Add files using upload-large-folder tool

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<im_end>": 32003,
+  "<im_patch>": 32001,
+  "<im_start>": 32002,
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/netscratch/duynguyen/Research/Nghiem_LLaVA-Med/LVLM-Med/models/checkpoint_llava-med-7b-pretrain_version_1-5_newloss_1e0_multi_graph_test/stage1_2024-08-18-21:33:59",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_start_end": true,
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava",
+  "more_mlp": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32004
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412b0f234df2890685408d880cca16a5d7d031c8aae1ff1b3b09729dbe5d4cbc
+size 9878055609

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea03b553ea6aad7ddd290b7ed19f78499a8ab21fdd0d3cef5d8c042fd2f68bc
+size 9894801501

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12561fa9eeb030109cb5e983b857941ee69bcf535518560ae6785984bfd93ad
+size 7533447308

pytorch_model.bin.index.json

@@ -0,0 +1,340 @@
+{
+  "metadata": {
+    "total_size": 27306188800
+  },
+  "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.message_pass_node_features.conv1.lin_rel.bias": "pytorch_model-00003-of-00003.bin",
+    "model.message_pass_node_features.conv1.lin_rel.weight": "pytorch_model-00003-of-00003.bin",
+    "model.message_pass_node_features.conv1.lin_root.weight": "pytorch_model-00003-of-00003.bin",
+    "model.message_pass_node_features.conv2.lin_rel.bias": "pytorch_model-00003-of-00003.bin",
+    "model.message_pass_node_features.conv2.lin_rel.weight": "pytorch_model-00003-of-00003.bin",
+    "model.message_pass_node_features.conv2.lin_root.weight": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

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 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "special_tokens_map_file": "/nobackup/haotian/.cache/huggingface/hub/models--lmsys--vicuna-7b-delta-v0/snapshots/6d2e645f62e734821be8c392c08c8b2098b35434/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,2257 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9879518072289155,
+  "global_step": 372,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 5.0884,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 4.7854,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 5.0376,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0,
+      "loss": 4.7559,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 4.7119,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 4.7231,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 4.9405,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5e-06,
+      "loss": 4.2954,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.8764,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.494,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1e-05,
+      "loss": 2.2347,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 1.9839,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.9597,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.8386,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.8563,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.7444,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.7385,
+      "step": 17
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 1.8322,
+      "step": 18
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2e-05,
+      "loss": 1.5215,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9999619230641714e-05,
+      "loss": 1.6287,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9998476951563914e-05,
+      "loss": 1.5388,
+      "step": 21
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9996573249755573e-05,
+      "loss": 1.4677,
+      "step": 22
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.999390827019096e-05,
+      "loss": 1.4576,
+      "step": 23
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 1.3485,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9986295347545738e-05,
+      "loss": 1.4161,
+      "step": 25
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.998134798421867e-05,
+      "loss": 1.3036,
+      "step": 26
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 1.3949,
+      "step": 27
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 1.3105,
+      "step": 28
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 1.3662,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9953961983671792e-05,
+      "loss": 1.2802,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 1.3319,
+      "step": 31
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9935718556765878e-05,
+      "loss": 1.2182,
+      "step": 32
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9925461516413224e-05,
+      "loss": 1.2211,
+      "step": 33
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 1.1868,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 1.2214,
+      "step": 35
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.989015863361917e-05,
+      "loss": 1.2086,
+      "step": 36
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 1.2121,
+      "step": 37
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9862856015372315e-05,
+      "loss": 1.103,
+      "step": 38
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 1.1184,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.983254907563955e-05,
+      "loss": 1.1194,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9816271834476642e-05,
+      "loss": 1.0623,
+      "step": 41
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9799247046208297e-05,
+      "loss": 1.0094,
+      "step": 42
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 1.1196,
+      "step": 43
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 1.2043,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9743700647852356e-05,
+      "loss": 1.0698,
+      "step": 45
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 1.1203,
+      "step": 46
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9702957262759964e-05,
+      "loss": 1.0431,
+      "step": 47
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.968147640378108e-05,
+      "loss": 1.1588,
+      "step": 48
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 1.0619,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.963630453208623e-05,
+      "loss": 1.0128,
+      "step": 50
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.9996,
+      "step": 51
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.958819734868193e-05,
+      "loss": 1.0946,
+      "step": 52
