_rate": 0.001,
+      "loss": 37.4062,
+      "step": 1270
+    },
+    {
+      "epoch": 20.32,
+      "learning_rate": 0.001,
+      "loss": 37.4937,
+      "step": 1280
+    },
+    {
+      "epoch": 20.48,
+      "learning_rate": 0.001,
+      "loss": 37.5625,
+      "step": 1290
+    },
+    {
+      "epoch": 20.63,
+      "learning_rate": 0.001,
+      "loss": 37.6,
+      "step": 1300
+    },
+    {
+      "epoch": 20.79,
+      "learning_rate": 0.001,
+      "loss": 37.6156,
+      "step": 1310
+    },
+    {
+      "epoch": 20.95,
+      "learning_rate": 0.001,
+      "loss": 37.625,
+      "step": 1320
+    },
+    {
+      "epoch": 21.11,
+      "learning_rate": 0.001,
+      "loss": 37.5906,
+      "step": 1330
+    },
+    {
+      "epoch": 21.27,
+      "learning_rate": 0.001,
+      "loss": 37.8344,
+      "step": 1340
+    },
+    {
+      "epoch": 21.43,
+      "learning_rate": 0.001,
+      "loss": 37.7656,
+      "step": 1350
+    },
+    {
+      "epoch": 21.59,
+      "learning_rate": 0.001,
+      "loss": 37.8875,
+      "step": 1360
+    },
+    {
+      "epoch": 21.75,
+      "learning_rate": 0.001,
+      "loss": 37.6437,
+      "step": 1370
+    },
+    {
+      "epoch": 21.9,
+      "learning_rate": 0.001,
+      "loss": 38.0063,
+      "step": 1380
+    },
+    {
+      "epoch": 22.06,
+      "learning_rate": 0.001,
+      "loss": 38.0594,
+      "step": 1390
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 0.001,
+      "loss": 37.9656,
+      "step": 1400
+    },
+    {
+      "epoch": 22.38,
+      "learning_rate": 0.001,
+      "loss": 38.125,
+      "step": 1410
+    },
+    {
+      "epoch": 22.54,
+      "learning_rate": 0.001,
+      "loss": 38.1469,
+      "step": 1420
+    },
+    {
+      "epoch": 22.7,
+      "learning_rate": 0.001,
+      "loss": 38.2188,
+      "step": 1430
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 0.001,
+      "loss": 38.0969,
+      "step": 1440
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.001,
+      "loss": 38.3469,
+      "step": 1450
+    },
+    {
+      "epoch": 23.17,
+      "learning_rate": 0.001,
+      "loss": 38.3563,
+      "step": 1460
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 0.001,
+      "loss": 38.3719,
+      "step": 1470
+    },
+    {
+      "epoch": 23.49,
+      "learning_rate": 0.001,
+      "loss": 38.3375,
+      "step": 1480
+    },
+    {
+      "epoch": 23.65,
+      "learning_rate": 0.001,
+      "loss": 38.5375,
+      "step": 1490
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 0.001,
+      "loss": 38.4531,
+      "step": 1500
+    },
+    {
+      "epoch": 23.97,
+      "learning_rate": 0.001,
+      "loss": 38.4469,
+      "step": 1510
+    },
+    {
+      "epoch": 24.13,
+      "learning_rate": 0.001,
+      "loss": 38.4375,
+      "step": 1520
+    },
+    {
+      "epoch": 24.29,
+      "learning_rate": 0.001,
+      "loss": 38.6406,
+      "step": 1530
+    },
+    {
+      "epoch": 24.44,
+      "learning_rate": 0.001,
+      "loss": 38.7156,
+      "step": 1540
+    },
+    {
+      "epoch": 24.6,
+      "learning_rate": 0.001,
+      "loss": 38.7719,
+      "step": 1550
+    },
+    {
+      "epoch": 24.76,
+      "learning_rate": 0.001,
+      "loss": 38.7313,
+      "step": 1560
+    },
+    {
+      "epoch": 24.92,
+      "learning_rate": 0.001,
+      "loss": 38.9125,
+      "step": 1570
+    },
+    {
+      "epoch": 25.08,
+      "learning_rate": 0.001,
+      "loss": 38.8281,
+      "step": 1580
+    },
+    {
+      "epoch": 25.24,
+      "learning_rate": 0.001,
+      "loss": 38.9062,
+      "step": 1590
+    },
+    {
+      "epoch": 25.4,
+      "learning_rate": 0.001,
+      "loss": 39.025,
+      "step": 1600
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 0.001,
+      "loss": 38.9125,
+      "step": 1610
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 0.001,
