Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9992659652556888,
+    "total_flos": 2.8896472925732864e+18,
+    "train_loss": 1.1314670071662583,
+    "train_runtime": 7504.4933,
+    "train_samples_per_second": 17.424,
+    "train_steps_per_second": 0.136
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "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": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd89c6c65228d3973c821522d1372d5538478fd3617ee124eb0fd2eb613f519d
+size 4997750760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34eba3738098a5e4dc71675474fecb28c21f71b66dfe8840edb907c1131ca7e4
+size 3133917248

model.safetensors.index.json

@@ -0,0 +1,832 @@
+{
+  "metadata": {
+    "total_size": 8131575808
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "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-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-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.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.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.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "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.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "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"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9992659652556888,
+    "total_flos": 2.8896472925732864e+18,
+    "train_loss": 1.1314670071662583,
+    "train_runtime": 7504.4933,
+    "train_samples_per_second": 17.424,
+    "train_steps_per_second": 0.136
+}

trainer_log.jsonl

@@ -0,0 +1,116 @@
+{"current_steps": 10, "total_steps": 1022, "loss": 1.6183, "lr": 8.737864077669904e-07, "epoch": 0.009784735812133072, "percentage": 0.98, "elapsed_time": "0:01:17", "remaining_time": "2:10:10"}
+{"current_steps": 20, "total_steps": 1022, "loss": 1.572, "lr": 1.8446601941747574e-06, "epoch": 0.019569471624266144, "percentage": 1.96, "elapsed_time": "0:02:30", "remaining_time": "2:05:42"}
+{"current_steps": 30, "total_steps": 1022, "loss": 1.4955, "lr": 2.8155339805825245e-06, "epoch": 0.029354207436399216, "percentage": 2.94, "elapsed_time": "0:03:44", "remaining_time": "2:03:32"}
+{"current_steps": 40, "total_steps": 1022, "loss": 1.3854, "lr": 3.7864077669902915e-06, "epoch": 0.03913894324853229, "percentage": 3.91, "elapsed_time": "0:04:59", "remaining_time": "2:02:43"}
+{"current_steps": 50, "total_steps": 1022, "loss": 1.3327, "lr": 4.7572815533980585e-06, "epoch": 0.04892367906066536, "percentage": 4.89, "elapsed_time": "0:06:14", "remaining_time": "2:01:17"}
+{"current_steps": 60, "total_steps": 1022, "loss": 1.285, "lr": 5.728155339805825e-06, "epoch": 0.05870841487279843, "percentage": 5.87, "elapsed_time": "0:07:28", "remaining_time": "1:59:50"}
+{"current_steps": 70, "total_steps": 1022, "loss": 1.2348, "lr": 6.6990291262135935e-06, "epoch": 0.0684931506849315, "percentage": 6.85, "elapsed_time": "0:08:40", "remaining_time": "1:57:52"}
+{"current_steps": 80, "total_steps": 1022, "loss": 1.2406, "lr": 7.66990291262136e-06, "epoch": 0.07827788649706457, "percentage": 7.83, "elapsed_time": "0:09:59", "remaining_time": "1:57:37"}