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9563047559630356e-05,
+      "loss": 1.0351,
+      "step": 53
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 1.0649,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.959,
+      "step": 55
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9483236552061996e-05,
+      "loss": 0.9775,
+      "step": 56
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.945518575599317e-05,
+      "loss": 0.9489,
+      "step": 57
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9426414910921785e-05,
+      "loss": 1.0552,
+      "step": 58
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.0922,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9366721892483976e-05,
+      "loss": 0.9028,
+      "step": 60
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9335804264972018e-05,
+      "loss": 0.9918,
+      "step": 61
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9304175679820247e-05,
+      "loss": 0.9333,
+      "step": 62
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9271838545667876e-05,
+      "loss": 0.994,
+      "step": 63
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.9579,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9205048534524405e-05,
+      "loss": 1.0544,
+      "step": 65
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.917060074385124e-05,
+      "loss": 1.102,
+      "step": 66
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.964,
+      "step": 67
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.9099612708765432e-05,
+      "loss": 0.9713,
+      "step": 68
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 1.0004,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.902585284349861e-05,
+      "loss": 0.8788,
+      "step": 70
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8987940462991673e-05,
+      "loss": 0.8891,
+      "step": 71
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.894934361602025e-05,
+      "loss": 0.8483,
+      "step": 72
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.8736,
+      "step": 73
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 0.903,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.8843,
+      "step": 75
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8788171126619653e-05,
+      "loss": 0.9005,
+      "step": 76
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.874619707139396e-05,
+      "loss": 0.9247,
+      "step": 77
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8703556959398998e-05,
+      "loss": 0.891,
+      "step": 78
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.9221,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.861629160441526e-05,
+      "loss": 0.9188,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8571673007021124e-05,
+      "loss": 0.862,
+      "step": 81
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 0.8925,
+      "step": 82
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.8603,
+      "step": 83
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 0.8004,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8386705679454243e-05,
+      "loss": 0.8574,
+      "step": 85
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8338858220671683e-05,
+      "loss": 0.8504,
+      "step": 86
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 0.8505,
+      "step": 87
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.8241261886220155e-05,
+      "loss": 0.9328,
+      "step": 88
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.9068,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8141155183563195e-05,
+      "loss": 0.8666,
+      "step": 90
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.9206,
+      "step": 91
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8038568606172172e-05,
+      "loss": 0.7624,
+      "step": 92
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.798635510047293e-05,
+      "loss": 0.8813,
+      "step": 93
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 0.9439,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 0.918,
+      "step": 95
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.782608156852414e-05,
+      "loss": 0.9833,
+      "step": 96
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.777145961456971e-05,
+      "loss": 0.8755,
+      "step": 97
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7716245833877202e-05,
+      "loss": 0.8411,
+      "step": 98
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.8254,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.8472,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7547095802227723e-05,
+      "loss": 0.9188,
+      "step": 101
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7489557207890025e-05,
+      "loss": 0.8442,
+      "step": 102
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 0.8099,
+      "step": 103
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 0.8528,
+      "step": 104
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7313537016191706e-05,
+      "loss": 0.8462,
+      "step": 105
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7253743710122877e-05,
+      "loss": 0.7993,
+      "step": 106
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.7671,
+      "step": 107
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.713250449154182e-05,
+      "loss": 0.8988,
+      "step": 108
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.8949,
+      "step": 109
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.700909264299851e-05,
+      "loss": 0.8492,
+      "step": 110
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 0.8249,
+      "step": 111
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.688354575693754e-05,
+      "loss": 0.7691,
+      "step": 112
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6819983600624986e-05,
+      "loss": 0.8523,
+      "step": 113
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6755902076156606e-05,
+      "loss": 0.8356,
+      "step": 114
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.7547,
+      "step": 115
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6626200482157378e-05,
+      "loss": 0.7943,
+      "step": 116
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6560590289905074e-05,
+      "loss": 0.9412,
+      "step": 117
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.806,
+      "step": 118
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.8377,
+      "step": 119
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.636078220277764e-05,
+      "loss": 0.7885,
+      "step": 120
