Upload folder using huggingface_hub

llava-med-base/added_tokens.json

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

llava-med-base/checkpoint-505/added_tokens.json

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

llava-med-base/checkpoint-505/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/netscratch/duynguyen/Research/LLaVA-Med/weights_full/checkpoint_llava_med_instruct_60k_inline_mention_version_1-5",
+  "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",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "qformer_path": "/netscratch/trnguyen/instructBLIP_checkpoint/blip2_pretrained_vitL.pth",
+  "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
+}

llava-med-base/checkpoint-505/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": -1,
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false
+}

llava-med-base/checkpoint-505/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8078c90b680799160c89b5171a82808b0c32d5e744ddc663d6dbb6aecb588b7
+size 27037741527

llava-med-base/checkpoint-505/pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e48597c388f95e414f866b046dfc886a58d648445d40f15c4f191303194512
+size 9878059513

llava-med-base/checkpoint-505/pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c4f31f0b2d2b60c51b69ffaffbc821259dade3b2f64bbc963e23924e44387b
+size 9894805597

llava-med-base/checkpoint-505/pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a9f0468620494080ed9bf20ca874e6a5fdc99036effb2842c02ce0437fa114
+size 7264979864

llava-med-base/checkpoint-505/pytorch_model.bin.index.json

@@ -0,0 +1,334 @@
+{
+  "metadata": {
+    "total_size": 27037720576
+  },
+  "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.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"
+  }
+}

llava-med-base/checkpoint-505/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29dff6166f65daaf1452f2cc790f186b9aa83c96dcab7178950582ca83f4cb4
+size 14256

llava-med-base/checkpoint-505/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfaade05870101a00d40564a269d930ec05de733fb8ecde8131ce6ad74f224d
+size 14256

llava-med-base/checkpoint-505/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea9d0c7821b0f1ad1b2468bf7f3441427f47f6f86f63635b678916f8f6c5ced
+size 1064

llava-med-base/checkpoint-505/special_tokens_map.json

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

llava-med-base/checkpoint-505/tokenizer.model

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

llava-med-base/checkpoint-505/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
+  }
+}