+      "loss": 39.0594,
+      "step": 1620
+    },
+    {
+      "epoch": 25.87,
+      "learning_rate": 0.001,
+      "loss": 38.9625,
+      "step": 1630
+    },
+    {
+      "epoch": 26.03,
+      "learning_rate": 0.001,
+      "loss": 39.1187,
+      "step": 1640
+    },
+    {
+      "epoch": 26.19,
+      "learning_rate": 0.001,
+      "loss": 39.1,
+      "step": 1650
+    },
+    {
+      "epoch": 26.35,
+      "learning_rate": 0.001,
+      "loss": 39.1313,
+      "step": 1660
+    },
+    {
+      "epoch": 26.51,
+      "learning_rate": 0.001,
+      "loss": 39.2906,
+      "step": 1670
+    },
+    {
+      "epoch": 26.67,
+      "learning_rate": 0.001,
+      "loss": 39.1719,
+      "step": 1680
+    },
+    {
+      "epoch": 26.83,
+      "learning_rate": 0.001,
+      "loss": 39.2687,
+      "step": 1690
+    },
+    {
+      "epoch": 26.98,
+      "learning_rate": 0.001,
+      "loss": 39.4312,
+      "step": 1700
+    },
+    {
+      "epoch": 27.14,
+      "learning_rate": 0.001,
+      "loss": 39.2563,
+      "step": 1710
+    },
+    {
+      "epoch": 27.3,
+      "learning_rate": 0.001,
+      "loss": 39.3344,
+      "step": 1720
+    },
+    {
+      "epoch": 27.46,
+      "learning_rate": 0.001,
+      "loss": 39.375,
+      "step": 1730
+    },
+    {
+      "epoch": 27.62,
+      "learning_rate": 0.001,
+      "loss": 39.4031,
+      "step": 1740
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 0.001,
+      "loss": 39.4969,
+      "step": 1750
+    },
+    {
+      "epoch": 27.94,
+      "learning_rate": 0.001,
+      "loss": 39.5219,
+      "step": 1760
+    },
+    {
+      "epoch": 28.1,
+      "learning_rate": 0.001,
+      "loss": 39.5719,
+      "step": 1770
+    },
+    {
+      "epoch": 28.25,
+      "learning_rate": 0.001,
+      "loss": 39.6719,
+      "step": 1780
+    },
+    {
+      "epoch": 28.41,
+      "learning_rate": 0.001,
+      "loss": 39.7156,
+      "step": 1790
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 0.001,
+      "loss": 39.8312,
+      "step": 1800
+    },
+    {
+      "epoch": 28.73,
+      "learning_rate": 0.001,
+      "loss": 39.8687,
+      "step": 1810
+    },
+    {
+      "epoch": 28.89,
+      "learning_rate": 0.001,
+      "loss": 39.9906,
+      "step": 1820
+    },
+    {
+      "epoch": 29.05,
+      "learning_rate": 0.001,
+      "loss": 40.0156,
+      "step": 1830
+    },
+    {
+      "epoch": 29.21,
+      "learning_rate": 0.001,
+      "loss": 40.1469,
+      "step": 1840
+    },
+    {
+      "epoch": 29.37,
+      "learning_rate": 0.001,
+      "loss": 40.1938,
+      "step": 1850
+    },
+    {
+      "epoch": 29.52,
+      "learning_rate": 0.001,
+      "loss": 40.1594,
+      "step": 1860
+    },
+    {
+      "epoch": 29.68,
+      "learning_rate": 0.001,
+      "loss": 39.9094,
+      "step": 1870
+    },
+    {
+      "epoch": 29.84,
+      "learning_rate": 0.001,
+      "loss": 40.1625,
+      "step": 1880
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.001,
+      "loss": 40.1906,
+      "step": 1890
+    },
+    {
+      "epoch": 30.16,
+      "learning_rate": 0.001,
+      "loss": 40.3406,
+      "step": 1900
+    },
+    {
+      "epoch": 30.32,
+      "learning_rate": 0.001,
+      "loss": 40.2812,
+      "step": 1910
+    },
+    {
+      "epoch": 30.48,
+      "learning_rate": 0.001,
+      "loss": 40.2969,
+      "step": 1920
+    },
+    {
+      "epoch": 30.63,
+      "learning_rate": 0.001,
+      "loss": 40.2469,
+      "step": 1930
+    },
+    {
+      "epoch": 30.79,
+      "learning_rate": 0.001,
+      "loss": 40.3656,
+      "step": 1940
+    },
+    {
+      "epoch": 30.95,
+      "learning_rate": 0.001,
+      "loss": 40.4156,
+      "step": 1950
+    },
+    {
+      "epoch": 31.11,
+      "learning_rate": 0.001,
+      "loss": 40.4844,
+      "step": 1960
+    },
+    {
+      "epoch": 31.27,
