Upload 17 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-400/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-400/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "saves\\Qwen2VL-2B-Chat\\full\\v2/checkpoint-800",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

checkpoint-400/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.45.0"
+}

checkpoint-400/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e6db0cc654b7772aedc6337aa32bc9ce1b5d6a010aa6fb76671dd3b5567bcd
+size 4961855184

checkpoint-400/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2942e6243fe8ee5e2effb0fb45e1b48235f7c8701a9791413464f6f74663c1
+size 2543623968

checkpoint-400/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 7505399808
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113f89bd81a69b4a7986ef8bbf67bd0ade9e2f18efc4ed4888a812a610535920
+size 12350008300

checkpoint-400/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cb1869983733651486e797294b9d075e35ed911b745abc673b44d5ac187b23
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e107db35cbbd73d1564cadb38600f1576aea64bad7db92e16860fa5993b98853
+size 1064

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,673 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.686635944700461,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04608294930875576,
+      "grad_norm": 5.774722576141357,
+      "learning_rate": 4.999970619519374e-05,
+      "loss": 0.9942,
+      "num_input_tokens_seen": 6072,
+      "step": 5
+    },
+    {
+      "epoch": 0.09216589861751152,
+      "grad_norm": 4.252433776855469,
+      "learning_rate": 4.9998824787680656e-05,
+      "loss": 0.6317,
+      "num_input_tokens_seen": 11928,
+      "step": 10
+    },
+    {
+      "epoch": 0.1382488479262673,
+      "grad_norm": 1.8097654581069946,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.305,
+      "num_input_tokens_seen": 18040,
+      "step": 15
+    },
+    {
+      "epoch": 0.18433179723502305,
+      "grad_norm": 2.511850118637085,
+      "learning_rate": 4.9995299261212536e-05,
+      "loss": 0.1734,
+      "num_input_tokens_seen": 24016,
+      "step": 20
+    },
+    {
+      "epoch": 0.2304147465437788,
+      "grad_norm": 4.347301006317139,
+      "learning_rate": 4.999265522512283e-05,
+      "loss": 0.2654,
+      "num_input_tokens_seen": 29848,
+      "step": 25
+    },
+    {
+      "epoch": 0.2764976958525346,
+      "grad_norm": 1.3125089406967163,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.1326,
+      "num_input_tokens_seen": 35440,
+      "step": 30
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 2.6110188961029053,
+      "learning_rate": 4.998560491796287e-05,
+      "loss": 0.0996,
+      "num_input_tokens_seen": 41360,
+      "step": 35
+    },
+    {
+      "epoch": 0.3686635944700461,
+      "grad_norm": 2.0633397102355957,
+      "learning_rate": 4.998119881260576e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 47016,
+      "step": 40
+    },
+    {
+      "epoch": 0.4147465437788018,
+      "grad_norm": 1.6892552375793457,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.1384,
+      "num_input_tokens_seen": 53056,
+      "step": 45
+    },
+    {
+      "epoch": 0.4608294930875576,
+      "grad_norm": 2.2047786712646484,
+      "learning_rate": 4.997062521614876e-05,
+      "loss": 0.1176,
+      "num_input_tokens_seen": 58952,
+      "step": 50
+    },
+    {
+      "epoch": 0.5069124423963134,
+      "grad_norm": 2.8315374851226807,
+      "learning_rate": 4.996445797357477e-05,
+      "loss": 0.0888,
+      "num_input_tokens_seen": 64760,
+      "step": 55
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 2.423229932785034,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.0812,
+      "num_input_tokens_seen": 70672,
+      "step": 60
+    },
+    {
+      "epoch": 0.5990783410138248,
+      "grad_norm": 2.2459795475006104,
+      "learning_rate": 4.9950363324518584e-05,
+      "loss": 0.1233,
+      "num_input_tokens_seen": 76608,
+      "step": 65
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 2.267782211303711,
+      "learning_rate": 4.9942436249322444e-05,
+      "loss": 0.1446,
+      "num_input_tokens_seen": 82336,
+      "step": 70
+    },
+    {
+      "epoch": 0.6912442396313364,
+      "grad_norm": 2.2236413955688477,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.0736,
+      "num_input_tokens_seen": 88120,
+      "step": 75
+    },
+    {
+      "epoch": 0.7373271889400922,
+      "grad_norm": 1.833316683769226,
+      "learning_rate": 4.99248235291948e-05,
+      "loss": 0.1129,
+      "num_input_tokens_seen": 93808,