llava-med-base/checkpoint-505/trainer_state.json

@@ -0,0 +1,3056 @@
+{
+  "best_metric": 47.146562905317765,
+  "best_model_checkpoint": "/netscratch/duynguyen/Research/Nghiem_LLaVA-Med/LVLM-Med/weights_finetuned/CoT-100_llava_med_on_CoT_dataset_epochs9_batchsize32_lr2e-5_prompt_mode_simple/checkpoint-505",
+  "epoch": 2.9881656804733727,
+  "global_step": 505,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 1.0828,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.078,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 0.678,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.3132,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 0.1264,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.0705,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 0.072,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.0581,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 0.0831,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.0746,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.0704,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.0832,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 0.0688,
+      "step": 13
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.0672,
+      "step": 14
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.0829,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.064,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 0.0704,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.0656,
+      "step": 18
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.0556,
+      "step": 19
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.057,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.0722,
+      "step": 21
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.0586,
+      "step": 22
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0577,
+      "step": 23
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.0587,
+      "step": 24
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.0498,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.0668,
+      "step": 26
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1739130434782611e-05,
+      "loss": 0.0578,
+      "step": 27
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.045,
+      "step": 28
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.2608695652173915e-05,
+      "loss": 0.0664,
+      "step": 29
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.0592,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.3478260869565218e-05,
+      "loss": 0.066,
+      "step": 31
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.0524,
+      "step": 32
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.4347826086956522e-05,
+      "loss": 0.0486,
+      "step": 33
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.0482,
+      "step": 34
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 0.05,
+      "step": 35
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.041,
+      "step": 36
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.6086956521739132e-05,
+      "loss": 0.0386,
+      "step": 37
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.0421,
+      "step": 38
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.6956521739130437e-05,
+      "loss": 0.0521,
+      "step": 39
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.0463,
+      "step": 40
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.782608695652174e-05,
+      "loss": 0.0441,
+      "step": 41
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.0401,
+      "step": 42
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8695652173913045e-05,
+      "loss": 0.0384,
+      "step": 43
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.0696,
+      "step": 44
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.0474,
+      "step": 45
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2e-05,
+      "loss": 0.0401,
+      "step": 46
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.999997731778071e-05,
+      "loss": 0.0375,
+      "step": 47
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9999909271225726e-05,
+      "loss": 0.0368,
+      "step": 48
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.999979586064374e-05,
+      "loss": 0.049,
+      "step": 49
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9999637086549236e-05,
+      "loss": 0.0478,
+      "step": 50
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9999432949662483e-05,
+      "loss": 0.0434,
+      "step": 51
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9999183450909533e-05,
+      "loss": 0.0498,
+      "step": 52
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.999888859142223e-05,
+      "loss": 0.0428,
+      "step": 53
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9998548372538175e-05,
+      "loss": 0.033,
+      "step": 54
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9998162795800766e-05,
+      "loss": 0.0337,
+      "step": 55
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9997731862959143e-05,
+      "loss": 0.0396,
+      "step": 56
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9997255575968207e-05,
+      "loss": 0.0183,
+      "step": 57
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9996733936988613e-05,
+      "loss": 0.0243,
+      "step": 58
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9996166948386745e-05,
+      "loss": 0.031,
+      "step": 59
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9995554612734713e-05,
+      "loss": 0.0241,
+      "step": 60
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.999489693281034e-05,
+      "loss": 0.0267,
+      "step": 61
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.999419391159716e-05,
+      "loss": 0.0319,
+      "step": 62
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9993445552284388e-05,
+      "loss": 0.027,
+      "step": 63
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9992651858266913e-05,
+      "loss": 0.0416,
+      "step": 64
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9991812833145287e-05,
+      "loss": 0.0368,
+      "step": 65
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9990928480725694e-05,
+      "loss": 0.047,
+      "step": 66
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.998999880501995e-05,
+      "loss": 0.0232,
+      "step": 67
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9989023810245484e-05,
+      "loss": 0.0311,
+      "step": 68
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9988003500825293e-05,
+      "loss": 0.0281,
+      "step": 69
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9986937881387968e-05,
+      "loss": 0.0185,
+      "step": 70
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.998582695676762e-05,
+      "loss": 0.0237,
+      "step": 71
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.99846707320039e-05,
+      "loss": 0.0245,
+      "step": 72
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.998346921234196e-05,
+      "loss": 0.0278,
+      "step": 73
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.998222240323242e-05,
+      "loss": 0.0345,
+      "step": 74
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9980930310331367e-05,
+      "loss": 0.0268,
+      "step": 75
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.99795929395003e-05,
+      "loss": 0.023,
+      "step": 76
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9978210296806134e-05,
+      "loss": 0.0458,
+      "step": 77
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9976782388521144e-05,
+      "loss": 0.0254,
+      "step": 78
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9975309221122958e-05,
+      "loss": 0.0289,
+      "step": 79
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9973790801294518e-05,
+      "loss": 0.0294,
+      "step": 80
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.997222713592405e-05,
+      "loss": 0.0245,
+      "step": 81
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9970618232105036e-05,
+      "loss": 0.0161,
+      "step": 82
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9968964097136173e-05,
+      "loss": 0.0206,
+      "step": 83
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9967264738521358e-05,
+      "loss": 0.0382,
+      "step": 84
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.996552016396963e-05,
+      "loss": 0.0234,
+      "step": 85
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9963730381395154e-05,
+      "loss": 0.0165,
+      "step": 86
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9961895398917182e-05,
+      "loss": 0.0286,
+      "step": 87
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9960015224860007e-05,
+      "loss": 0.0228,
+      "step": 88
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.995808986775293e-05,
+      "loss": 0.0138,
+      "step": 89
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9956119336330233e-05,
+      "loss": 0.0219,
+      "step": 90
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.9954103639531116e-05,
+      "loss": 0.0291,
+      "step": 91
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.995204278649967e-05,
+      "loss": 0.0232,
+      "step": 92
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.9949936786584846e-05,
+      "loss": 0.017,
+      "step": 93
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.9947785649340395e-05,
+      "loss": 0.0454,
+      "step": 94
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.9945589384524827e-05,
+      "loss": 0.0204,
+      "step": 95