+      "learning_rate": 0.001,
+      "loss": 40.4531,
+      "step": 1970
+    },
+    {
+      "epoch": 31.43,
+      "learning_rate": 0.001,
+      "loss": 40.6187,
+      "step": 1980
+    },
+    {
+      "epoch": 31.59,
+      "learning_rate": 0.001,
+      "loss": 40.8844,
+      "step": 1990
+    },
+    {
+      "epoch": 31.75,
+      "learning_rate": 0.001,
+      "loss": 40.8125,
+      "step": 2000
+    },
+    {
+      "epoch": 31.9,
+      "learning_rate": 0.001,
+      "loss": 40.9562,
+      "step": 2010
+    },
+    {
+      "epoch": 32.06,
+      "learning_rate": 0.001,
+      "loss": 40.8312,
+      "step": 2020
+    },
+    {
+      "epoch": 32.22,
+      "learning_rate": 0.001,
+      "loss": 40.825,
+      "step": 2030
+    },
+    {
+      "epoch": 32.38,
+      "learning_rate": 0.001,
+      "loss": 41.0594,
+      "step": 2040
+    },
+    {
+      "epoch": 32.54,
+      "learning_rate": 0.001,
+      "loss": 40.8875,
+      "step": 2050
+    },
+    {
+      "epoch": 32.7,
+      "learning_rate": 0.001,
+      "loss": 40.8062,
+      "step": 2060
+    },
+    {
+      "epoch": 32.86,
+      "learning_rate": 0.001,
+      "loss": 41.0844,
+      "step": 2070
+    },
+    {
+      "epoch": 33.02,
+      "learning_rate": 0.001,
+      "loss": 41.1187,
+      "step": 2080
+    },
+    {
+      "epoch": 33.17,
+      "learning_rate": 0.001,
+      "loss": 41.1031,
+      "step": 2090
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 0.001,
+      "loss": 41.2344,
+      "step": 2100
+    },
+    {
+      "epoch": 33.49,
+      "learning_rate": 0.001,
+      "loss": 41.175,
+      "step": 2110
+    },
+    {
+      "epoch": 33.65,
+      "learning_rate": 0.001,
+      "loss": 41.4813,
+      "step": 2120
+    },
+    {
+      "epoch": 33.81,
+      "learning_rate": 0.001,
+      "loss": 41.4031,
+      "step": 2130
+    },
+    {
+      "epoch": 33.97,
+      "learning_rate": 0.001,
+      "loss": 41.2875,
+      "step": 2140
+    },
+    {
+      "epoch": 34.13,
+      "learning_rate": 0.001,
+      "loss": 41.6031,
+      "step": 2150
+    },
+    {
+      "epoch": 34.29,
+      "learning_rate": 0.001,
+      "loss": 41.3781,
+      "step": 2160
+    },
+    {
+      "epoch": 34.44,
+      "learning_rate": 0.001,
+      "loss": 41.7094,
+      "step": 2170
+    },
+    {
+      "epoch": 34.6,
+      "learning_rate": 0.001,
+      "loss": 41.6,
+      "step": 2180
+    },
+    {
+      "epoch": 34.76,
+      "learning_rate": 0.001,
+      "loss": 41.6313,
+      "step": 2190
+    },
+    {
+      "epoch": 34.92,
+      "learning_rate": 0.001,
+      "loss": 41.7125,
+      "step": 2200
+    },
+    {
+      "epoch": 35.08,
+      "learning_rate": 0.001,
+      "loss": 41.7625,
+      "step": 2210
+    },
+    {
+      "epoch": 35.24,
+      "learning_rate": 0.001,
+      "loss": 41.8656,
+      "step": 2220
+    },
+    {
+      "epoch": 35.4,
+      "learning_rate": 0.001,
+      "loss": 41.8531,
+      "step": 2230
+    },
+    {
+      "epoch": 35.56,
+      "learning_rate": 0.001,
+      "loss": 41.9312,
+      "step": 2240
+    },
+    {
+      "epoch": 35.71,
+      "learning_rate": 0.001,
+      "loss": 41.9406,
+      "step": 2250
+    },
+    {
+      "epoch": 35.87,
+      "learning_rate": 0.001,
+      "loss": 42.0187,
+      "step": 2260
+    },
+    {
+      "epoch": 36.03,
+      "learning_rate": 0.001,
+      "loss": 42.2437,
+      "step": 2270
+    },
+    {
+      "epoch": 36.19,
+      "learning_rate": 0.001,
+      "loss": 42.15,
+      "step": 2280
+    },
+    {
+      "epoch": 36.35,
+      "learning_rate": 0.001,
+      "loss": 42.2094,
+      "step": 2290
+    },
+    {
+      "epoch": 36.51,
+      "learning_rate": 0.001,
+      "loss": 42.2344,
+      "step": 2300
+    },
+    {
+      "epoch": 36.67,
+      "learning_rate": 0.001,
+      "loss": 42.4469,