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6293203910498375e-05,
+      "loss": 0.7891,
+      "step": 121
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6225146366376198e-05,
+      "loss": 0.8052,
+      "step": 122
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.7566,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 0.9221,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6018150231520486e-05,
+      "loss": 0.7344,
+      "step": 125
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5948227867513416e-05,
+      "loss": 0.5818,
+      "step": 126
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.566,
+      "step": 127
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5807029557109398e-05,
+      "loss": 0.6114,
+      "step": 128
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.5593,
+      "step": 129
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.566406236924833e-05,
+      "loss": 0.6462,
+      "step": 130
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.6097,
+      "step": 131
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5519369853120584e-05,
+      "loss": 0.5266,
+      "step": 132
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5446390350150272e-05,
+      "loss": 0.5594,
+      "step": 133
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5372996083468242e-05,
+      "loss": 0.517,
+      "step": 134
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 0.5794,
+      "step": 135
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.5224985647159489e-05,
+      "loss": 0.5297,
+      "step": 136
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.5150380749100545e-05,
+      "loss": 0.5459,
+      "step": 137
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.5075383629607043e-05,
+      "loss": 0.538,
+      "step": 138
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5824,
+      "step": 139
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4924235601034673e-05,
+      "loss": 0.5505,
+      "step": 140
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4848096202463373e-05,
+      "loss": 0.5307,
+      "step": 141
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4771587602596085e-05,
+      "loss": 0.5135,
+      "step": 142
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 0.4806,
+      "step": 143
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4617486132350343e-05,
+      "loss": 0.608,
+      "step": 144
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.5978,
+      "step": 145
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4461978131098089e-05,
+      "loss": 0.5243,
+      "step": 146
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.5385,
+      "step": 147
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4305110968082953e-05,
+      "loss": 0.5338,
+      "step": 148
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.5232,
+      "step": 149
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.4146932426562391e-05,
+      "loss": 0.4947,
+      "step": 150
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.5123,
+      "step": 151
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3987490689252463e-05,
+      "loss": 0.515,
+      "step": 152
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3907311284892737e-05,
+      "loss": 0.5556,
+      "step": 153
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.5917,
+      "step": 154
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.6144,
+      "step": 155
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3665012267242974e-05,
+      "loss": 0.571,
+      "step": 156
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3583679495453e-05,
+      "loss": 0.4864,
+      "step": 157
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3502073812594677e-05,
+      "loss": 0.5451,
+      "step": 158
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.5456,
+      "step": 159
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.333806859233771e-05,
+      "loss": 0.4726,
+      "step": 160
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3255681544571568e-05,
+      "loss": 0.4925,
+      "step": 161
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3173046564050923e-05,
+      "loss": 0.5335,
+      "step": 162
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5302,
+      "step": 163
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.300705799504273e-05,
+      "loss": 0.5038,
+      "step": 164
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2923717047227368e-05,
+      "loss": 0.5917,
+      "step": 165
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.284015344703923e-05,
+      "loss": 0.5775,
+      "step": 166
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 0.5037,
+      "step": 167
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.267238376078257e-05,
+      "loss": 0.5588,
+      "step": 168
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.5512,
+      "step": 169
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2503800040544417e-05,
+      "loss": 0.5266,
+      "step": 170
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.5557,
+      "step": 171
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.2334453638559057e-05,
+      "loss": 0.5246,
+      "step": 172
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.2249510543438652e-05,
+      "loss": 0.628,
+      "step": 173
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 0.4878,
+      "step": 174
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.5337,
+      "step": 175
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1993679344171973e-05,
+      "loss": 0.5351,
+      "step": 176
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.190808995376545e-05,
+      "loss": 0.5197,
+      "step": 177
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1822355254921478e-05,
+      "loss": 0.4592,
+      "step": 178
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.501,
+      "step": 179
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1650476058606776e-05,
+      "loss": 0.485,
+      "step": 180
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.5917,
+      "step": 181
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1478094111296109e-05,
+      "loss": 0.5471,
+      "step": 182
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.5176,
+      "step": 183
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 0.4817,
+      "step": 184
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.1218693434051475e-05,
+      "loss": 0.5285,
+      "step": 185