+{"current_steps": 90, "total_steps": 1022, "loss": 1.2062, "lr": 8.640776699029127e-06, "epoch": 0.08806262230919765, "percentage": 8.81, "elapsed_time": "0:11:20", "remaining_time": "1:57:27"}
+{"current_steps": 100, "total_steps": 1022, "loss": 1.2061, "lr": 9.611650485436894e-06, "epoch": 0.09784735812133072, "percentage": 9.78, "elapsed_time": "0:12:33", "remaining_time": "1:55:44"}
+{"current_steps": 110, "total_steps": 1022, "loss": 1.1952, "lr": 9.998948289992603e-06, "epoch": 0.10763209393346379, "percentage": 10.76, "elapsed_time": "0:13:45", "remaining_time": "1:54:02"}
+{"current_steps": 120, "total_steps": 1022, "loss": 1.1933, "lr": 9.9925227754539e-06, "epoch": 0.11741682974559686, "percentage": 11.74, "elapsed_time": "0:14:53", "remaining_time": "1:51:57"}
+{"current_steps": 130, "total_steps": 1022, "loss": 1.1683, "lr": 9.980263528784014e-06, "epoch": 0.12720156555772993, "percentage": 12.72, "elapsed_time": "0:16:09", "remaining_time": "1:50:50"}
+{"current_steps": 10, "total_steps": 1021, "loss": 1.6202, "lr": 8.737864077669904e-07, "epoch": 0.009787129924149743, "percentage": 0.98, "elapsed_time": "0:01:10", "remaining_time": "1:59:34"}
+{"current_steps": 20, "total_steps": 1021, "loss": 1.5766, "lr": 1.8446601941747574e-06, "epoch": 0.019574259848299486, "percentage": 1.96, "elapsed_time": "0:02:20", "remaining_time": "1:57:28"}
+{"current_steps": 30, "total_steps": 1021, "loss": 1.4962, "lr": 2.8155339805825245e-06, "epoch": 0.029361389772449228, "percentage": 2.94, "elapsed_time": "0:03:32", "remaining_time": "1:56:45"}
+{"current_steps": 40, "total_steps": 1021, "loss": 1.3827, "lr": 3.7864077669902915e-06, "epoch": 0.03914851969659897, "percentage": 3.92, "elapsed_time": "0:04:42", "remaining_time": "1:55:27"}
+{"current_steps": 50, "total_steps": 1021, "loss": 1.3328, "lr": 4.7572815533980585e-06, "epoch": 0.048935649620748714, "percentage": 4.9, "elapsed_time": "0:05:55", "remaining_time": "1:54:57"}
+{"current_steps": 60, "total_steps": 1021, "loss": 1.2826, "lr": 5.728155339805825e-06, "epoch": 0.058722779544898455, "percentage": 5.88, "elapsed_time": "0:07:07", "remaining_time": "1:54:08"}
+{"current_steps": 70, "total_steps": 1021, "loss": 1.234, "lr": 6.6990291262135935e-06, "epoch": 0.0685099094690482, "percentage": 6.86, "elapsed_time": "0:08:16", "remaining_time": "1:52:22"}
+{"current_steps": 80, "total_steps": 1021, "loss": 1.2398, "lr": 7.66990291262136e-06, "epoch": 0.07829703939319795, "percentage": 7.84, "elapsed_time": "0:09:28", "remaining_time": "1:51:31"}
+{"current_steps": 90, "total_steps": 1021, "loss": 1.2031, "lr": 8.640776699029127e-06, "epoch": 0.0880841693173477, "percentage": 8.81, "elapsed_time": "0:10:44", "remaining_time": "1:51:05"}
+{"current_steps": 100, "total_steps": 1021, "loss": 1.2039, "lr": 9.611650485436894e-06, "epoch": 0.09787129924149743, "percentage": 9.79, "elapsed_time": "0:11:54", "remaining_time": "1:49:39"}
+{"current_steps": 110, "total_steps": 1021, "loss": 1.1918, "lr": 9.998945997517957e-06, "epoch": 0.10765842916564718, "percentage": 10.77, "elapsed_time": "0:13:04", "remaining_time": "1:48:13"}
+{"current_steps": 120, "total_steps": 1021, "loss": 1.1916, "lr": 9.992506480404137e-06, "epoch": 0.11744555908979691, "percentage": 11.75, "elapsed_time": "0:14:13", "remaining_time": "1:46:46"}