+      "step": 2310
+    },
+    {
+      "epoch": 36.83,
+      "learning_rate": 0.001,
+      "loss": 42.3031,
+      "step": 2320
+    },
+    {
+      "epoch": 36.98,
+      "learning_rate": 0.001,
+      "loss": 42.3625,
+      "step": 2330
+    },
+    {
+      "epoch": 37.14,
+      "learning_rate": 0.001,
+      "loss": 42.7094,
+      "step": 2340
+    },
+    {
+      "epoch": 37.3,
+      "learning_rate": 0.001,
+      "loss": 42.6344,
+      "step": 2350
+    },
+    {
+      "epoch": 37.46,
+      "learning_rate": 0.001,
+      "loss": 42.6531,
+      "step": 2360
+    },
+    {
+      "epoch": 37.62,
+      "learning_rate": 0.001,
+      "loss": 42.6063,
+      "step": 2370
+    },
+    {
+      "epoch": 37.78,
+      "learning_rate": 0.001,
+      "loss": 42.6313,
+      "step": 2380
+    },
+    {
+      "epoch": 37.94,
+      "learning_rate": 0.001,
+      "loss": 42.7375,
+      "step": 2390
+    },
+    {
+      "epoch": 38.1,
+      "learning_rate": 0.001,
+      "loss": 42.7563,
+      "step": 2400
+    },
+    {
+      "epoch": 38.25,
+      "learning_rate": 0.001,
+      "loss": 42.7812,
+      "step": 2410
+    },
+    {
+      "epoch": 38.41,
+      "learning_rate": 0.001,
+      "loss": 42.7969,
+      "step": 2420
+    },
+    {
+      "epoch": 38.57,
+      "learning_rate": 0.001,
+      "loss": 42.8375,
+      "step": 2430
+    },
+    {
+      "epoch": 38.73,
+      "learning_rate": 0.001,
+      "loss": 43.0281,
+      "step": 2440
+    },
+    {
+      "epoch": 38.89,
+      "learning_rate": 0.001,
+      "loss": 42.9031,
+      "step": 2450
+    },
+    {
+      "epoch": 39.05,
+      "learning_rate": 0.001,
+      "loss": 42.9969,
+      "step": 2460
+    },
+    {
+      "epoch": 39.21,
+      "learning_rate": 0.001,
+      "loss": 43.075,
+      "step": 2470
+    },
+    {
+      "epoch": 39.37,
+      "learning_rate": 0.001,
+      "loss": 43.075,
+      "step": 2480
+    },
+    {
+      "epoch": 39.52,
+      "learning_rate": 0.001,
+      "loss": 43.0812,
+      "step": 2490
+    },
+    {
+      "epoch": 39.68,
+      "learning_rate": 0.001,
+      "loss": 43.2406,
+      "step": 2500
+    },
+    {
+      "epoch": 39.84,
+      "learning_rate": 0.001,
+      "loss": 43.1375,
+      "step": 2510
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.001,
+      "loss": 43.1625,
+      "step": 2520
+    },
+    {
+      "epoch": 40.16,
+      "learning_rate": 0.001,
+      "loss": 43.2313,
+      "step": 2530
+    },
+    {
+      "epoch": 40.32,
+      "learning_rate": 0.001,
+      "loss": 43.4375,
+      "step": 2540
+    },
+    {
+      "epoch": 40.48,
+      "learning_rate": 0.001,
+      "loss": 43.4719,
+      "step": 2550
+    },
+    {
+      "epoch": 40.63,
+      "learning_rate": 0.001,
+      "loss": 43.3969,
+      "step": 2560
+    },
+    {
+      "epoch": 40.79,
+      "learning_rate": 0.001,
+      "loss": 43.675,
+      "step": 2570
+    },
+    {
+      "epoch": 40.95,
+      "learning_rate": 0.001,
+      "loss": 43.5562,
+      "step": 2580
+    },
+    {
+      "epoch": 41.11,
+      "learning_rate": 0.001,
+      "loss": 43.6844,
+      "step": 2590
+    },
+    {
+      "epoch": 41.27,
+      "learning_rate": 0.001,
+      "loss": 43.8094,
+      "step": 2600
+    },
+    {
+      "epoch": 41.43,
+      "learning_rate": 0.001,
+      "loss": 43.8656,
+      "step": 2610
+    },
+    {
+      "epoch": 41.59,
+      "learning_rate": 0.001,
+      "loss": 43.9969,
+      "step": 2620
+    },
+    {
+      "epoch": 41.75,
+      "learning_rate": 0.001,
+      "loss": 43.8469,
+      "step": 2630
+    },
+    {
+      "epoch": 41.9,
+      "learning_rate": 0.001,
+      "loss": 44.0688,
+      "step": 2640
+    },
+    {
+      "epoch": 42.06,
+      "learning_rate": 0.001,
+      "loss": 43.9531,
+      "step": 2650
+    },
+    {
+      "epoch": 42.22,
+      "learning_rate": 0.001,
