update

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<im_end>": 32002,
+  "<im_patch>": 32000,
+  "<im_start>": 32001
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "shikra-Genixer-350K-7b",
+  "architectures": [
+    "ShikraLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mm_hidden_size": 1024,
+  "mm_use_im_start_end": true,
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "checkpoints/clip-vit-large-patch14",
+  "model_type": "shikra",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vocab_size": 32003
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7c9f9c5310a390d0fe41e8393915a4ac4124b087aad15ea641fa9443a738fb
+size 6742658331

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52628497161200a9990f565f1b6ec7fa42ba4e0be05c8689a893c41a8fc14bed
+size 9878037202

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272088bf32c869f39c9cb99e7e9cf9310055fe3e646c6c6b4296077ca26860f1
+size 9894799542

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e8649bb9495cf69ddba1bc1de80ce865a1ff33067f7a804d1478560fb7ea54
+size 7197833077

pytorch_model.bin.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 26970558464
+  },
+  "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.bias": "pytorch_model-00003-of-00003.bin",
+    "model.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415997ccc00520c1868cdd2dc608af04bc0e57a2b0d75ab0749bf4c087adc7f9
+size 627

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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": "/codes/llm_codes/LLaVA/checkpoints/vicuna-7b-v1.3/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 +1,616 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8934554389099844,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.941176470588235e-07,
+      "loss": 2.6188,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.88235294117647e-07,
+      "loss": 2.4129,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.823529411764705e-07,
+      "loss": 2.1366,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.999245478090202e-07,
+      "loss": 1.8696,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.994635335507661e-07,
+      "loss": 1.6629,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.985838089271184e-07,
+      "loss": 1.5366,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.972861114289922e-07,
+      "loss": 1.4687,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.955715289424037e-07,
+      "loss": 1.398,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.934414988364722e-07,
+      "loss": 1.3378,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.908978067584452e-07,
+      "loss": 1.2982,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.879425851367544e-07,
+      "loss": 1.2802,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.845783113933575e-07,
+      "loss": 1.2718,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.808078058668652e-07,
+      "loss": 1.231,
+      "step": 130
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.766342294481949e-07,
+      "loss": 1.2435,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.720610809307313e-07,
+      "loss": 1.2031,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.670921940772186e-07,
+      "loss": 1.2031,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.617317344058378e-07,
+      "loss": 1.1938,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.559841956981707e-07,
+      "loss": 1.2037,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.498543962319708e-07,
+      "loss": 1.182,
+      "step": 190
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.433474747419042e-07,
+      "loss": 1.1655,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.364688861116443e-07,
+      "loss": 1.147,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.29224396800933e-07,
+      "loss": 1.147,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.216200800114411e-07,
+      "loss": 1.1768,
+      "step": 230
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.136623105954802e-07,
+      "loss": 1.1543,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.053577597118358e-07,
+      "loss": 1.1404,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.967133892331999e-07,
+      "loss": 1.1323,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.877364459098931e-07,
+      "loss": 1.136,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.784344552947665e-07,
+      "loss": 1.1469,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.688152154343793e-07,
+      "loss": 1.1319,
+      "step": 290
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.588867903317394e-07,
+      "loss": 1.1288,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.486575031860859e-07,
+      "loss": 1.1225,
+      "step": 310
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.381359294153838e-07,
+      "loss": 1.1105,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.27330889467378e-07,
+      "loss": 1.1283,
+      "step": 330
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.16251441425233e-07,
+      "loss": 1.107,
+      "step": 340
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.049068734139603e-07,
+      "loss": 1.1044,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.933066958139942e-07,
+      "loss": 1.1316,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.814606332884488e-07,
+      "loss": 1.0889,
+      "step": 370
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.69378616630736e-07,
+      "loss": 1.0929,
+      "step": 380
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.570707744393813e-07,
+      "loss": 1.1371,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.445474246270149e-07,
+      "loss": 1.1332,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.318190657706574e-07,
+      "loss": 1.0957,
+      "step": 410
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.188963683105504e-07,
+      "loss": 1.0889,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.057901656049109e-07,
+      "loss": 1.1067,
+      "step": 430
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.925114448481088e-07,
+      "loss": 1.1219,
+      "step": 440
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.790713378598802e-07,
+      "loss": 1.1267,
+      "step": 450
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.65481111753297e-07,
+      "loss": 1.087,
+      "step": 460