+{"current_steps": 130, "total_steps": 1021, "loss": 1.1654, "lr": 9.980220534903889e-06, "epoch": 0.12723268901394666, "percentage": 12.73, "elapsed_time": "0:15:26", "remaining_time": "1:45:47"}
+{"current_steps": 140, "total_steps": 1021, "loss": 1.1627, "lr": 9.96210254835968e-06, "epoch": 0.1370198189380964, "percentage": 13.71, "elapsed_time": "0:16:39", "remaining_time": "1:44:51"}
+{"current_steps": 150, "total_steps": 1021, "loss": 1.1622, "lr": 9.938173737671531e-06, "epoch": 0.14680694886224616, "percentage": 14.69, "elapsed_time": "0:17:49", "remaining_time": "1:43:27"}
+{"current_steps": 160, "total_steps": 1021, "loss": 1.1588, "lr": 9.908462124451152e-06, "epoch": 0.1565940787863959, "percentage": 15.67, "elapsed_time": "0:18:58", "remaining_time": "1:42:03"}
+{"current_steps": 170, "total_steps": 1021, "loss": 1.1774, "lr": 9.873002502207502e-06, "epoch": 0.16638120871054562, "percentage": 16.65, "elapsed_time": "0:20:10", "remaining_time": "1:40:59"}
+{"current_steps": 180, "total_steps": 1021, "loss": 1.1632, "lr": 9.831836395602164e-06, "epoch": 0.1761683386346954, "percentage": 17.63, "elapsed_time": "0:21:22", "remaining_time": "1:39:52"}
+{"current_steps": 190, "total_steps": 1021, "loss": 1.1575, "lr": 9.78501201182228e-06, "epoch": 0.18595546855884512, "percentage": 18.61, "elapsed_time": "0:22:31", "remaining_time": "1:38:32"}
+{"current_steps": 200, "total_steps": 1021, "loss": 1.145, "lr": 9.732584184127973e-06, "epoch": 0.19574259848299486, "percentage": 19.59, "elapsed_time": "0:23:44", "remaining_time": "1:37:25"}
+{"current_steps": 210, "total_steps": 1021, "loss": 1.1595, "lr": 9.674614307640368e-06, "epoch": 0.20552972840714462, "percentage": 20.57, "elapsed_time": "0:24:53", "remaining_time": "1:36:08"}
+{"current_steps": 220, "total_steps": 1021, "loss": 1.1383, "lr": 9.611170267445401e-06, "epoch": 0.21531685833129435, "percentage": 21.55, "elapsed_time": "0:26:06", "remaining_time": "1:35:02"}
+{"current_steps": 230, "total_steps": 1021, "loss": 1.1329, "lr": 9.542326359097619e-06, "epoch": 0.2251039882554441, "percentage": 22.53, "elapsed_time": "0:27:16", "remaining_time": "1:33:47"}
+{"current_steps": 240, "total_steps": 1021, "loss": 1.1323, "lr": 9.468163201617063e-06, "epoch": 0.23489111817959382, "percentage": 23.51, "elapsed_time": "0:28:28", "remaining_time": "1:32:39"}
+{"current_steps": 250, "total_steps": 1021, "loss": 1.1332, "lr": 9.388767643081109e-06, "epoch": 0.24467824810374358, "percentage": 24.49, "elapsed_time": "0:29:36", "remaining_time": "1:31:18"}
+{"current_steps": 260, "total_steps": 1021, "loss": 1.1301, "lr": 9.30423265892184e-06, "epoch": 0.2544653780278933, "percentage": 25.47, "elapsed_time": "0:30:48", "remaining_time": "1:30:10"}
+{"current_steps": 270, "total_steps": 1021, "loss": 1.1483, "lr": 9.214657243048021e-06, "epoch": 0.2642525079520431, "percentage": 26.44, "elapsed_time": "0:31:57", "remaining_time": "1:28:53"}
+{"current_steps": 280, "total_steps": 1021, "loss": 1.1249, "lr": 9.120146291919206e-06, "epoch": 0.2740396378761928, "percentage": 27.42, "elapsed_time": "0:33:08", "remaining_time": "1:27:43"}