+      "loss": 43.9937,
+      "step": 2660
+    },
+    {
+      "epoch": 42.38,
+      "learning_rate": 0.001,
+      "loss": 44.1125,
+      "step": 2670
+    },
+    {
+      "epoch": 42.54,
+      "learning_rate": 0.001,
+      "loss": 44.1969,
+      "step": 2680
+    },
+    {
+      "epoch": 42.7,
+      "learning_rate": 0.001,
+      "loss": 44.1781,
+      "step": 2690
+    },
+    {
+      "epoch": 42.86,
+      "learning_rate": 0.001,
+      "loss": 44.3781,
+      "step": 2700
+    },
+    {
+      "epoch": 43.02,
+      "learning_rate": 0.001,
+      "loss": 44.3125,
+      "step": 2710
+    },
+    {
+      "epoch": 43.17,
+      "learning_rate": 0.001,
+      "loss": 44.2875,
+      "step": 2720
+    },
+    {
+      "epoch": 43.33,
+      "learning_rate": 0.001,
+      "loss": 44.3344,
+      "step": 2730
+    },
+    {
+      "epoch": 43.49,
+      "learning_rate": 0.001,
+      "loss": 44.3188,
+      "step": 2740
+    },
+    {
+      "epoch": 43.65,
+      "learning_rate": 0.001,
+      "loss": 44.3281,
+      "step": 2750
+    },
+    {
+      "epoch": 43.81,
+      "learning_rate": 0.001,
+      "loss": 44.5063,
+      "step": 2760
+    },
+    {
+      "epoch": 43.97,
+      "learning_rate": 0.001,
+      "loss": 44.5625,
+      "step": 2770
+    },
+    {
+      "epoch": 44.13,
+      "learning_rate": 0.001,
+      "loss": 44.2313,
+      "step": 2780
+    },
+    {
+      "epoch": 44.29,
+      "learning_rate": 0.001,
+      "loss": 44.7313,
+      "step": 2790
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 0.001,
+      "loss": 44.6125,
+      "step": 2800
+    },
+    {
+      "epoch": 44.6,
+      "learning_rate": 0.001,
+      "loss": 44.7125,
+      "step": 2810
+    },
+    {
+      "epoch": 44.76,
+      "learning_rate": 0.001,
+      "loss": 44.9594,
+      "step": 2820
+    },
+    {
+      "epoch": 44.92,
+      "learning_rate": 0.001,
+      "loss": 44.975,
+      "step": 2830
+    },
+    {
+      "epoch": 45.08,
+      "learning_rate": 0.001,
+      "loss": 44.9531,
+      "step": 2840
+    },
+    {
+      "epoch": 45.24,
+      "learning_rate": 0.001,
+      "loss": 44.9406,
+      "step": 2850
+    },
+    {
+      "epoch": 45.4,
+      "learning_rate": 0.001,
+      "loss": 45.0812,
+      "step": 2860
+    },
+    {
+      "epoch": 45.56,
+      "learning_rate": 0.001,
+      "loss": 45.1969,
+      "step": 2870
+    },
+    {
+      "epoch": 45.71,
+      "learning_rate": 0.001,
+      "loss": 44.9125,
+      "step": 2880
+    },
+    {
+      "epoch": 45.87,
+      "learning_rate": 0.001,
+      "loss": 45.0312,
+      "step": 2890
+    },
+    {
+      "epoch": 46.03,
+      "learning_rate": 0.001,
+      "loss": 45.1406,
+      "step": 2900
+    },
+    {
+      "epoch": 46.19,
+      "learning_rate": 0.001,
+      "loss": 45.3125,
+      "step": 2910
+    },
+    {
+      "epoch": 46.35,
+      "learning_rate": 0.001,
+      "loss": 45.4719,
+      "step": 2920
+    },
+    {
+      "epoch": 46.51,
+      "learning_rate": 0.001,
+      "loss": 45.3312,
+      "step": 2930
+    },
+    {
+      "epoch": 46.67,
+      "learning_rate": 0.001,
+      "loss": 45.5156,
+      "step": 2940
+    },
+    {
+      "epoch": 46.83,
+      "learning_rate": 0.001,
+      "loss": 45.5406,
+      "step": 2950
+    },
+    {
+      "epoch": 46.98,
+      "learning_rate": 0.001,
+      "loss": 45.6063,
+      "step": 2960
+    },
+    {
+      "epoch": 47.14,
+      "learning_rate": 0.001,
+      "loss": 45.5781,
+      "step": 2970
+    },
+    {
+      "epoch": 47.3,
+      "learning_rate": 0.001,
+      "loss": 45.8438,
+      "step": 2980
+    },
+    {
+      "epoch": 47.46,
+      "learning_rate": 0.001,
+      "loss": 45.8813,
+      "step": 2990
+    },
+    {
+      "epoch": 47.62,
+      "learning_rate": 0.001,
+      "loss": 46.0375,
+      "step": 3000
+    },