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.517521594893197e-07,
+      "loss": 1.0872,
+      "step": 470
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.378959903258474e-07,
+      "loss": 1.0818,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.239242201692752e-07,
+      "loss": 1.0856,
+      "step": 490
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.098485618366447e-07,
+      "loss": 1.0804,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.956808152365532e-07,
+      "loss": 1.0859,
+      "step": 510
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.814328574770522e-07,
+      "loss": 1.088,
+      "step": 520
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.671166329088277e-07,
+      "loss": 1.0791,
+      "step": 530
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.527441431120099e-07,
+      "loss": 1.0885,
+      "step": 540
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.383274368350061e-07,
+      "loss": 1.0808,
+      "step": 550
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.238785998937924e-07,
+      "loss": 1.0586,
+      "step": 560
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.094097450401282e-07,
+      "loss": 1.0984,
+      "step": 570
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.949330018071946e-07,
+      "loss": 1.0646,
+      "step": 580
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.804605063411592e-07,
+      "loss": 1.0581,
+      "step": 590
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.660043912272015e-07,
+      "loss": 1.0679,
+      "step": 600
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.515767753185208e-07,
+      "loss": 1.1003,
+      "step": 610
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.3718975357685725e-07,
+      "loss": 1.0751,
+      "step": 620
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.228553869330412e-07,
+      "loss": 1.0733,
+      "step": 630
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.0858569217607086e-07,
+      "loss": 1.0505,
+      "step": 640
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.943926318791963e-07,
+      "loss": 1.0813,
+      "step": 650
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.8028810437145214e-07,
+      "loss": 1.0671,
+      "step": 660
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.66283933763048e-07,
+      "loss": 1.0648,
+      "step": 670
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.523918600329788e-07,
+      "loss": 1.073,
+      "step": 680
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.386235291871625e-07,
+      "loss": 1.0672,
+      "step": 690
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.249904834953584e-07,
+      "loss": 1.0666,
+      "step": 700
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.115041518150502e-07,
+      "loss": 1.0644,
+      "step": 710
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.981758400104028e-07,
+      "loss": 1.0637,
+      "step": 720
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.850167214743282e-07,
+      "loss": 1.064,
+      "step": 730
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.7203782776160623e-07,
+      "loss": 1.0665,
+      "step": 740
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.592500393409066e-07,
+      "loss": 1.0707,
+      "step": 750
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.466640764734754e-07,
+      "loss": 1.0721,
+      "step": 760
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.3429049022612086e-07,
+      "loss": 1.0674,
+      "step": 770
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.2213965362604315e-07,
+      "loss": 1.0978,
+      "step": 780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.1022175296491512e-07,
+      "loss": 1.0692,
+      "step": 790
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.985467792595083e-07,
+      "loss": 1.0741,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8712451987602202e-07,
+      "loss": 1.0537,
+      "step": 810
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7596455032513707e-07,
+      "loss": 1.071,
+      "step": 820
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.650762262346713e-07,
+      "loss": 1.0652,
+      "step": 830
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5446867550656767e-07,
+      "loss": 1.0636,
+      "step": 840
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.441507906647905e-07,
+      "loss": 1.0744,
+      "step": 850
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3413122140054217e-07,
+      "loss": 1.0672,
+      "step": 860
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.244183673210532e-07,
+      "loss": 1.0683,
+      "step": 870
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.1502037090802153e-07,
+      "loss": 1.074,
+      "step": 880
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.0594511069160512e-07,
+      "loss": 1.0427,
+      "step": 890
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.720019464569218e-08,
+      "loss": 1.058,
+      "step": 900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.879295380998242e-08,
+      "loss": 1.0496,
+      "step": 910
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.073043614422786e-08,
+      "loss": 1.0498,
+      "step": 920
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.301940061978722e-08,
+      "loss": 1.0746,
+      "step": 930
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.566631155344244e-08,
+      "loss": 1.0475,
+      "step": 940
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.867733318823226e-08,
+      "loss": 1.0835,
+      "step": 950
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.2058324525842414e-08,
+      "loss": 1.0422,
+      "step": 960
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.5814834414886264e-08,
+      "loss": 1.0385,
+      "step": 970
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.995209689919282e-08,
+      "loss": 1.0351,
+      "step": 980
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.44750268300027e-08,
+      "loss": 1.0523,
+      "step": 990
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9388215745748345e-08,
+      "loss": 1.062,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1119,
+  "num_train_epochs": 1,
+  "total_flos": 2.935716160030638e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cdff91d1fb455f6659fb4d9766508982565d0592250e9d29be53487ffd5e3d
+size 3835