+{"current_steps": 290, "total_steps": 1021, "loss": 1.1385, "lr": 9.020810481707709e-06, "epoch": 0.28382676780034255, "percentage": 28.4, "elapsed_time": "0:34:22", "remaining_time": "1:26:38"}
+{"current_steps": 300, "total_steps": 1021, "loss": 1.1326, "lr": 8.916766138692303e-06, "epoch": 0.2936138977244923, "percentage": 29.38, "elapsed_time": "0:35:32", "remaining_time": "1:25:25"}
+{"current_steps": 310, "total_steps": 1021, "loss": 1.1223, "lr": 8.808135103035407e-06, "epoch": 0.303401027648642, "percentage": 30.36, "elapsed_time": "0:36:41", "remaining_time": "1:24:08"}
+{"current_steps": 320, "total_steps": 1021, "loss": 1.1314, "lr": 8.695044586103297e-06, "epoch": 0.3131881575727918, "percentage": 31.34, "elapsed_time": "0:37:51", "remaining_time": "1:22:55"}
+{"current_steps": 330, "total_steps": 1021, "loss": 1.1254, "lr": 8.577627021496413e-06, "epoch": 0.32297528749694154, "percentage": 32.32, "elapsed_time": "0:39:00", "remaining_time": "1:21:41"}
+{"current_steps": 340, "total_steps": 1021, "loss": 1.1115, "lr": 8.456019909964224e-06, "epoch": 0.33276241742109125, "percentage": 33.3, "elapsed_time": "0:40:11", "remaining_time": "1:20:29"}
+{"current_steps": 350, "total_steps": 1021, "loss": 1.142, "lr": 8.330365658386252e-06, "epoch": 0.342549547345241, "percentage": 34.28, "elapsed_time": "0:41:20", "remaining_time": "1:19:14"}
+{"current_steps": 360, "total_steps": 1021, "loss": 1.1254, "lr": 8.200811413007808e-06, "epoch": 0.3523366772693908, "percentage": 35.26, "elapsed_time": "0:42:32", "remaining_time": "1:18:06"}
+{"current_steps": 370, "total_steps": 1021, "loss": 1.127, "lr": 8.06750888712576e-06, "epoch": 0.3621238071935405, "percentage": 36.24, "elapsed_time": "0:43:43", "remaining_time": "1:16:55"}
+{"current_steps": 380, "total_steps": 1021, "loss": 1.0985, "lr": 7.930614183426074e-06, "epoch": 0.37191093711769024, "percentage": 37.22, "elapsed_time": "0:44:54", "remaining_time": "1:15:45"}
+{"current_steps": 390, "total_steps": 1021, "loss": 1.1061, "lr": 7.790287611181217e-06, "epoch": 0.38169806704184, "percentage": 38.2, "elapsed_time": "0:46:07", "remaining_time": "1:14:38"}
+{"current_steps": 400, "total_steps": 1021, "loss": 1.1178, "lr": 7.646693498521472e-06, "epoch": 0.3914851969659897, "percentage": 39.18, "elapsed_time": "0:47:16", "remaining_time": "1:13:23"}
+{"current_steps": 410, "total_steps": 1021, "loss": 1.1076, "lr": 7.500000000000001e-06, "epoch": 0.4012723268901395, "percentage": 40.16, "elapsed_time": "0:48:27", "remaining_time": "1:12:12"}
+{"current_steps": 420, "total_steps": 1021, "loss": 1.123, "lr": 7.35037889967702e-06, "epoch": 0.41105945681428924, "percentage": 41.14, "elapsed_time": "0:49:39", "remaining_time": "1:11:04"}
+{"current_steps": 430, "total_steps": 1021, "loss": 1.1142, "lr": 7.19800540995367e-06, "epoch": 0.42084658673843894, "percentage": 42.12, "elapsed_time": "0:50:51", "remaining_time": "1:09:54"}
+{"current_steps": 440, "total_steps": 1021, "loss": 1.1068, "lr": 7.043057966391158e-06, "epoch": 0.4306337166625887, "percentage": 43.1, "elapsed_time": "0:52:02", "remaining_time": "1:08:42"}
+{"current_steps": 450, "total_steps": 1021, "loss": 1.1024, "lr": 6.885718018755448e-06, "epoch": 0.4404208465867384, "percentage": 44.07, "elapsed_time": "0:53:13", "remaining_time": "1:07:32"}