+    {
+      "epoch": 47.78,
+      "learning_rate": 0.001,
+      "loss": 45.7313,
+      "step": 3010
+    },
+    {
+      "epoch": 47.94,
+      "learning_rate": 0.001,
+      "loss": 45.7844,
+      "step": 3020
+    },
+    {
+      "epoch": 48.1,
+      "learning_rate": 0.001,
+      "loss": 46.0875,
+      "step": 3030
+    },
+    {
+      "epoch": 48.25,
+      "learning_rate": 0.001,
+      "loss": 45.8438,
+      "step": 3040
+    },
+    {
+      "epoch": 48.41,
+      "learning_rate": 0.001,
+      "loss": 45.9375,
+      "step": 3050
+    },
+    {
+      "epoch": 48.57,
+      "learning_rate": 0.001,
+      "loss": 46.0656,
+      "step": 3060
+    },
+    {
+      "epoch": 48.73,
+      "learning_rate": 0.001,
+      "loss": 46.0469,
+      "step": 3070
+    },
+    {
+      "epoch": 48.89,
+      "learning_rate": 0.001,
+      "loss": 46.325,
+      "step": 3080
+    },
+    {
+      "epoch": 49.05,
+      "learning_rate": 0.001,
+      "loss": 46.2125,
+      "step": 3090
+    },
+    {
+      "epoch": 49.21,
+      "learning_rate": 0.001,
+      "loss": 46.3438,
+      "step": 3100
+    },
+    {
+      "epoch": 49.37,
+      "learning_rate": 0.001,
+      "loss": 46.4562,
+      "step": 3110
+    },
+    {
+      "epoch": 49.52,
+      "learning_rate": 0.001,
+      "loss": 46.3875,
+      "step": 3120
+    },
+    {
+      "epoch": 49.68,
+      "learning_rate": 0.001,
+      "loss": 46.1625,
+      "step": 3130
+    },
+    {
+      "epoch": 49.84,
+      "learning_rate": 0.001,
+      "loss": 46.7,
+      "step": 3140
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.001,
+      "loss": 46.4406,
+      "step": 3150
+    },
+    {
+      "epoch": 50.16,
+      "learning_rate": 0.001,
+      "loss": 46.5906,
+      "step": 3160
+    },
+    {
+      "epoch": 50.32,
+      "learning_rate": 0.001,
+      "loss": 46.6156,
+      "step": 3170
+    },
+    {
+      "epoch": 50.48,
+      "learning_rate": 0.001,
+      "loss": 46.6187,
+      "step": 3180
+    },
+    {
+      "epoch": 50.63,
+      "learning_rate": 0.001,
+      "loss": 46.8219,
+      "step": 3190
+    },
+    {
+      "epoch": 50.79,
+      "learning_rate": 0.001,
+      "loss": 46.7281,
+      "step": 3200
+    },
+    {
+      "epoch": 50.95,
+      "learning_rate": 0.001,
+      "loss": 46.6469,
+      "step": 3210
+    },
+    {
+      "epoch": 51.11,
+      "learning_rate": 0.001,
+      "loss": 46.7031,
+      "step": 3220
+    },
+    {
+      "epoch": 51.27,
+      "learning_rate": 0.001,
+      "loss": 46.8312,
+      "step": 3230
+    },
+    {
+      "epoch": 51.43,
+      "learning_rate": 0.001,
+      "loss": 47.0844,
+      "step": 3240
+    },
+    {
+      "epoch": 51.59,
+      "learning_rate": 0.001,
+      "loss": 46.9156,
+      "step": 3250
+    },
+    {
+      "epoch": 51.75,
+      "learning_rate": 0.001,
+      "loss": 46.9813,
+      "step": 3260
+    },
+    {
+      "epoch": 51.9,
+      "learning_rate": 0.001,
+      "loss": 47.3062,
+      "step": 3270
+    },
+    {
+      "epoch": 52.06,
+      "learning_rate": 0.001,
+      "loss": 47.2313,
+      "step": 3280
+    },
+    {
+      "epoch": 52.22,
+      "learning_rate": 0.001,
+      "loss": 47.2656,
+      "step": 3290
+    },
+    {
+      "epoch": 52.38,
+      "learning_rate": 0.001,
+      "loss": 47.2031,
+      "step": 3300
+    },
+    {
+      "epoch": 52.54,
+      "learning_rate": 0.001,
+      "loss": 47.2812,
+      "step": 3310
+    },
+    {
+      "epoch": 52.7,
+      "learning_rate": 0.001,
+      "loss": 47.2281,
+      "step": 3320
+    },
+    {
+      "epoch": 52.86,
+      "learning_rate": 0.001,
+      "loss": 47.2906,
+      "step": 3330
+    },
+    {
+      "epoch": 53.02,
+      "learning_rate": 0.001,
+      "loss": 47.4469,
+      "step": 3340
+    },
+    {
+      "epoch": 53.17,
+      "learning_rate": 0.001,