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9943348002101374e-05,
+      "loss": 0.0178,
+      "step": 96
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.994106151223794e-05,
+      "loss": 0.0193,
+      "step": 97
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9938729925307064e-05,
+      "loss": 0.0257,
+      "step": 98
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9936353251885853e-05,
+      "loss": 0.023,
+      "step": 99
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9933931502755956e-05,
+      "loss": 0.0251,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9931464688903502e-05,
+      "loss": 0.0213,
+      "step": 101
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9928952821519048e-05,
+      "loss": 0.0202,
+      "step": 102
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9926395911997548e-05,
+      "loss": 0.0158,
+      "step": 103
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.9923793971938274e-05,
+      "loss": 0.0152,
+      "step": 104
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.0185,
+      "step": 105
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.9918455047624847e-05,
+      "loss": 0.0207,
+      "step": 106
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.991571808759043e-05,
+      "loss": 0.0145,
+      "step": 107
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.9912936145457586e-05,
+      "loss": 0.0162,
+      "step": 108
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.9910109233846443e-05,
+      "loss": 0.0138,
+      "step": 109
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.990723736558113e-05,
+      "loss": 0.0093,
+      "step": 110
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.990432055368971e-05,
+      "loss": 0.0098,
+      "step": 111
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.990135881140414e-05,
+      "loss": 0.0169,
+      "step": 112
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.9898352152160204e-05,
+      "loss": 0.0123,
+      "step": 113
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.989530058959743e-05,
+      "loss": 0.0117,
+      "step": 114
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.989220413755907e-05,
+      "loss": 0.0069,
+      "step": 115
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9889062810092002e-05,
+      "loss": 0.0125,
+      "step": 116
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9885876621446677e-05,
+      "loss": 0.0056,
+      "step": 117
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.988264558607707e-05,
+      "loss": 0.0298,
+      "step": 118
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.987936971864058e-05,
+      "loss": 0.01,
+      "step": 119
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.9876049033998007e-05,
+      "loss": 0.0153,
+      "step": 120
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.9872683547213446e-05,
+      "loss": 0.023,
+      "step": 121
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.986927327355424e-05,
+      "loss": 0.0147,
+      "step": 122
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.98658182284909e-05,
+      "loss": 0.0277,
+      "step": 123
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.986231842769705e-05,
+      "loss": 0.0211,
+      "step": 124
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.985877388704933e-05,
+      "loss": 0.0303,
+      "step": 125
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9855184622627362e-05,
+      "loss": 0.0115,
+      "step": 126
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9851550650713632e-05,
+      "loss": 0.0159,
+      "step": 127
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.984787198779346e-05,
+      "loss": 0.0121,
+      "step": 128
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.9844148650554883e-05,
+      "loss": 0.0117,
+      "step": 129
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.9840380655888622e-05,
+      "loss": 0.0162,
+      "step": 130
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.9836568020887963e-05,
+      "loss": 0.0151,
+      "step": 131
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.9832710762848716e-05,
+      "loss": 0.0157,
+      "step": 132
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9828808899269114e-05,
+      "loss": 0.0106,
+      "step": 133
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9824862447849745e-05,
+      "loss": 0.0216,
+      "step": 134
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9820871426493458e-05,
+      "loss": 0.0181,
+      "step": 135
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9816835853305306e-05,
+      "loss": 0.0113,
+      "step": 136
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9812755746592436e-05,
+      "loss": 0.0121,
+      "step": 137
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.980863112486402e-05,
+      "loss": 0.0137,
+      "step": 138
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9804462006831174e-05,
+      "loss": 0.0208,
+      "step": 139
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.9800248411406876e-05,
+      "loss": 0.0208,
+      "step": 140
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.9795990357705853e-05,
+      "loss": 0.0206,
+      "step": 141
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9791687865044537e-05,
+      "loss": 0.0088,
+      "step": 142
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.9787340952940935e-05,
+      "loss": 0.0183,
+      "step": 143
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.9782949641114576e-05,
+      "loss": 0.0067,
+      "step": 144
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.97785139494864e-05,
+      "loss": 0.0143,
+      "step": 145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.9774033898178668e-05,
+      "loss": 0.0103,
+      "step": 146
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.9769509507514887e-05,
+      "loss": 0.0166,
+      "step": 147
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9764940798019695e-05,
+      "loss": 0.0111,
+      "step": 148
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.976032779041879e-05,
+      "loss": 0.0134,
+      "step": 149
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.9755670505638824e-05,
+      "loss": 0.0108,
+      "step": 150
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.9750968964807305e-05,
+      "loss": 0.0137,
+      "step": 151
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.974622318925251e-05,
+      "loss": 0.016,
+      "step": 152
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9741433200503382e-05,
+      "loss": 0.0114,
+      "step": 153
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9736599020289438e-05,
+      "loss": 0.0123,
+      "step": 154
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.973172067054066e-05,
+      "loss": 0.0244,
+      "step": 155
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.9726798173387417e-05,
+      "loss": 0.0102,
+      "step": 156
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9721831551160334e-05,
+      "loss": 0.0139,
+      "step": 157
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9716820826390214e-05,
+      "loss": 0.0079,
+      "step": 158
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.971176602180793e-05,
+      "loss": 0.0163,
+      "step": 159
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.9706667160344325e-05,
+      "loss": 0.0098,
+      "step": 160
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.9701524265130088e-05,
+      "loss": 0.0088,
+      "step": 161
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9696337359495678e-05,
+      "loss": 0.0037,
+      "step": 162
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9691106466971204e-05,
+      "loss": 0.0084,
+      "step": 163
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.0104,
+      "step": 164
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9680512816370096e-05,
+      "loss": 0.009,
+      "step": 165
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9675150106350957e-05,
+      "loss": 0.0039,
+      "step": 166
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9669743505556544e-05,
+      "loss": 0.0079,
+      "step": 167
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9664293038513587e-05,
+      "loss": 0.0118,
+      "step": 168
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9658798729947827e-05,
+      "loss": 0.0121,
+      "step": 169
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.9653260604783887e-05,
+      "loss": 0.006,
+      "step": 170
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.9647678688145163e-05,
+      "loss": 0.0076,
+      "step": 171
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.96420530053537e-05,
+      "loss": 0.0139,
+      "step": 172
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9636383581930097e-05,
+      "loss": 0.009,
+      "step": 173
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.9630670443593373e-05,
+      "loss": 0.0069,
+      "step": 174
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9624913616260862e-05,
+      "loss": 0.0051,
+      "step": 175
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9619113126048086e-05,
+      "loss": 0.0111,
+      "step": 176
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.9613268999268644e-05,
+      "loss": 0.0106,
+      "step": 177
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.9607381262434086e-05,
+      "loss": 0.009,
+      "step": 178
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.9601449942253805e-05,