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.113203213767907e-05,
+      "loss": 0.5612,
+      "step": 186
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.4928,
+      "step": 187
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0958457525202241e-05,
+      "loss": 0.5371,
+      "step": 188
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.526,
+      "step": 189
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.5643,
+      "step": 190
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.4597,
+      "step": 191
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0610485395348571e-05,
+      "loss": 0.5246,
+      "step": 192
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0523359562429441e-05,
+      "loss": 0.5116,
+      "step": 193
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.0436193873653362e-05,
+      "loss": 0.5411,
+      "step": 194
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.54,
+      "step": 195
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.0261769483078734e-05,
+      "loss": 0.5582,
+      "step": 196
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.0174524064372837e-05,
+      "loss": 0.5394,
+      "step": 197
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.008726535498374e-05,
+      "loss": 0.4873,
+      "step": 198
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1e-05,
+      "loss": 0.5107,
+      "step": 199
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.912734645016262e-06,
+      "loss": 0.4922,
+      "step": 200
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.825475935627165e-06,
+      "loss": 0.5211,
+      "step": 201
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.738230516921272e-06,
+      "loss": 0.5141,
+      "step": 202
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.5951,
+      "step": 203
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.563806126346643e-06,
+      "loss": 0.4997,
+      "step": 204
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.476640437570562e-06,
+      "loss": 0.5341,
+      "step": 205
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.38951460465143e-06,
+      "loss": 0.6075,
+      "step": 206
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 0.5166,
+      "step": 207
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 0.5022,
+      "step": 208
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.5255,
+      "step": 209
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 9.04154247479776e-06,
+      "loss": 0.5262,
+      "step": 210
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.5253,
+      "step": 211
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.867967862320935e-06,
+      "loss": 0.4554,
+      "step": 212
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.781306565948528e-06,
+      "loss": 0.4682,
+      "step": 213
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 0.5836,
+      "step": 214
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 0.5238,
+      "step": 215
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.521905888703894e-06,
+      "loss": 0.4846,
+      "step": 216
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.5358,
+      "step": 217
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.349523941393224e-06,
+      "loss": 0.6391,
+      "step": 218
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.5438,
+      "step": 219
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 8.177644745078525e-06,
+      "loss": 0.5327,
+      "step": 220
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.091910046234552e-06,
+      "loss": 0.5456,
+      "step": 221
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.00632065582803e-06,
+      "loss": 0.4808,
+      "step": 222
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.5277,
+      "step": 223
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 0.5768,
+      "step": 224
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.750489456561351e-06,
+      "loss": 0.5132,
+      "step": 225
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.66554636144095e-06,
+      "loss": 0.5936,
+      "step": 226
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.4926,
+      "step": 227
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.496199959455584e-06,
+      "loss": 0.4777,
+      "step": 228
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.4573,
+      "step": 229
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.327616239217432e-06,
+      "loss": 0.4502,
+      "step": 230
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.508,
+      "step": 231
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.159846552960774e-06,
+      "loss": 0.5499,
+      "step": 232
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.076282952772634e-06,
+      "loss": 0.4776,
+      "step": 233
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.992942004957271e-06,
+      "loss": 0.4889,
+      "step": 234
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.5219,
+      "step": 235
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.826953435949081e-06,
+      "loss": 0.527,
+      "step": 236
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.744318455428436e-06,
+      "loss": 0.4808,
+      "step": 237
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.661931407662292e-06,
+      "loss": 0.4402,
+      "step": 238
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.424,
+      "step": 239
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.497926187405326e-06,
+      "loss": 0.5171,
+      "step": 240
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.4163205045469975e-06,
+      "loss": 0.4871,
+      "step": 241
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.334987732757028e-06,
+      "loss": 0.4777,
+      "step": 242
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.503,
+      "step": 243
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.4576,
+      "step": 244
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.092688715107265e-06,
+      "loss": 0.4808,
+      "step": 245
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.0125093107475385e-06,
+      "loss": 0.4481,
+      "step": 246
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.4851,
+      "step": 247
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.853067573437612e-06,
+      "loss": 0.5207,
+      "step": 248
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.5261,
+      "step": 249
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.694889031917047e-06,