+      "step": 80
+    },
+    {
+      "epoch": 0.783410138248848,
+      "grad_norm": 2.8768177032470703,
+      "learning_rate": 4.991513829823945e-05,
+      "loss": 0.1426,
+      "num_input_tokens_seen": 99928,
+      "step": 85
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 2.096641778945923,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.1401,
+      "num_input_tokens_seen": 106288,
+      "step": 90
+    },
+    {
+      "epoch": 0.8755760368663594,
+      "grad_norm": 2.371711492538452,
+      "learning_rate": 4.9894011232767294e-05,
+      "loss": 0.1127,
+      "num_input_tokens_seen": 112136,
+      "step": 95
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 0.6439377665519714,
+      "learning_rate": 4.9882569894829144e-05,
+      "loss": 0.0524,
+      "num_input_tokens_seen": 117936,
+      "step": 100
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 2.412799835205078,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.0728,
+      "num_input_tokens_seen": 124152,
+      "step": 105
+    },
+    {
+      "epoch": 1.0138248847926268,
+      "grad_norm": 2.985877513885498,
+      "learning_rate": 4.9857932953150465e-05,
+      "loss": 0.0449,
+      "num_input_tokens_seen": 129872,
+      "step": 110
+    },
+    {
+      "epoch": 1.0599078341013826,
+      "grad_norm": 3.5899670124053955,
+      "learning_rate": 4.984473792848607e-05,
+      "loss": 0.0506,
+      "num_input_tokens_seen": 136080,
+      "step": 115
+    },
+    {
+      "epoch": 1.1059907834101383,
+      "grad_norm": 2.940323829650879,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.0431,
+      "num_input_tokens_seen": 141712,
+      "step": 120
+    },
+    {
+      "epoch": 1.1520737327188941,
+      "grad_norm": 2.948409080505371,
+      "learning_rate": 4.981659632220455e-05,
+      "loss": 0.0318,
+      "num_input_tokens_seen": 147544,
+      "step": 125
+    },
+    {
+      "epoch": 1.1981566820276497,
+      "grad_norm": 1.2344759702682495,
+      "learning_rate": 4.9801650402038555e-05,
+      "loss": 0.0593,
+      "num_input_tokens_seen": 153344,
+      "step": 130
+    },
+    {
+      "epoch": 1.2442396313364055,
+      "grad_norm": 3.271662473678589,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.0617,
+      "num_input_tokens_seen": 159160,
+      "step": 135
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 3.5447471141815186,
+      "learning_rate": 4.977001008412113e-05,
+      "loss": 0.0456,
+      "num_input_tokens_seen": 164760,
+      "step": 140
+    },
+    {
+      "epoch": 1.336405529953917,
+      "grad_norm": 4.001632213592529,
+      "learning_rate": 4.9753316430055894e-05,
+      "loss": 0.068,
+      "num_input_tokens_seen": 170624,
+      "step": 145
+    },
+    {
+      "epoch": 1.3824884792626728,
+      "grad_norm": 1.6239632368087769,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.0383,
+      "num_input_tokens_seen": 176480,
+      "step": 150
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.19192902743816376,
+      "learning_rate": 4.9718184093573475e-05,
+      "loss": 0.0351,
+      "num_input_tokens_seen": 182056,
+      "step": 155
+    },
+    {
+      "epoch": 1.4746543778801844,
+      "grad_norm": 3.1995279788970947,
+      "learning_rate": 4.969974623692023e-05,
+      "loss": 0.1139,
+      "num_input_tokens_seen": 188032,
+      "step": 160
+    },
+    {
+      "epoch": 1.52073732718894,
+      "grad_norm": 2.926187038421631,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.0738,
+      "num_input_tokens_seen": 194112,
+      "step": 165
+    },
+    {
+      "epoch": 1.5668202764976957,
+      "grad_norm": 1.8316713571548462,
+      "learning_rate": 4.966112931363185e-05,
+      "loss": 0.0567,
+      "num_input_tokens_seen": 200368,
+      "step": 170
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 2.283552885055542,
+      "learning_rate": 4.964095115466373e-05,
+      "loss": 0.0793,
+      "num_input_tokens_seen": 206520,
+      "step": 175
+    },
+    {
+      "epoch": 1.6589861751152073,
+      "grad_norm": 2.575171709060669,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.0564,
+      "num_input_tokens_seen": 212328,
+      "step": 180
+    },
+    {
+      "epoch": 1.705069124423963,
+      "grad_norm": 3.201814651489258,
+      "learning_rate": 4.959885781344452e-05,
+      "loss": 0.0677,
+      "num_input_tokens_seen": 218456,
+      "step": 185
+    },
+    {
+      "epoch": 1.7511520737327189,
+      "grad_norm": 2.607283592224121,
+      "learning_rate": 4.9576943620571507e-05,
+      "loss": 0.0474,
+      "num_input_tokens_seen": 224240,