+{"current_steps": 460, "total_steps": 1021, "loss": 1.0918, "lr": 6.7261698185322e-06, "epoch": 0.4502079765108882, "percentage": 45.05, "elapsed_time": "0:54:24", "remaining_time": "1:06:21"}
+{"current_steps": 470, "total_steps": 1021, "loss": 1.1092, "lr": 6.5646002031607726e-06, "epoch": 0.45999510643503794, "percentage": 46.03, "elapsed_time": "0:55:36", "remaining_time": "1:05:11"}
+{"current_steps": 480, "total_steps": 1021, "loss": 1.1096, "lr": 6.401198377239979e-06, "epoch": 0.46978223635918764, "percentage": 47.01, "elapsed_time": "0:56:48", "remaining_time": "1:04:01"}
+{"current_steps": 490, "total_steps": 1021, "loss": 1.1118, "lr": 6.236155690961795e-06, "epoch": 0.4795693662833374, "percentage": 47.99, "elapsed_time": "0:57:57", "remaining_time": "1:02:48"}
+{"current_steps": 500, "total_steps": 1021, "loss": 1.0969, "lr": 6.0696654160324875e-06, "epoch": 0.48935649620748717, "percentage": 48.97, "elapsed_time": "0:59:10", "remaining_time": "1:01:39"}
+{"current_steps": 510, "total_steps": 1021, "loss": 1.107, "lr": 5.901922519343586e-06, "epoch": 0.4991436261316369, "percentage": 49.95, "elapsed_time": "1:01:58", "remaining_time": "1:02:05"}
+{"current_steps": 520, "total_steps": 1021, "loss": 1.1008, "lr": 5.733123434657704e-06, "epoch": 0.5089307560557866, "percentage": 50.93, "elapsed_time": "1:03:09", "remaining_time": "1:00:51"}
+{"current_steps": 530, "total_steps": 1021, "loss": 1.1122, "lr": 5.5634658325766066e-06, "epoch": 0.5187178859799364, "percentage": 51.91, "elapsed_time": "1:04:20", "remaining_time": "0:59:36"}
+{"current_steps": 540, "total_steps": 1021, "loss": 1.1052, "lr": 5.393148389060893e-06, "epoch": 0.5285050159040862, "percentage": 52.89, "elapsed_time": "1:05:37", "remaining_time": "0:58:27"}
+{"current_steps": 550, "total_steps": 1021, "loss": 1.1014, "lr": 5.222370552772353e-06, "epoch": 0.5382921458282359, "percentage": 53.87, "elapsed_time": "1:06:47", "remaining_time": "0:57:12"}
+{"current_steps": 560, "total_steps": 1021, "loss": 1.0981, "lr": 5.05133231151145e-06, "epoch": 0.5480792757523856, "percentage": 54.85, "elapsed_time": "1:07:57", "remaining_time": "0:55:56"}
+{"current_steps": 570, "total_steps": 1021, "loss": 1.1086, "lr": 4.880233958023486e-06, "epoch": 0.5578664056765353, "percentage": 55.83, "elapsed_time": "1:09:10", "remaining_time": "0:54:44"}
+{"current_steps": 580, "total_steps": 1021, "loss": 1.0938, "lr": 4.7092758554476215e-06, "epoch": 0.5676535356006851, "percentage": 56.81, "elapsed_time": "1:10:21", "remaining_time": "0:53:29"}
+{"current_steps": 590, "total_steps": 1021, "loss": 1.1038, "lr": 4.53865820268349e-06, "epoch": 0.5774406655248349, "percentage": 57.79, "elapsed_time": "1:11:31", "remaining_time": "0:52:15"}
+{"current_steps": 600, "total_steps": 1021, "loss": 1.0784, "lr": 4.368580799950133e-06, "epoch": 0.5872277954489846, "percentage": 58.77, "elapsed_time": "1:12:42", "remaining_time": "0:51:00"}
+{"current_steps": 610, "total_steps": 1021, "loss": 1.1028, "lr": 4.199242814811807e-06, "epoch": 0.5970149253731343, "percentage": 59.75, "elapsed_time": "1:13:53", "remaining_time": "0:49:47"}