+      "loss": 47.3719,
+      "step": 3350
+    },
+    {
+      "epoch": 53.33,
+      "learning_rate": 0.001,
+      "loss": 47.4813,
+      "step": 3360
+    },
+    {
+      "epoch": 53.49,
+      "learning_rate": 0.001,
+      "loss": 47.5906,
+      "step": 3370
+    },
+    {
+      "epoch": 53.65,
+      "learning_rate": 0.001,
+      "loss": 47.5719,
+      "step": 3380
+    },
+    {
+      "epoch": 53.81,
+      "learning_rate": 0.001,
+      "loss": 47.5938,
+      "step": 3390
+    },
+    {
+      "epoch": 53.97,
+      "learning_rate": 0.001,
+      "loss": 47.5906,
+      "step": 3400
+    },
+    {
+      "epoch": 54.13,
+      "learning_rate": 0.001,
+      "loss": 47.8594,
+      "step": 3410
+    },
+    {
+      "epoch": 54.29,
+      "learning_rate": 0.001,
+      "loss": 47.7969,
+      "step": 3420
+    },
+    {
+      "epoch": 54.44,
+      "learning_rate": 0.001,
+      "loss": 47.7844,
+      "step": 3430
+    },
+    {
+      "epoch": 54.6,
+      "learning_rate": 0.001,
+      "loss": 47.7656,
+      "step": 3440
+    },
+    {
+      "epoch": 54.76,
+      "learning_rate": 0.001,
+      "loss": 48.0594,
+      "step": 3450
+    },
+    {
+      "epoch": 54.92,
+      "learning_rate": 0.001,
+      "loss": 47.8937,
+      "step": 3460
+    },
+    {
+      "epoch": 55.08,
+      "learning_rate": 0.001,
+      "loss": 48.0063,
+      "step": 3470
+    },
+    {
+      "epoch": 55.24,
+      "learning_rate": 0.001,
+      "loss": 47.8875,
+      "step": 3480
+    },
+    {
+      "epoch": 55.4,
+      "learning_rate": 0.001,
+      "loss": 47.9594,
+      "step": 3490
+    },
+    {
+      "epoch": 55.56,
+      "learning_rate": 0.001,
+      "loss": 48.0375,
+      "step": 3500
+    },
+    {
+      "epoch": 55.71,
+      "learning_rate": 0.001,
+      "loss": 47.9625,
+      "step": 3510
+    },
+    {
+      "epoch": 55.87,
+      "learning_rate": 0.001,
+      "loss": 48.2219,
+      "step": 3520
+    },
+    {
+      "epoch": 56.03,
+      "learning_rate": 0.001,
+      "loss": 48.2938,
+      "step": 3530
+    },
+    {
+      "epoch": 56.19,
+      "learning_rate": 0.001,
+      "loss": 48.3875,
+      "step": 3540
+    },
+    {
+      "epoch": 56.35,
+      "learning_rate": 0.001,
+      "loss": 48.3156,
+      "step": 3550
+    },
+    {
+      "epoch": 56.51,
+      "learning_rate": 0.001,
+      "loss": 48.4281,
+      "step": 3560
+    },
+    {
+      "epoch": 56.67,
+      "learning_rate": 0.001,
+      "loss": 48.3813,
+      "step": 3570
+    },
+    {
+      "epoch": 56.83,
+      "learning_rate": 0.001,
+      "loss": 48.6594,
+      "step": 3580
+    },
+    {
+      "epoch": 56.98,
+      "learning_rate": 0.001,
+      "loss": 48.5344,
+      "step": 3590
+    },
+    {
+      "epoch": 57.14,
+      "learning_rate": 0.001,
+      "loss": 48.4781,
+      "step": 3600
+    },
+    {
+      "epoch": 57.3,
+      "learning_rate": 0.001,
+      "loss": 48.6469,
+      "step": 3610
+    },
+    {
+      "epoch": 57.46,
+      "learning_rate": 0.001,
+      "loss": 48.7406,
+      "step": 3620
+    },
+    {
+      "epoch": 57.62,
+      "learning_rate": 0.001,
+      "loss": 48.8312,
+      "step": 3630
+    },
+    {
+      "epoch": 57.78,
+      "learning_rate": 0.001,
+      "loss": 48.7844,
+      "step": 3640
+    },
+    {
+      "epoch": 57.94,
+      "learning_rate": 0.001,
+      "loss": 48.9906,
+      "step": 3650
+    },
+    {
+      "epoch": 58.1,
+      "learning_rate": 0.001,
+      "loss": 48.7906,
+      "step": 3660
+    },
+    {
+      "epoch": 58.25,
+      "learning_rate": 0.001,
+      "loss": 49.2281,
+      "step": 3670
+    },
+    {
+      "epoch": 58.41,
+      "learning_rate": 0.001,
+      "loss": 49.2406,
+      "step": 3680
+    },
+    {
+      "epoch": 58.57,
+      "learning_rate": 0.001,
+      "loss": 48.9844,
+      "step": 3690
+    },
+    {