+      "step": 190
+    },
+    {
+      "epoch": 1.7972350230414746,
+      "grad_norm": 1.2559226751327515,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.053,
+      "num_input_tokens_seen": 230456,
+      "step": 195
+    },
+    {
+      "epoch": 1.8433179723502304,
+      "grad_norm": 1.7003673315048218,
+      "learning_rate": 4.953138276568462e-05,
+      "loss": 0.0477,
+      "num_input_tokens_seen": 236448,
+      "step": 200
+    },
+    {
+      "epoch": 1.8894009216589862,
+      "grad_norm": 2.2908496856689453,
+      "learning_rate": 4.950773717455061e-05,
+      "loss": 0.0581,
+      "num_input_tokens_seen": 242536,
+      "step": 205
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 3.7818005084991455,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.0583,
+      "num_input_tokens_seen": 248352,
+      "step": 210
+    },
+    {
+      "epoch": 1.9815668202764978,
+      "grad_norm": 1.7777669429779053,
+      "learning_rate": 4.945871844376369e-05,
+      "loss": 0.0245,
+      "num_input_tokens_seen": 253928,
+      "step": 215
+    },
+    {
+      "epoch": 2.0276497695852536,
+      "grad_norm": 1.5329607725143433,
+      "learning_rate": 4.94333464562659e-05,
+      "loss": 0.0354,
+      "num_input_tokens_seen": 259904,
+      "step": 220
+    },
+    {
+      "epoch": 2.0737327188940093,
+      "grad_norm": 2.1847078800201416,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.0352,
+      "num_input_tokens_seen": 265656,
+      "step": 225
+    },
+    {
+      "epoch": 2.119815668202765,
+      "grad_norm": 1.6991156339645386,
+      "learning_rate": 4.938088021881233e-05,
+      "loss": 0.0416,
+      "num_input_tokens_seen": 271576,
+      "step": 230
+    },
+    {
+      "epoch": 2.165898617511521,
+      "grad_norm": 3.675462484359741,
+      "learning_rate": 4.935378720204319e-05,
+      "loss": 0.047,
+      "num_input_tokens_seen": 277464,
+      "step": 235
+    },
+    {
+      "epoch": 2.2119815668202767,
+      "grad_norm": 1.8100879192352295,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.0454,
+      "num_input_tokens_seen": 283592,
+      "step": 240
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 2.6867613792419434,
+      "learning_rate": 4.929788455642864e-05,
+      "loss": 0.0647,
+      "num_input_tokens_seen": 289544,
+      "step": 245
+    },
+    {
+      "epoch": 2.3041474654377883,
+      "grad_norm": 0.8391556143760681,
+      "learning_rate": 4.9269076241540505e-05,
+      "loss": 0.0283,
+      "num_input_tokens_seen": 295480,
+      "step": 250
+    },
+    {
+      "epoch": 2.3502304147465436,
+      "grad_norm": 3.0261058807373047,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.0301,
+      "num_input_tokens_seen": 301680,
+      "step": 255
+    },
+    {
+      "epoch": 2.3963133640552994,
+      "grad_norm": 1.320726990699768,
+      "learning_rate": 4.920974901319515e-05,
+      "loss": 0.0416,
+      "num_input_tokens_seen": 307768,
+      "step": 260
+    },
+    {
+      "epoch": 2.442396313364055,
+      "grad_norm": 3.625941753387451,
+      "learning_rate": 4.917923149418792e-05,
+      "loss": 0.0504,
+      "num_input_tokens_seen": 313376,
+      "step": 265
+    },
+    {
+      "epoch": 2.488479262672811,
+      "grad_norm": 1.6434024572372437,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.0499,
+      "num_input_tokens_seen": 319592,
+      "step": 270
+    },
+    {
+      "epoch": 2.5345622119815667,
+      "grad_norm": 2.392733573913574,
+      "learning_rate": 4.911649223296499e-05,
+      "loss": 0.03,
+      "num_input_tokens_seen": 325392,
+      "step": 275
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 3.644463539123535,
+      "learning_rate": 4.9084271965397014e-05,
+      "loss": 0.0416,
+      "num_input_tokens_seen": 331264,
+      "step": 280
+    },
+    {
+      "epoch": 2.6267281105990783,
+      "grad_norm": 1.160701870918274,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.0639,
+      "num_input_tokens_seen": 337584,
+      "step": 285
+    },
+    {
+      "epoch": 2.672811059907834,
+      "grad_norm": 2.189955711364746,
+      "learning_rate": 4.901813394291801e-05,
+      "loss": 0.048,
+      "num_input_tokens_seen": 343632,
+      "step": 290
+    },
+    {
+      "epoch": 2.71889400921659,
+      "grad_norm": 2.4015591144561768,
+      "learning_rate": 4.898421774254051e-05,
+      "loss": 0.0465,
+      "num_input_tokens_seen": 349392,
+      "step": 295
+    },
+    {
+      "epoch": 2.7649769585253456,
+      "grad_norm": 1.5051063299179077,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.0512,
