Add files using upload-large-folder tool

added_tokens.json

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "weights_infonce/checkpoint_llava-med-7b-pretrain_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,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32004
+}

generation_config.json

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

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c2c1e0286678886f115536f9480b1588037cfb7e8b741fba51071789e73bf5
+size 9878055609

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a333d339d23802cf0ff5395cdfb9c04c00270c973e0f92d1da6a4ccb261d6c7b
+size 9894801501

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b758dede49cfa8ca256cb8e9876ed77b2ab5262887e39538873e07404f7b4ab
+size 7264976856

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"
+  }
+}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "special_tokens_map_file": "/nobackup/haotian/.cache/huggingface/hub/models--lmsys--vicuna-7b-delta-v0/snapshots/6d2e645f62e734821be8c392c08c8b2098b35434/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9879518072289155,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1166,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.1079,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 1.0037,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9462,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8892,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.9079,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998476951563914e-05,
+      "loss": 0.8614,
+      "step": 7
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999390827019096e-05,
+      "loss": 0.8644,
+      "step": 8
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986295347545738e-05,
+      "loss": 0.8468,
+      "step": 9
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.8693,
+      "step": 10
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 0.839,
+      "step": 11
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 0.8395,
+      "step": 12
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9925461516413224e-05,
+      "loss": 0.8389,
+      "step": 13
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.83,
+      "step": 14
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.8273,
+      "step": 15
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.8489,
+      "step": 16
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9816271834476642e-05,
+      "loss": 0.7885,
+      "step": 17
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.8397,
+      "step": 18
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9743700647852356e-05,
+      "loss": 0.7727,
+      "step": 19
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9702957262759964e-05,
+      "loss": 0.7558,
+      "step": 20
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.7638,
+      "step": 21
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.8176,
+      "step": 22
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9563047559630356e-05,
+      "loss": 0.8318,
+      "step": 23
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.8329,
+      "step": 24
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.945518575599317e-05,
+      "loss": 0.8085,
+      "step": 25
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.7387,
+      "step": 26
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9335804264972018e-05,
+      "loss": 0.8065,
+      "step": 27
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9271838545667876e-05,
+      "loss": 0.789,
+      "step": 28
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9205048534524405e-05,
+      "loss": 0.8126,
+      "step": 29
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.7798,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 0.7797,
+      "step": 31
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8987940462991673e-05,
+      "loss": 0.7673,
+      "step": 32
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.8111,
+      "step": 33
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.7703,
+      "step": 34
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.874619707139396e-05,
+      "loss": 0.7802,
+      "step": 35
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.7463,
+      "step": 36
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8571673007021124e-05,
+      "loss": 0.7685,
+      "step": 37
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.7878,
+      "step": 38
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8386705679454243e-05,
+      "loss": 0.7804,
+      "step": 39
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 0.7496,
+      "step": 40
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.7291,
+      "step": 41
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.719,
+      "step": 42
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.798635510047293e-05,
+      "loss": 0.7418,
+      "step": 43
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 0.7863,
+      "step": 44
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.777145961456971e-05,
+      "loss": 0.7877,
+      "step": 45
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.7172,
+      "step": 46
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7547095802227723e-05,
+      "loss": 0.8055,
+      "step": 47
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 0.7943,
+      "step": 48
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7313537016191706e-05,
+      "loss": 0.7359,
+      "step": 49
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.7287,
+      "step": 50
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.7704,
+      "step": 51
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 0.7463,
+      "step": 52
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6819983600624986e-05,
+      "loss": 0.7505,
+      "step": 53
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.7528,
+      "step": 54
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6560590289905074e-05,
+      "loss": 0.7547,
+      "step": 55
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.6967,
+      "step": 56
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6293203910498375e-05,
+      "loss": 0.7067,
+      "step": 57
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.7201,
+      "step": 58
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6018150231520486e-05,
+      "loss": 0.7541,
+      "step": 59
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.7247,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.7124,
+      "step": 61
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.7564,
+      "step": 62
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5446390350150272e-05,
+      "loss": 0.5717,
+      "step": 63
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 0.5542,
+      "step": 64
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5150380749100545e-05,
+      "loss": 0.5303,
+      "step": 65
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4975,
+      "step": 66
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4848096202463373e-05,
+      "loss": 0.4998,
+      "step": 67
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 0.5106,
+      "step": 68
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.4744,
+      "step": 69
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.4874,
+      "step": 70
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.4865,
+      "step": 71
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.5166,
+      "step": 72
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3907311284892737e-05,
+      "loss": 0.5052,
+      "step": 73
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.477,
+      "step": 74
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3583679495453e-05,
+      "loss": 0.4927,
+      "step": 75
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.4834,
+      "step": 76
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3255681544571568e-05,
+      "loss": 0.4601,
+      "step": 77
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5014,
+      "step": 78
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2923717047227368e-05,
+      "loss": 0.4874,
+      "step": 79
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 0.4659,
+      "step": 80
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.4712,
+      "step": 81
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.4778,
+      "step": 82
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2249510543438652e-05,
+      "loss": 0.4893,
+      "step": 83
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.4945,
+      "step": 84
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.190808995376545e-05,
+      "loss": 0.4899,
+      "step": 85
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4667,
+      "step": 86
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.4696,
+      "step": 87
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.461,
+      "step": 88
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1218693434051475e-05,
+      "loss": 0.4387,
+      "step": 89
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.4862,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.4836,
+      "step": 91