+      "epoch": 58.73,
+      "learning_rate": 0.001,
+      "loss": 49.0469,
+      "step": 3700
+    },
+    {
+      "epoch": 58.89,
+      "learning_rate": 0.001,
+      "loss": 49.3438,
+      "step": 3710
+    },
+    {
+      "epoch": 59.05,
+      "learning_rate": 0.001,
+      "loss": 49.2219,
+      "step": 3720
+    },
+    {
+      "epoch": 59.21,
+      "learning_rate": 0.001,
+      "loss": 49.3219,
+      "step": 3730
+    },
+    {
+      "epoch": 59.37,
+      "learning_rate": 0.001,
+      "loss": 49.4906,
+      "step": 3740
+    },
+    {
+      "epoch": 59.52,
+      "learning_rate": 0.001,
+      "loss": 49.2281,
+      "step": 3750
+    },
+    {
+      "epoch": 59.68,
+      "learning_rate": 0.001,
+      "loss": 49.4375,
+      "step": 3760
+    },
+    {
+      "epoch": 59.84,
+      "learning_rate": 0.001,
+      "loss": 49.4844,
+      "step": 3770
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 0.001,
+      "loss": 49.4969,
+      "step": 3780
+    },
+    {
+      "epoch": 60.16,
+      "learning_rate": 0.001,
+      "loss": 49.475,
+      "step": 3790
+    },
+    {
+      "epoch": 60.32,
+      "learning_rate": 0.001,
+      "loss": 49.7406,
+      "step": 3800
+    },
+    {
+      "epoch": 60.48,
+      "learning_rate": 0.001,
+      "loss": 49.7406,
+      "step": 3810
+    },
+    {
+      "epoch": 60.63,
+      "learning_rate": 0.001,
+      "loss": 49.7687,
+      "step": 3820
+    },
+    {
+      "epoch": 60.79,
+      "learning_rate": 0.001,
+      "loss": 49.6281,
+      "step": 3830
+    },
+    {
+      "epoch": 60.95,
+      "learning_rate": 0.001,
+      "loss": 49.8312,
+      "step": 3840
+    },
+    {
+      "epoch": 61.11,
+      "learning_rate": 0.001,
+      "loss": 50.1094,
+      "step": 3850
+    },
+    {
+      "epoch": 61.27,
+      "learning_rate": 0.001,
+      "loss": 49.9156,
+      "step": 3860
+    },
+    {
+      "epoch": 61.43,
+      "learning_rate": 0.001,
+      "loss": 49.7563,
+      "step": 3870
+    },
+    {
+      "epoch": 61.59,
+      "learning_rate": 0.001,
+      "loss": 49.8719,
+      "step": 3880
+    },
+    {
+      "epoch": 61.75,
+      "learning_rate": 0.001,
+      "loss": 50.1219,
+      "step": 3890
+    },
+    {
+      "epoch": 61.9,
+      "learning_rate": 0.001,
+      "loss": 50.2469,
+      "step": 3900
+    },
+    {
+      "epoch": 62.06,
+      "learning_rate": 0.001,
+      "loss": 50.0844,
+      "step": 3910
+    },
+    {
+      "epoch": 62.22,
+      "learning_rate": 0.001,
+      "loss": 50.2719,
+      "step": 3920
+    },
+    {
+      "epoch": 62.38,
+      "learning_rate": 0.001,
+      "loss": 50.0219,
+      "step": 3930
+    },
+    {
+      "epoch": 62.54,
+      "learning_rate": 0.001,
+      "loss": 50.3875,
+      "step": 3940
+    },
+    {
+      "epoch": 62.7,
+      "learning_rate": 0.001,
+      "loss": 50.3594,
+      "step": 3950
+    },
+    {
+      "epoch": 62.86,
+      "learning_rate": 0.001,
+      "loss": 50.4531,
+      "step": 3960
+    },
+    {
+      "epoch": 63.02,
+      "learning_rate": 0.001,
+      "loss": 50.6,
+      "step": 3970
+    },
+    {
+      "epoch": 63.17,
+      "learning_rate": 0.001,
+      "loss": 50.5063,
+      "step": 3980
+    },
+    {
+      "epoch": 63.33,
+      "learning_rate": 0.001,
+      "loss": 50.6125,
+      "step": 3990
+    },
+    {
+      "epoch": 63.49,
+      "learning_rate": 0.001,
+      "loss": 50.6313,
+      "step": 4000
+    },
+    {
+      "epoch": 63.49,
+      "eval_loss": 41.125,
+      "eval_runtime": 97.8561,
+      "eval_samples_per_second": 5.11,
+      "eval_steps_per_second": 0.644,
+      "step": 4000
+    }
+  ],
+  "max_steps": 20000,
+  "num_train_epochs": 318,
+  "total_flos": 4.897803240892662e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff58baa46bb8aee666b0902ee4924895d7de9d78d5cf9cfe739bc4abed3b0622
+size 4984