+{"current_steps": 620, "total_steps": 1021, "loss": 1.0938, "lr": 4.03084254894465e-06, "epoch": 0.606802055297284, "percentage": 60.72, "elapsed_time": "1:15:03", "remaining_time": "0:48:32"}
+{"current_steps": 630, "total_steps": 1021, "loss": 1.0917, "lr": 3.863577205917356e-06, "epoch": 0.6165891852214338, "percentage": 61.7, "elapsed_time": "1:16:14", "remaining_time": "0:47:19"}
+{"current_steps": 640, "total_steps": 1021, "loss": 1.0837, "lr": 3.6976426602577565e-06, "epoch": 0.6263763151455836, "percentage": 62.68, "elapsed_time": "1:17:22", "remaining_time": "0:46:03"}
+{"current_steps": 650, "total_steps": 1021, "loss": 1.0964, "lr": 3.5332332280757706e-06, "epoch": 0.6361634450697333, "percentage": 63.66, "elapsed_time": "1:18:35", "remaining_time": "0:44:51"}
+{"current_steps": 660, "total_steps": 1021, "loss": 1.0897, "lr": 3.3705414395113354e-06, "epoch": 0.6459505749938831, "percentage": 64.64, "elapsed_time": "1:19:45", "remaining_time": "0:43:37"}
+{"current_steps": 670, "total_steps": 1021, "loss": 1.0986, "lr": 3.2097578132737716e-06, "epoch": 0.6557377049180327, "percentage": 65.62, "elapsed_time": "1:20:57", "remaining_time": "0:42:24"}
+{"current_steps": 680, "total_steps": 1021, "loss": 1.0877, "lr": 3.0510706335366034e-06, "epoch": 0.6655248348421825, "percentage": 66.6, "elapsed_time": "1:22:10", "remaining_time": "0:41:12"}
+{"current_steps": 690, "total_steps": 1021, "loss": 1.0941, "lr": 2.8946657294491452e-06, "epoch": 0.6753119647663323, "percentage": 67.58, "elapsed_time": "1:23:20", "remaining_time": "0:39:58"}
+{"current_steps": 700, "total_steps": 1021, "loss": 1.0857, "lr": 2.740726257522987e-06, "epoch": 0.685099094690482, "percentage": 68.56, "elapsed_time": "1:24:30", "remaining_time": "0:38:45"}
+{"current_steps": 710, "total_steps": 1021, "loss": 1.0781, "lr": 2.5894324871482557e-06, "epoch": 0.6948862246146318, "percentage": 69.54, "elapsed_time": "1:25:42", "remaining_time": "0:37:32"}
+{"current_steps": 720, "total_steps": 1021, "loss": 1.0713, "lr": 2.4409615894908407e-06, "epoch": 0.7046733545387815, "percentage": 70.52, "elapsed_time": "1:26:51", "remaining_time": "0:36:18"}
+{"current_steps": 730, "total_steps": 1021, "loss": 1.0765, "lr": 2.2954874300177197e-06, "epoch": 0.7144604844629312, "percentage": 71.5, "elapsed_time": "1:27:59", "remaining_time": "0:35:04"}
+{"current_steps": 740, "total_steps": 1021, "loss": 1.0835, "lr": 2.1531803648934333e-06, "epoch": 0.724247614387081, "percentage": 72.48, "elapsed_time": "1:29:12", "remaining_time": "0:33:52"}
+{"current_steps": 750, "total_steps": 1021, "loss": 1.0836, "lr": 2.0142070414860704e-06, "epoch": 0.7340347443112307, "percentage": 73.46, "elapsed_time": "1:30:23", "remaining_time": "0:32:39"}
+{"current_steps": 760, "total_steps": 1021, "loss": 1.0816, "lr": 1.8787302032164168e-06, "epoch": 0.7438218742353805, "percentage": 74.44, "elapsed_time": "1:31:35", "remaining_time": "0:31:27"}
+{"current_steps": 770, "total_steps": 1021, "loss": 1.0807, "lr": 1.746908498978791e-06, "epoch": 0.7536090041595302, "percentage": 75.42, "elapsed_time": "1:32:47", "remaining_time": "0:30:14"}
+{"current_steps": 780, "total_steps": 1021, "loss": 1.0828, "lr": 1.6188962973567068e-06, "epoch": 0.76339613408368, "percentage": 76.4, "elapsed_time": "1:34:00", "remaining_time": "0:29:02"}