+      "loss": 0.009,
+      "step": 179
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.9595475065634896e-05,
+      "loss": 0.0274,
+      "step": 180
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.958945665968206e-05,
+      "loss": 0.0086,
+      "step": 181
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9583394751697447e-05,
+      "loss": 0.0163,
+      "step": 182
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.957728936918057e-05,
+      "loss": 0.0103,
+      "step": 183
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.957114053982815e-05,
+      "loss": 0.0054,
+      "step": 184
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.956494829153401e-05,
+      "loss": 0.0129,
+      "step": 185
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.9558712652388932e-05,
+      "loss": 0.0066,
+      "step": 186
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.9552433650680545e-05,
+      "loss": 0.0127,
+      "step": 187
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.954611131489319e-05,
+      "loss": 0.0083,
+      "step": 188
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.9539745673707785e-05,
+      "loss": 0.0117,
+      "step": 189
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.9533336756001707e-05,
+      "loss": 0.0048,
+      "step": 190
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.9526884590848646e-05,
+      "loss": 0.0114,
+      "step": 191
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9520389207518495e-05,
+      "loss": 0.0032,
+      "step": 192
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9513850635477188e-05,
+      "loss": 0.0054,
+      "step": 193
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.9507268904386596e-05,
+      "loss": 0.0086,
+      "step": 194
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.950064404410437e-05,
+      "loss": 0.0052,
+      "step": 195
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.9493976084683814e-05,
+      "loss": 0.0066,
+      "step": 196
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9487265056373756e-05,
+      "loss": 0.0053,
+      "step": 197
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9480510989618396e-05,
+      "loss": 0.0022,
+      "step": 198
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9473713915057183e-05,
+      "loss": 0.0071,
+      "step": 199
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.946687386352466e-05,
+      "loss": 0.004,
+      "step": 200
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.9459990866050337e-05,
+      "loss": 0.007,
+      "step": 201
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.945306495385855e-05,
+      "loss": 0.0085,
+      "step": 202
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.9446096158368303e-05,
+      "loss": 0.0041,
+      "step": 203
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.9439084511193153e-05,
+      "loss": 0.0038,
+      "step": 204
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.943203004414104e-05,
+      "loss": 0.0094,
+      "step": 205
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9424932789214158e-05,
+      "loss": 0.0037,
+      "step": 206
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9417792778608806e-05,
+      "loss": 0.0037,
+      "step": 207
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.9410610044715243e-05,
+      "loss": 0.0137,
+      "step": 208
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.9403384620117534e-05,
+      "loss": 0.0029,
+      "step": 209
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.9396116537593413e-05,
+      "loss": 0.0019,
+      "step": 210
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9388805830114132e-05,
+      "loss": 0.0065,
+      "step": 211
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9381452530844306e-05,
+      "loss": 0.0011,
+      "step": 212
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.9374056673141756e-05,
+      "loss": 0.0039,
+      "step": 213
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.9366618290557384e-05,
+      "loss": 0.0027,
+      "step": 214
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.9359137416834987e-05,
+      "loss": 0.0044,
+      "step": 215
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.9351614085911134e-05,
+      "loss": 0.0041,
+      "step": 216
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.9344048331914998e-05,
+      "loss": 0.0009,
+      "step": 217
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.9336440189168186e-05,
+      "loss": 0.0033,
+      "step": 218
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.9328789692184618e-05,
+      "loss": 0.0064,
+      "step": 219
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.932109687567034e-05,
+      "loss": 0.0032,
+      "step": 220
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.9313361774523387e-05,
+      "loss": 0.0023,
+      "step": 221
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.9305584423833606e-05,
+      "loss": 0.0258,
+      "step": 222
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.0021,
+      "step": 223
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.9289903115143133e-05,
+      "loss": 0.0069,
+      "step": 224
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.9281999228279814e-05,
+      "loss": 0.0047,
+      "step": 225
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.92740532341481e-05,
+      "loss": 0.0025,
+      "step": 226
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.9266065168794546e-05,
+      "loss": 0.0016,
+      "step": 227
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.9258035068456566e-05,
+      "loss": 0.0038,
+      "step": 228
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.9249962969562256e-05,
+      "loss": 0.0117,
+      "step": 229
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.9241848908730238e-05,
+      "loss": 0.003,
+      "step": 230
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.9233692922769497e-05,
+      "loss": 0.0125,
+      "step": 231
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.92254950486792e-05,
+      "loss": 0.0025,
+      "step": 232
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.9217255323648548e-05,
+      "loss": 0.0048,
+      "step": 233
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.920897378505659e-05,
+      "loss": 0.0095,
+      "step": 234
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.920065047047206e-05,
+      "loss": 0.0117,
+      "step": 235
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.9192285417653208e-05,
+      "loss": 0.0043,
+      "step": 236
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.9183878664547628e-05,
+      "loss": 0.0047,
+      "step": 237
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.917543024929208e-05,
+      "loss": 0.0025,
+      "step": 238
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.9166940210212324e-05,
+      "loss": 0.0104,
+      "step": 239
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.915840858582295e-05,
+      "loss": 0.0039,
+      "step": 240
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.9149835414827193e-05,
+      "loss": 0.0055,
+      "step": 241
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.914122073611676e-05,
+      "loss": 0.007,
+      "step": 242
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.913256458877166e-05,
+      "loss": 0.0032,
+      "step": 243
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.9123867012060016e-05,
+      "loss": 0.0057,
+      "step": 244
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.9115128045437896e-05,
+      "loss": 0.0068,
+      "step": 245
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.9106347728549134e-05,
+      "loss": 0.0023,
+      "step": 246
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.9097526101225146e-05,
+      "loss": 0.0025,
+      "step": 247
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.9088663203484742e-05,
+      "loss": 0.0031,
+      "step": 248
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.907975907553397e-05,
+      "loss": 0.0019,
+      "step": 249
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.90708137577659e-05,
+      "loss": 0.0009,
+      "step": 250
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.9061827290760466e-05,
+      "loss": 0.0013,
+      "step": 251
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.905279971528427e-05,
+      "loss": 0.0022,
+      "step": 252
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.90437310722904e-05,
+      "loss": 0.0045,
+      "step": 253
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.903462140291825e-05,
+      "loss": 0.0022,
+      "step": 254
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.9025470748493323e-05,
+      "loss": 0.0028,
+      "step": 255
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.9016279150527044e-05,
+      "loss": 0.0032,
+      "step": 256
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.9007046650716584e-05,
+      "loss": 0.0024,
+      "step": 257
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.8997773290944663e-05,
+      "loss": 0.0065,
+      "step": 258
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.8988459113279355e-05,
+      "loss": 0.0382,
+      "step": 259
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.8979104159973905e-05,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.896970847346653e-05,
+      "loss": 0.0208,
+      "step": 261