+      "loss": 0.3693,
+      "step": 250
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.2815,
+      "step": 251
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.5380218689019125e-06,
+      "loss": 0.3233,
+      "step": 252
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.2961,
+      "step": 253
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5.382513867649663e-06,
+      "loss": 0.2815,
+      "step": 254
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.2444,
+      "step": 255
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 5.228412397403916e-06,
+      "loss": 0.3003,
+      "step": 256
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 5.151903797536631e-06,
+      "loss": 0.2502,
+      "step": 257
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5.075764398965331e-06,
+      "loss": 0.2873,
+      "step": 258
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.2323,
+      "step": 259
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.924616370392962e-06,
+      "loss": 0.2485,
+      "step": 260
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.849619250899458e-06,
+      "loss": 0.247,
+      "step": 261
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.775014352840512e-06,
+      "loss": 0.2538,
+      "step": 262
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 0.225,
+      "step": 263
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.627003916531761e-06,
+      "loss": 0.261,
+      "step": 264
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.5536096498497295e-06,
+      "loss": 0.2631,
+      "step": 265
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.480630146879419e-06,
+      "loss": 0.2404,
+      "step": 266
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.239,
+      "step": 267
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 4.335937630751675e-06,
+      "loss": 0.2577,
+      "step": 268
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.2747,
+      "step": 269
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 4.192970442890602e-06,
+      "loss": 0.2522,
+      "step": 270
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.2853,
+      "step": 271
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 4.051772132486589e-06,
+      "loss": 0.267,
+      "step": 272
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.981849768479516e-06,
+      "loss": 0.2855,
+      "step": 273
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.912385709912794e-06,
+      "loss": 0.1936,
+      "step": 274
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.2863,
+      "step": 275
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.774853633623806e-06,
+      "loss": 0.2304,
+      "step": 276
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.7067960895016277e-06,
+      "loss": 0.2094,
+      "step": 277
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.6392177972223596e-06,
+      "loss": 0.2849,
+      "step": 278
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.2421,
+      "step": 279
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.3125,
+      "step": 280
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.4394097100949286e-06,
+      "loss": 0.2065,
+      "step": 281
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.3737995178426276e-06,
+      "loss": 0.254,
+      "step": 282
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.2489,
+      "step": 283
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.2440979238433977e-06,
+      "loss": 0.2486,
+      "step": 284
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.1800163993750166e-06,
+      "loss": 0.2091,
+      "step": 285
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 3.116454243062459e-06,
+      "loss": 0.2248,
+      "step": 286
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.2021,
+      "step": 287
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.990907357001491e-06,
+      "loss": 0.29,
+      "step": 288
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.2682,
+      "step": 289
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.867495508458186e-06,
+      "loss": 0.2308,
+      "step": 290
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.2608,
+      "step": 291
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.746256289877126e-06,
+      "loss": 0.3028,
+      "step": 292
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.6864629838082957e-06,
+      "loss": 0.2273,
+      "step": 293
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.6272266318987606e-06,
+      "loss": 0.2589,
+      "step": 294
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.255,
+      "step": 295
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.5104427921099783e-06,
+      "loss": 0.2102,
+      "step": 296
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.45290419777228e-06,
+      "loss": 0.2481,
+      "step": 297
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.2569,
+      "step": 298
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.207,
+      "step": 299
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.2837541661228024e-06,
+      "loss": 0.2541,
+      "step": 300
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.2285403854302912e-06,
+      "loss": 0.2386,
+      "step": 301
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.173918431475861e-06,
+      "loss": 0.271,
+      "step": 302
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.2199,
+      "step": 303
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.0664665970876496e-06,
+      "loss": 0.2631,
+      "step": 304
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.013644899527074e-06,
+      "loss": 0.2742,
+      "step": 305
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.961431393827827e-06,
+      "loss": 0.2861,
+      "step": 306
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.2211,
+      "step": 307
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.858844816436809e-06,
+      "loss": 0.2603,
+      "step": 308
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.2319,
+      "step": 309
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.7587381137798432e-06,
+      "loss": 0.233,
+      "step": 310
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.2385,
+      "step": 311
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.6611417793283192e-06,
+      "loss": 0.2186,
+      "step": 312
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.6132943205457607e-06,
+      "loss": 0.1897,
+      "step": 313