+{"current_steps": 790, "total_steps": 1021, "loss": 1.1013, "lr": 1.4948435058510036e-06, "epoch": 0.7731832640078297, "percentage": 77.38, "elapsed_time": "1:35:09", "remaining_time": "0:27:49"}
+{"current_steps": 800, "total_steps": 1021, "loss": 1.07, "lr": 1.374895395332037e-06, "epoch": 0.7829703939319794, "percentage": 78.35, "elapsed_time": "1:36:21", "remaining_time": "0:26:37"}
+{"current_steps": 810, "total_steps": 1021, "loss": 1.0796, "lr": 1.259192429921584e-06, "epoch": 0.7927575238561292, "percentage": 79.33, "elapsed_time": "1:37:32", "remaining_time": "0:25:24"}
+{"current_steps": 820, "total_steps": 1021, "loss": 1.1017, "lr": 1.1478701025036359e-06, "epoch": 0.802544653780279, "percentage": 80.31, "elapsed_time": "1:38:43", "remaining_time": "0:24:11"}
+{"current_steps": 830, "total_steps": 1021, "loss": 1.0805, "lr": 1.0410587760567104e-06, "epoch": 0.8123317837044287, "percentage": 81.29, "elapsed_time": "1:39:53", "remaining_time": "0:22:59"}
+{"current_steps": 840, "total_steps": 1021, "loss": 1.068, "lr": 9.388835309934985e-07, "epoch": 0.8221189136285785, "percentage": 82.27, "elapsed_time": "1:41:05", "remaining_time": "0:21:46"}
+{"current_steps": 850, "total_steps": 1021, "loss": 1.0832, "lr": 8.414640186866063e-07, "epoch": 0.8319060435527281, "percentage": 83.25, "elapsed_time": "1:42:15", "remaining_time": "0:20:34"}
+{"current_steps": 860, "total_steps": 1021, "loss": 1.0858, "lr": 7.489143213519301e-07, "epoch": 0.8416931734768779, "percentage": 84.23, "elapsed_time": "1:43:28", "remaining_time": "0:19:22"}
+{"current_steps": 870, "total_steps": 1021, "loss": 1.0938, "lr": 6.613428184537235e-07, "epoch": 0.8514803034010276, "percentage": 85.21, "elapsed_time": "1:44:38", "remaining_time": "0:18:09"}
+{"current_steps": 880, "total_steps": 1021, "loss": 1.0722, "lr": 5.788520597878477e-07, "epoch": 0.8612674333251774, "percentage": 86.19, "elapsed_time": "1:45:48", "remaining_time": "0:16:57"}
+{"current_steps": 890, "total_steps": 1021, "loss": 1.0721, "lr": 5.015386453917742e-07, "epoch": 0.8710545632493272, "percentage": 87.17, "elapsed_time": "1:46:57", "remaining_time": "0:15:44"}
+{"current_steps": 900, "total_steps": 1021, "loss": 1.0691, "lr": 4.29493112422007e-07, "epoch": 0.8808416931734768, "percentage": 88.15, "elapsed_time": "1:48:06", "remaining_time": "0:14:32"}
+{"current_steps": 910, "total_steps": 1021, "loss": 1.086, "lr": 3.627998291313939e-07, "epoch": 0.8906288230976266, "percentage": 89.13, "elapsed_time": "1:49:16", "remaining_time": "0:13:19"}
+{"current_steps": 920, "total_steps": 1021, "loss": 1.0739, "lr": 3.015368960704584e-07, "epoch": 0.9004159530217763, "percentage": 90.11, "elapsed_time": "1:50:28", "remaining_time": "0:12:07"}
+{"current_steps": 930, "total_steps": 1021, "loss": 1.0684, "lr": 2.4577605462847764e-07, "epoch": 0.9102030829459261, "percentage": 91.09, "elapsed_time": "1:51:39", "remaining_time": "0:10:55"}
+{"current_steps": 940, "total_steps": 1021, "loss": 1.0857, "lr": 1.9558260302139642e-07, "epoch": 0.9199902128700759, "percentage": 92.07, "elapsed_time": "1:52:50", "remaining_time": "0:09:43"}