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.8960272096380236e-05,
+      "loss": 0.0117,
+      "step": 262
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.895079507152262e-05,
+      "loss": 0.0053,
+      "step": 263
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.8941277441885672e-05,
+      "loss": 0.0108,
+      "step": 264
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.8931719250645583e-05,
+      "loss": 0.005,
+      "step": 265
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.892212054116255e-05,
+      "loss": 0.0124,
+      "step": 266
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.8912481356980582e-05,
+      "loss": 0.0009,
+      "step": 267
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.89028017418273e-05,
+      "loss": 0.0039,
+      "step": 268
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.8893081739613728e-05,
+      "loss": 0.0075,
+      "step": 269
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.8883321394434116e-05,
+      "loss": 0.0089,
+      "step": 270
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.8873520750565716e-05,
+      "loss": 0.0016,
+      "step": 271
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8863679852468605e-05,
+      "loss": 0.0056,
+      "step": 272
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8853798744785466e-05,
+      "loss": 0.0064,
+      "step": 273
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8843877472341382e-05,
+      "loss": 0.0075,
+      "step": 274
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.883391608014365e-05,
+      "loss": 0.0029,
+      "step": 275
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.8823914613381568e-05,
+      "loss": 0.0026,
+      "step": 276
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.881387311742623e-05,
+      "loss": 0.0025,
+      "step": 277
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.8803791637830317e-05,
+      "loss": 0.001,
+      "step": 278
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.8793670220327897e-05,
+      "loss": 0.0029,
+      "step": 279
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.8783508910834212e-05,
+      "loss": 0.0018,
+      "step": 280
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.8773307755445468e-05,
+      "loss": 0.0012,
+      "step": 281
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.0092,
+      "step": 282
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.875278609227124e-05,
+      "loss": 0.0026,
+      "step": 283
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.874246567758112e-05,
+      "loss": 0.0048,
+      "step": 284
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.8732105603186273e-05,
+      "loss": 0.0029,
+      "step": 285
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.872170591608459e-05,
+      "loss": 0.003,
+      "step": 286
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.8711266663453666e-05,
+      "loss": 0.0019,
+      "step": 287
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.8700787892650584e-05,
+      "loss": 0.0096,
+      "step": 288
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.8690269651211705e-05,
+      "loss": 0.0007,
+      "step": 289
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.8679711986852432e-05,
+      "loss": 0.0047,
+      "step": 290
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.866911494746702e-05,
+      "loss": 0.0037,
+      "step": 291
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.8658478581128347e-05,
+      "loss": 0.0027,
+      "step": 292
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.864780293608769e-05,
+      "loss": 0.0028,
+      "step": 293
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.8637088060774514e-05,
+      "loss": 0.0032,
+      "step": 294
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8626334003796244e-05,
+      "loss": 0.0028,
+      "step": 295
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8615540813938063e-05,
+      "loss": 0.0033,
+      "step": 296
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8604708540162665e-05,
+      "loss": 0.0083,
+      "step": 297
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8593837231610056e-05,
+      "loss": 0.0006,
+      "step": 298
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.8582926937597316e-05,
+      "loss": 0.0017,
+      "step": 299
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.857197770761838e-05,
+      "loss": 0.0061,
+      "step": 300
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.856098959134381e-05,
+      "loss": 0.0037,
+      "step": 301
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.8549962638620592e-05,
+      "loss": 0.0014,
+      "step": 302
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.8538896899471868e-05,
+      "loss": 0.0017,
+      "step": 303
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.8527792424096743e-05,
+      "loss": 0.0094,
+      "step": 304
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.851664926287005e-05,
+      "loss": 0.0024,
+      "step": 305
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.850546746634211e-05,
+      "loss": 0.0034,
+      "step": 306
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.8494247085238516e-05,
+      "loss": 0.0024,
+      "step": 307
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.84829881704599e-05,
+      "loss": 0.0041,
+      "step": 308
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.84716907730817e-05,
+      "loss": 0.0079,
+      "step": 309
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.846035494435391e-05,
+      "loss": 0.0026,
+      "step": 310
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.84489807357009e-05,
+      "loss": 0.0013,
+      "step": 311
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.8437568198721113e-05,
+      "loss": 0.0005,
+      "step": 312
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.842611738518689e-05,
+      "loss": 0.0023,
+      "step": 313
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.8414628347044203e-05,
+      "loss": 0.0013,
+      "step": 314
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.840310113641243e-05,
+      "loss": 0.0061,
+      "step": 315
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.839153580558411e-05,
+      "loss": 0.0001,
+      "step": 316
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8379932407024723e-05,
+      "loss": 0.0038,
+      "step": 317
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.836829099337243e-05,
+      "loss": 0.0016,
+      "step": 318
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8356611617437853e-05,
+      "loss": 0.0027,
+      "step": 319
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8344894332203823e-05,
+      "loss": 0.0011,
+      "step": 320
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.833313919082515e-05,
+      "loss": 0.0019,
+      "step": 321
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8321346246628374e-05,
+      "loss": 0.0064,
+      "step": 322
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8309515553111518e-05,
+      "loss": 0.0023,
+      "step": 323
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8297647163943865e-05,
+      "loss": 0.0003,
+      "step": 324
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8285741132965693e-05,
+      "loss": 0.0006,
+      "step": 325
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.8273797514188043e-05,
+      "loss": 0.0026,
+      "step": 326
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.8261816361792474e-05,
+      "loss": 0.0017,
+      "step": 327
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.8249797730130804e-05,
+      "loss": 0.0022,
+      "step": 328
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.8237741673724892e-05,
+      "loss": 0.0008,
+      "step": 329
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.822564824726635e-05,
+      "loss": 0.0055,
+      "step": 330
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.821351750561634e-05,
+      "loss": 0.0052,
+      "step": 331
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.8201349503805275e-05,
+      "loss": 0.0101,
+      "step": 332
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.8189144297032627e-05,
+      "loss": 0.0022,
+      "step": 333
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.8176901940666624e-05,
+      "loss": 0.0149,
+      "step": 334
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.8164622490244027e-05,
+      "loss": 0.0065,
+      "step": 335
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.8152306001469875e-05,
+      "loss": 0.0037,
+      "step": 336
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.8139952530217232e-05,
+      "loss": 0.0033,
+      "step": 337
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8127562132526922e-05,
+      "loss": 0.0032,
+      "step": 338
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.811513486460729e-05,
+      "loss": 0.0086,
+      "step": 339
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.8102670782833938e-05,
+      "loss": 0.0081,
+      "step": 340
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.0011,
+      "step": 341
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.8077632404063256e-05,
+      "loss": 0.0004,
+      "step": 342
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.8065058220651127e-05,
+      "loss": 0.0105,
+      "step": 343
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.8052447450555157e-05,
+      "loss": 0.0014,
+      "step": 344