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.475,
+      "step": 92
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0523359562429441e-05,
+      "loss": 0.5063,
+      "step": 93
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.4836,
+      "step": 94
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0174524064372837e-05,
+      "loss": 0.4892,
+      "step": 95
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1e-05,
+      "loss": 0.449,
+      "step": 96
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.825475935627165e-06,
+      "loss": 0.453,
+      "step": 97
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.4785,
+      "step": 98
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.476640437570562e-06,
+      "loss": 0.4835,
+      "step": 99
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 0.4778,
+      "step": 100
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.4749,
+      "step": 101
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.4832,
+      "step": 102
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.781306565948528e-06,
+      "loss": 0.5055,
+      "step": 103
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 0.4938,
+      "step": 104
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.4953,
+      "step": 105
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.452,
+      "step": 106
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.091910046234552e-06,
+      "loss": 0.4631,
+      "step": 107
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.452,
+      "step": 108
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.750489456561351e-06,
+      "loss": 0.5013,
+      "step": 109
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.4987,
+      "step": 110
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.4759,
+      "step": 111
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.4932,
+      "step": 112
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.076282952772634e-06,
+      "loss": 0.4847,
+      "step": 113
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.437,
+      "step": 114
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.744318455428436e-06,
+      "loss": 0.4861,
+      "step": 115
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.4599,
+      "step": 116
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.4163205045469975e-06,
+      "loss": 0.4861,
+      "step": 117
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.4565,
+      "step": 118
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.092688715107265e-06,
+      "loss": 0.4403,
+      "step": 119
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.4631,
+      "step": 120
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.4572,
+      "step": 121
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.4597,
+      "step": 122
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.4731,
+      "step": 123
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.4798,
+      "step": 124
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.151903797536631e-06,
+      "loss": 0.4207,
+      "step": 125
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3084,
+      "step": 126
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.849619250899458e-06,
+      "loss": 0.3211,
+      "step": 127
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 0.3206,
+      "step": 128
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.5536096498497295e-06,
+      "loss": 0.2936,
+      "step": 129
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.2846,
+      "step": 130
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.3028,
+      "step": 131
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.309,
+      "step": 132
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.981849768479516e-06,
+      "loss": 0.2914,
+      "step": 133
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.2821,
+      "step": 134
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.7067960895016277e-06,
+      "loss": 0.2961,
+      "step": 135
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.3004,
+      "step": 136
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.4394097100949286e-06,
+      "loss": 0.281,
+      "step": 137
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.2975,
+      "step": 138
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.1800163993750166e-06,
+      "loss": 0.2784,
+      "step": 139
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.2797,
+      "step": 140
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.2755,
+      "step": 141
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.3029,
+      "step": 142
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.6864629838082957e-06,
+      "loss": 0.2718,
+      "step": 143
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.2636,
+      "step": 144
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.45290419777228e-06,
+      "loss": 0.294,
+      "step": 145
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.2779,
+      "step": 146
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.2285403854302912e-06,
+      "loss": 0.3099,
+      "step": 147
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.2679,
+      "step": 148
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.013644899527074e-06,
+      "loss": 0.2911,
+      "step": 149
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.2653,
+      "step": 150
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.2732,
+      "step": 151
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.2805,
+      "step": 152
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6132943205457607e-06,
+      "loss": 0.2853,
+      "step": 153
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.3033,
+      "step": 154
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4283269929788779e-06,
+      "loss": 0.2935,
+      "step": 155
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.2713,
+      "step": 156
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2538029286060428e-06,
+      "loss": 0.2641,
+      "step": 157
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.2892,
+      "step": 158
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.2799,
+      "step": 159
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.2715,
+      "step": 160
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.297,
+      "step": 161
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.2717,
+      "step": 162
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.949514654755963e-07,
+      "loss": 0.2658,
+      "step": 163
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.2821,
+      "step": 164
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.641957350279838e-07,
+      "loss": 0.2912,
+      "step": 165
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.2728,
+      "step": 166
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.448142440068316e-07,
+      "loss": 0.2915,
+      "step": 167
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.3042,
+      "step": 168
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.3695244036964567e-07,
+      "loss": 0.2685,
+      "step": 169
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.3022,
+      "step": 170
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.2707,
+      "step": 171
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.3072,
+      "step": 172
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.5629935214764866e-07,
+      "loss": 0.2731,
+      "step": 173
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.2907,
+      "step": 174
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.8372816552336025e-07,
+      "loss": 0.2757,
+      "step": 175
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.2658,
+      "step": 176
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.2864,
+      "step": 177
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.2767,
+      "step": 178
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.453848358678018e-08,
+      "loss": 0.2858,
+      "step": 179
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.2683,
+      "step": 180
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.805301908254455e-08,
+      "loss": 0.2911,
+      "step": 181
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.2775,
+      "step": 182
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.370465245426167e-08,
+      "loss": 0.2777,
+      "step": 183
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 0.2737,
+      "step": 184
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.5230484360873043e-09,
+      "loss": 0.2778,
+      "step": 185
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0,
+      "loss": 0.2891,
+      "step": 186
+    },
+    {
+      "epoch": 2.99,
+      "step": 186,
+      "total_flos": 1.5592942139028275e+17,
+      "train_loss": 0.5238676683236194,
+      "train_runtime": 2078.491,
+      "train_samples_per_second": 11.491,
+      "train_steps_per_second": 0.089
+    }
+  ],
+  "max_steps": 186,
+  "num_train_epochs": 3,
+  "total_flos": 1.5592942139028275e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19df389a72f67a66cdaab20764b2db33d96098d30bb3b59e8d6f65d97f1bdd55
+size 4408