+      "num_input_tokens_seen": 355104,
+      "step": 300
+    },
+    {
+      "epoch": 2.8110599078341014,
+      "grad_norm": 2.82021427154541,
+      "learning_rate": 4.891469494938781e-05,
+      "loss": 0.0412,
+      "num_input_tokens_seen": 360824,
+      "step": 305
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.578285574913025,
+      "learning_rate": 4.887908999070308e-05,
+      "loss": 0.0292,
+      "num_input_tokens_seen": 366792,
+      "step": 310
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 2.392061710357666,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.0264,
+      "num_input_tokens_seen": 372536,
+      "step": 315
+    },
+    {
+      "epoch": 2.9493087557603688,
+      "grad_norm": 0.46661177277565,
+      "learning_rate": 4.880619713346039e-05,
+      "loss": 0.0402,
+      "num_input_tokens_seen": 378472,
+      "step": 320
+    },
+    {
+      "epoch": 2.9953917050691246,
+      "grad_norm": 2.8422093391418457,
+      "learning_rate": 4.876891094820417e-05,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 383984,
+      "step": 325
+    },
+    {
+      "epoch": 3.0414746543778803,
+      "grad_norm": 1.581181526184082,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.0536,
+      "num_input_tokens_seen": 389896,
+      "step": 330
+    },
+    {
+      "epoch": 3.087557603686636,
+      "grad_norm": 2.1210877895355225,
+      "learning_rate": 4.869266344634556e-05,
+      "loss": 0.0295,
+      "num_input_tokens_seen": 395848,
+      "step": 335
+    },
+    {
+      "epoch": 3.133640552995392,
+      "grad_norm": 0.6473267078399658,
+      "learning_rate": 4.8653703921893766e-05,
+      "loss": 0.0209,
+      "num_input_tokens_seen": 401784,
+      "step": 340
+    },
+    {
+      "epoch": 3.1797235023041477,
+      "grad_norm": 3.651721239089966,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.0348,
+      "num_input_tokens_seen": 407656,
+      "step": 345
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 1.2039521932601929,
+      "learning_rate": 4.85741179045219e-05,
+      "loss": 0.0167,
+      "num_input_tokens_seen": 413344,
+      "step": 350
+    },
+    {
+      "epoch": 3.271889400921659,
+      "grad_norm": 2.5414485931396484,
+      "learning_rate": 4.853349328222219e-05,
+      "loss": 0.0567,
+      "num_input_tokens_seen": 419112,
+      "step": 355
+    },
+    {
+      "epoch": 3.3179723502304146,
+      "grad_norm": 0.12772409617900848,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.0483,
+      "num_input_tokens_seen": 425104,
+      "step": 360
+    },
+    {
+      "epoch": 3.3640552995391704,
+      "grad_norm": 1.686139702796936,
+      "learning_rate": 4.845058558465645e-05,
+      "loss": 0.0379,
+      "num_input_tokens_seen": 430920,
+      "step": 365
+    },
+    {
+      "epoch": 3.410138248847926,
+      "grad_norm": 1.3768738508224487,
+      "learning_rate": 4.840830445808483e-05,
+      "loss": 0.0447,
+      "num_input_tokens_seen": 436864,
+      "step": 370
+    },
+    {
+      "epoch": 3.456221198156682,
+      "grad_norm": 1.8329992294311523,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.0417,
+      "num_input_tokens_seen": 442880,
+      "step": 375
+    },
+    {
+      "epoch": 3.5023041474654377,
+      "grad_norm": 2.0811145305633545,
+      "learning_rate": 4.832209261830002e-05,
+      "loss": 0.0368,
+      "num_input_tokens_seen": 448536,
+      "step": 380
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.14438925683498383,
+      "learning_rate": 4.827816393144305e-05,
+      "loss": 0.0269,
+      "num_input_tokens_seen": 454664,
+      "step": 385
+    },
+    {
+      "epoch": 3.5944700460829493,
+      "grad_norm": 2.131544828414917,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.0387,
+      "num_input_tokens_seen": 460584,
+      "step": 390
+    },
+    {
+      "epoch": 3.640552995391705,
+      "grad_norm": 2.2278664112091064,
+      "learning_rate": 4.818866618635947e-05,
+      "loss": 0.0365,
+      "num_input_tokens_seen": 466352,
+      "step": 395
+    },
+    {
+      "epoch": 3.686635944700461,
+      "grad_norm": 0.2778138220310211,
+      "learning_rate": 4.814309923172227e-05,
+      "loss": 0.0394,
+      "num_input_tokens_seen": 472288,
+      "step": 400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3240,
+  "num_input_tokens_seen": 472288,
+  "num_train_epochs": 30,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5598346769498112.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56b169a05e83938a23cdb9f6db34965a96f52e4cf59396fd2ba7967cebc66c0
+size 5368