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.803980015098341e-05,
+      "loss": 0.004,
+      "step": 345
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.8027116379309637e-05,
+      "loss": 0.0003,
+      "step": 346
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.8014396193073067e-05,
+      "loss": 0.0012,
+      "step": 347
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.8001639649978102e-05,
+      "loss": 0.0011,
+      "step": 348
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.798884680789409e-05,
+      "loss": 0.0049,
+      "step": 349
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.797601772485504e-05,
+      "loss": 0.0054,
+      "step": 350
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.796315245905936e-05,
+      "loss": 0.0016,
+      "step": 351
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.795025106886962e-05,
+      "loss": 0.0011,
+      "step": 352
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.7937313612812234e-05,
+      "loss": 0.0007,
+      "step": 353
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.7924340149577263e-05,
+      "loss": 0.0012,
+      "step": 354
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.7911330738018084e-05,
+      "loss": 0.0004,
+      "step": 355
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.7898285437151163e-05,
+      "loss": 0.0073,
+      "step": 356
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.7885204306155777e-05,
+      "loss": 0.0012,
+      "step": 357
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.787208740437374e-05,
+      "loss": 0.0006,
+      "step": 358
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.7858934791309146e-05,
+      "loss": 0.0006,
+      "step": 359
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.784574652662808e-05,
+      "loss": 0.0016,
+      "step": 360
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.783252267015837e-05,
+      "loss": 0.0016,
+      "step": 361
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.781926328188929e-05,
+      "loss": 0.0051,
+      "step": 362
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.780596842197132e-05,
+      "loss": 0.0006,
+      "step": 363
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.779263815071584e-05,
+      "loss": 0.0073,
+      "step": 364
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.7779272528594876e-05,
+      "loss": 0.0018,
+      "step": 365
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.776587161624083e-05,
+      "loss": 0.0002,
+      "step": 366
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.7752435474446178e-05,
+      "loss": 0.0003,
+      "step": 367
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.773896416416323e-05,
+      "loss": 0.0017,
+      "step": 368
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.772545774650383e-05,
+      "loss": 0.0003,
+      "step": 369
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.7711916282739075e-05,
+      "loss": 0.0001,
+      "step": 370
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.7698339834299064e-05,
+      "loss": 0.0004,
+      "step": 371
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.768472846277259e-05,
+      "loss": 0.0023,
+      "step": 372
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.767108222990687e-05,
+      "loss": 0.001,
+      "step": 373
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.765740119760729e-05,
+      "loss": 0.0022,
+      "step": 374
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.7643685427937065e-05,
+      "loss": 0.0039,
+      "step": 375
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.7629934983117025e-05,
+      "loss": 0.0017,
+      "step": 376
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.761614992552529e-05,
+      "loss": 0.0036,
+      "step": 377
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.7602330317696998e-05,
+      "loss": 0.0004,
+      "step": 378
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.758847622232402e-05,
+      "loss": 0.0001,
+      "step": 379
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.7574587702254692e-05,
+      "loss": 0.001,
+      "step": 380
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.7560664820493502e-05,
+      "loss": 0.0024,
+      "step": 381
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.7546707640200815e-05,
+      "loss": 0.0003,
+      "step": 382
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.7532716224692602e-05,
+      "loss": 0.0001,
+      "step": 383
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.7518690637440135e-05,
+      "loss": 0.0003,
+      "step": 384
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.7504630942069695e-05,
+      "loss": 0.0043,
+      "step": 385
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.7490537202362313e-05,
+      "loss": 0.001,
+      "step": 386
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.7476409482253433e-05,
+      "loss": 0.0031,
+      "step": 387
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.746224784583268e-05,
+      "loss": 0.0003,
+      "step": 388
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.7448052357343514e-05,
+      "loss": 0.0002,
+      "step": 389
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.7433823081182967e-05,
+      "loss": 0.006,
+      "step": 390
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.741956008190136e-05,
+      "loss": 0.001,
+      "step": 391
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.7405263424201987e-05,
+      "loss": 0.0002,
+      "step": 392
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.739093317294083e-05,
+      "loss": 0.0007,
+      "step": 393
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.7376569393126274e-05,
+      "loss": 0.0015,
+      "step": 394
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.736217214991879e-05,
+      "loss": 0.0003,
+      "step": 395
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.7347741508630673e-05,
+      "loss": 0.0013,
+      "step": 396
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.7333277534725716e-05,
+      "loss": 0.0012,
+      "step": 397
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.731878029381892e-05,
+      "loss": 0.0007,
+      "step": 398
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.730424985167621e-05,
+      "loss": 0.0004,
+      "step": 399
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.0036,
+      "step": 400
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.7275089627499493e-05,
+      "loss": 0.0001,
+      "step": 401
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.7260459977749206e-05,
+      "loss": 0.0,
+      "step": 402
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.7245797391329847e-05,
+      "loss": 0.0007,
+      "step": 403
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.7231101934757406e-05,
+      "loss": 0.0054,
+      "step": 404
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.7216373674697002e-05,
+      "loss": 0.0013,
+      "step": 405
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.720161267796256e-05,
+      "loss": 0.0021,
+      "step": 406
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.7186819011516512e-05,
+      "loss": 0.0015,
+      "step": 407
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.71719927424695e-05,
+      "loss": 0.001,
+      "step": 408
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.7157133938080054e-05,
+      "loss": 0.009,
+      "step": 409
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7142242665754308e-05,
+      "loss": 0.0061,
+      "step": 410
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7127318993045686e-05,
+      "loss": 0.0018,
+      "step": 411
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7112362987654587e-05,
+      "loss": 0.002,
+      "step": 412
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7097374717428096e-05,
+      "loss": 0.0064,
+      "step": 413
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.708235425035965e-05,
+      "loss": 0.004,
+      "step": 414
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.7067301654588764e-05,
+      "loss": 0.0025,
+      "step": 415
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.705221699840069e-05,
+      "loss": 0.0005,
+      "step": 416
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.7037100350226118e-05,
+      "loss": 0.0005,
+      "step": 417
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.7021951778640885e-05,
+      "loss": 0.0064,
+      "step": 418
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.7006771352365627e-05,
+      "loss": 0.0002,
+      "step": 419
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.6991559140265498e-05,
+      "loss": 0.0027,
+      "step": 420
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.6976315211349848e-05,
+      "loss": 0.002,
+      "step": 421
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.69610396347719e-05,
+      "loss": 0.0012,
+      "step": 422
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.694573247982845e-05,
+      "loss": 0.002,
+      "step": 423
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.693039381595955e-05,
+      "loss": 0.009,
+      "step": 424
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.6915023712748185e-05,
+      "loss": 0.0002,
+      "step": 425
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.6899622239919965e-05,
+      "loss": 0.0059,
+      "step": 426
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.6884189467342805e-05,