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.566085541871145e-06,
+      "loss": 0.2663,
+      "step": 314
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.2473,
+      "step": 315
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.4735983564590784e-06,
+      "loss": 0.2427,
+      "step": 316
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.4283269929788779e-06,
+      "loss": 0.1984,
+      "step": 317
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.3837083955847418e-06,
+      "loss": 0.2077,
+      "step": 318
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.1855,
+      "step": 319
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.2964430406010032e-06,
+      "loss": 0.2378,
+      "step": 320
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.2538029286060428e-06,
+      "loss": 0.2164,
+      "step": 321
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.2118288733803474e-06,
+      "loss": 0.3097,
+      "step": 322
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.2085,
+      "step": 323
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.129891668217783e-06,
+      "loss": 0.2366,
+      "step": 324
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.2338,
+      "step": 325
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.0506563839797501e-06,
+      "loss": 0.2611,
+      "step": 326
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.2233,
+      "step": 327
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.74147156501396e-07,
+      "loss": 0.2695,
+      "step": 328
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.264,
+      "step": 329
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 9.00387291234569e-07,
+      "loss": 0.2213,
+      "step": 330
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.2636,
+      "step": 331
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 8.293992561487596e-07,
+      "loss": 0.2662,
+      "step": 332
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.949514654755963e-07,
+      "loss": 0.2269,
+      "step": 333
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.2339,
+      "step": 334
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.2467,
+      "step": 335
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.958243201797554e-07,
+      "loss": 0.2689,
+      "step": 336
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.641957350279838e-07,
+      "loss": 0.2697,
+      "step": 337
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.332781075160244e-07,
+      "loss": 0.2022,
+      "step": 338
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.2426,
+      "step": 339
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 5.735850890782158e-07,
+      "loss": 0.2701,
+      "step": 340
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 5.448142440068316e-07,
+      "loss": 0.2341,
+      "step": 341
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 5.167634479380068e-07,
+      "loss": 0.2402,
+      "step": 342
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.2232,
+      "step": 343
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.628304925177318e-07,
+      "loss": 0.2802,
+      "step": 344
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.3695244036964567e-07,
+      "loss": 0.2328,
+      "step": 345
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 4.118026513180695e-07,
+      "loss": 0.25,
+      "step": 346
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.2588,
+      "step": 347
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.6369546791377054e-07,
+      "loss": 0.229,
+      "step": 348
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.2802,
+      "step": 349
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.185235962189237e-07,
+      "loss": 0.2033,
+      "step": 350
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.2928,
+      "step": 351
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.7630079602323447e-07,
+      "loss": 0.2249,
+      "step": 352
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.5629935214764866e-07,
+      "loss": 0.2332,
+      "step": 353
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.370399288006664e-07,
+      "loss": 0.296,
+      "step": 354
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.2597,
+      "step": 355
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.0075295379170413e-07,
+      "loss": 0.2734,
+      "step": 356
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.8372816552336025e-07,
+      "loss": 0.2157,
+      "step": 357
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.6745092436045495e-07,
+      "loss": 0.2567,
+      "step": 358
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.2158,
+      "step": 359
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.3714398462768563e-07,
+      "loss": 0.2566,
+      "step": 360
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.2933,
+      "step": 361
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.0984136638083176e-07,
+      "loss": 0.2528,
+      "step": 362
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.2569,
+      "step": 363
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 8.555138626189619e-08,
+      "loss": 0.2524,
+      "step": 364
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 7.453848358678018e-08,
+      "loss": 0.2734,
+      "step": 365
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 6.428144323412544e-08,
+      "loss": 0.2613,
+      "step": 366
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.199,
+      "step": 367
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 4.603801632821148e-08,
+      "loss": 0.2573,
+      "step": 368
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.805301908254455e-08,
+      "loss": 0.3048,
+      "step": 369
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.2107,
+      "step": 370
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.2641,
+      "step": 371
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.86520157813308e-08,
+      "loss": 0.2406,
+      "step": 372
+    },
+    {
+      "epoch": 2.99,
+      "step": 372,
+      "total_flos": 1.6840117540880384e+17,
+      "train_loss": 0.7044627577146535,
+      "train_runtime": 3722.2832,
+      "train_samples_per_second": 6.416,
+      "train_steps_per_second": 0.1
+    }
+  ],
+  "max_steps": 372,
+  "num_train_epochs": 3,
+  "total_flos": 1.6840117540880384e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f025cc9aff81efdc5120e43a8d8aeeaed2ae5762d50c6d8ef801a7b07d32499
+size 4600