+      "loss": 0.0124,
+      "step": 427
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.6868725465026616e-05,
+      "loss": 0.0001,
+      "step": 428
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.6853230303122977e-05,
+      "loss": 0.0043,
+      "step": 429
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.6837704051924814e-05,
+      "loss": 0.0079,
+      "step": 430
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.6822146781866097e-05,
+      "loss": 0.0014,
+      "step": 431
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.680655856352151e-05,
+      "loss": 0.002,
+      "step": 432
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.679093946760613e-05,
+      "loss": 0.0014,
+      "step": 433
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.6775289564975104e-05,
+      "loss": 0.004,
+      "step": 434
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.6759608926623344e-05,
+      "loss": 0.0008,
+      "step": 435
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.6743897623685178e-05,
+      "loss": 0.0043,
+      "step": 436
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.6728155727434057e-05,
+      "loss": 0.005,
+      "step": 437
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.6712383309282208e-05,
+      "loss": 0.004,
+      "step": 438
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.6696580440780314e-05,
+      "loss": 0.0101,
+      "step": 439
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.6680747193617206e-05,
+      "loss": 0.002,
+      "step": 440
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.666488363961952e-05,
+      "loss": 0.0026,
+      "step": 441
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.664898985075138e-05,
+      "loss": 0.0047,
+      "step": 442
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.6633065899114065e-05,
+      "loss": 0.0048,
+      "step": 443
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.6617111856945686e-05,
+      "loss": 0.0012,
+      "step": 444
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.6601127796620863e-05,
+      "loss": 0.0017,
+      "step": 445
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.658511379065039e-05,
+      "loss": 0.0009,
+      "step": 446
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.6569069911680896e-05,
+      "loss": 0.0002,
+      "step": 447
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 1.655299623249455e-05,
+      "loss": 0.0005,
+      "step": 448
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 1.6536892826008687e-05,
+      "loss": 0.0004,
+      "step": 449
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 1.652075976527551e-05,
+      "loss": 0.0022,
+      "step": 450
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.6504597123481737e-05,
+      "loss": 0.0013,
+      "step": 451
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.6488404973948292e-05,
+      "loss": 0.0036,
+      "step": 452
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.6472183390129953e-05,
+      "loss": 0.0032,
+      "step": 453
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.645593244561502e-05,
+      "loss": 0.0014,
+      "step": 454
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.6439652214124992e-05,
+      "loss": 0.0007,
+      "step": 455
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.6423342769514227e-05,
+      "loss": 0.0008,
+      "step": 456
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.64070041857696e-05,
+      "loss": 0.0006,
+      "step": 457
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.6390636537010188e-05,
+      "loss": 0.0072,
+      "step": 458
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.0009,
+      "step": 459
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.6357814341582173e-05,
+      "loss": 0.002,
+      "step": 460
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.6341359943809626e-05,
+      "loss": 0.0067,
+      "step": 461
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.6324876778813704e-05,
+      "loss": 0.0032,
+      "step": 462
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.6308364921369365e-05,
+      "loss": 0.0069,
+      "step": 463
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.629182444638172e-05,
+      "loss": 0.0001,
+      "step": 464
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.62752554288857e-05,
+      "loss": 0.0007,
+      "step": 465
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.625865794404573e-05,
+      "loss": 0.0008,
+      "step": 466
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.624203206715537e-05,
+      "loss": 0.0005,
+      "step": 467
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.622537787363697e-05,
+      "loss": 0.0005,
+      "step": 468
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.620869543904135e-05,
+      "loss": 0.001,
+      "step": 469
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.6191984839047435e-05,
+      "loss": 0.0025,
+      "step": 470
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.617524614946192e-05,
+      "loss": 0.0016,
+      "step": 471
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.615847944621894e-05,
+      "loss": 0.0041,
+      "step": 472
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.6141684805379693e-05,
+      "loss": 0.0003,
+      "step": 473
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.612486230313213e-05,
+      "loss": 0.0033,
+      "step": 474
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.6108012015790587e-05,
+      "loss": 0.0006,
+      "step": 475
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.6091134019795447e-05,
+      "loss": 0.0035,
+      "step": 476
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.6074228391712788e-05,
+      "loss": 0.008,
+      "step": 477
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.605729520823405e-05,
+      "loss": 0.0015,
+      "step": 478
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.6040334546175663e-05,
+      "loss": 0.0015,
+      "step": 479
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.6023346482478714e-05,
+      "loss": 0.0003,
+      "step": 480
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.600633109420861e-05,
+      "loss": 0.0026,
+      "step": 481
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.5989288458554703e-05,
+      "loss": 0.0116,
+      "step": 482
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.5972218652829948e-05,
+      "loss": 0.0022,
+      "step": 483
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.5955121754470562e-05,
+      "loss": 0.0035,
+      "step": 484
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.5937997841035667e-05,
+      "loss": 0.0019,
+      "step": 485
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.5920846990206934e-05,
+      "loss": 0.0035,
+      "step": 486
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.5903669279788234e-05,
+      "loss": 0.0006,
+      "step": 487
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.5886464787705285e-05,
+      "loss": 0.0003,
+      "step": 488
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.58692335920053e-05,
+      "loss": 0.0022,
+      "step": 489
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.585197577085663e-05,
+      "loss": 0.0004,
+      "step": 490
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.5834691402548415e-05,
+      "loss": 0.0002,
+      "step": 491
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.581738056549022e-05,
+      "loss": 0.0002,
+      "step": 492
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.5800043338211683e-05,
+      "loss": 0.0005,
+      "step": 493
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.578267979936217e-05,
+      "loss": 0.0015,
+      "step": 494
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.576529002771039e-05,
+      "loss": 0.0004,
+      "step": 495
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.5747874102144073e-05,
+      "loss": 0.0005,
+      "step": 496
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.573043210166958e-05,
+      "loss": 0.007,
+      "step": 497
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.5712964105411575e-05,
+      "loss": 0.0006,
+      "step": 498
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.569547019261264e-05,
+      "loss": 0.0004,
+      "step": 499
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.5677950442632924e-05,
+      "loss": 0.0006,
+      "step": 500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.5660404934949798e-05,
+      "loss": 0.0016,
+      "step": 501
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.5642833749157466e-05,
+      "loss": 0.0001,
+      "step": 502
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.5625236964966624e-05,
+      "loss": 0.0072,
+      "step": 503
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.56076146622041e-05,
+      "loss": 0.0051,
+      "step": 504
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.5589966920812483e-05,
+      "loss": 0.0001,
+      "step": 505
+    },
+    {
+      "epoch": 2.99,
+      "eval_test_accuracy": 47.146562905317765,
+      "eval_test_average": 47.146562905317765,
+      "eval_test_loss": 1.5961765050888062,
+      "eval_test_runtime": 1237.3205,
+      "eval_test_samples_per_second": 1.246,
+      "eval_test_steps_per_second": 0.011,
+      "step": 505
+    }
+  ],
+  "max_steps": 1521,
+  "num_train_epochs": 9,
+  "total_flos": 2.3068511638336307e+17,
+  "trial_name": null,
+  "trial_params": null
+}

llava-med-base/checkpoint-505/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e0311561d3de005c888bba84de385c76b1da71fbee3f24682133187b0ebead
+size 4664

llava-med-base/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/netscratch/duynguyen/Research/LLaVA-Med/weights_full/checkpoint_llava_med_instruct_60k_inline_mention_version_1-5",
+  "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",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "qformer_path": "/netscratch/trnguyen/instructBLIP_checkpoint/blip2_pretrained_vitL.pth",
+  "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
+}

llava-med-base/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": -1,
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false
+}

llava-med-base/pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0981232f683fecd5f512f7ebf9636139ebc3c6c3c20b9cf9b41428cda6b9bf82
+size 9878055609

llava-med-base/pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d462157632368e3ee3419bf15e782cabcc1db76c081560515bc8824c6a87ba
+size 9894801501

llava-med-base/pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341cd1a1de286284b136c253b425f8ceb42f38ea5d81f5f1f3ee03b5c33af18c
+size 7264976856

llava-med-base/pytorch_model.bin.index.json

@@ -0,0 +1,334 @@
+{
+  "metadata": {
+    "total_size": 27037720576
+  },
+  "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.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"
+  }
+}

llava-med-base/special_tokens_map.json

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

llava-med-base/tokenizer.model

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

llava-med-base/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
+  }
+}

llava-med-base/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e0311561d3de005c888bba84de385c76b1da71fbee3f24682133187b0ebead
+size 4664