+{"current_steps": 950, "total_steps": 1021, "loss": 1.0742, "lr": 1.510153198249531e-07, "epoch": 0.9297773427942256, "percentage": 93.05, "elapsed_time": "1:54:04", "remaining_time": "0:08:31"}
+{"current_steps": 960, "total_steps": 1021, "loss": 1.0909, "lr": 1.1212639514257829e-07, "epoch": 0.9395644727183753, "percentage": 94.03, "elapsed_time": "1:55:16", "remaining_time": "0:07:19"}
+{"current_steps": 970, "total_steps": 1021, "loss": 1.0675, "lr": 7.896136948865429e-08, "epoch": 0.949351602642525, "percentage": 95.0, "elapsed_time": "1:56:24", "remaining_time": "0:06:07"}
+{"current_steps": 980, "total_steps": 1021, "loss": 1.0865, "lr": 5.155908045872349e-08, "epoch": 0.9591387325666748, "percentage": 95.98, "elapsed_time": "1:57:40", "remaining_time": "0:04:55"}
+{"current_steps": 990, "total_steps": 1021, "loss": 1.0787, "lr": 2.995161724907658e-08, "epoch": 0.9689258624908246, "percentage": 96.96, "elapsed_time": "1:58:48", "remaining_time": "0:03:43"}
+{"current_steps": 1000, "total_steps": 1021, "loss": 1.0988, "lr": 1.4164283079001196e-08, "epoch": 0.9787129924149743, "percentage": 97.94, "elapsed_time": "1:59:59", "remaining_time": "0:02:31"}
+{"current_steps": 1010, "total_steps": 1021, "loss": 1.0825, "lr": 4.2155655596809455e-09, "epoch": 0.9885001223391241, "percentage": 98.92, "elapsed_time": "2:02:25", "remaining_time": "0:01:20"}
+{"current_steps": 1020, "total_steps": 1021, "loss": 1.0754, "lr": 1.1711504444733567e-10, "epoch": 0.9982872522632737, "percentage": 99.9, "elapsed_time": "2:03:37", "remaining_time": "0:00:07"}
+{"current_steps": 1021, "total_steps": 1021, "epoch": 0.9992659652556888, "percentage": 100.0, "elapsed_time": "2:05:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,757 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9992659652556888,
+  "eval_steps": 500,
+  "global_step": 1021,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009787129924149743,
+      "grad_norm": 3.160645008087158,
+      "learning_rate": 8.737864077669904e-07,
+      "loss": 1.6202,
+      "step": 10
+    },
+    {
+      "epoch": 0.019574259848299486,
+      "grad_norm": 1.8336282968521118,
+      "learning_rate": 1.8446601941747574e-06,
+      "loss": 1.5766,
+      "step": 20
+    },
+    {
+      "epoch": 0.029361389772449228,
+      "grad_norm": 1.5718436241149902,
+      "learning_rate": 2.8155339805825245e-06,
+      "loss": 1.4962,
+      "step": 30
+    },
+    {
+      "epoch": 0.03914851969659897,
+      "grad_norm": 1.2343661785125732,
+      "learning_rate": 3.7864077669902915e-06,
+      "loss": 1.3827,
+      "step": 40
+    },
+    {
+      "epoch": 0.048935649620748714,
+      "grad_norm": 1.0965512990951538,
+      "learning_rate": 4.7572815533980585e-06,
+      "loss": 1.3328,
+      "step": 50
+    },
+    {
+      "epoch": 0.058722779544898455,
+      "grad_norm": 1.0640696287155151,
+      "learning_rate": 5.728155339805825e-06,
+      "loss": 1.2826,
+      "step": 60
+    },
+    {
+      "epoch": 0.0685099094690482,
+      "grad_norm": 1.076289415359497,
+      "learning_rate": 6.6990291262135935e-06,
+      "loss": 1.234,
+      "step": 70
+    },
+    {
+      "epoch": 0.07829703939319795,
+      "grad_norm": 1.036766529083252,
+      "learning_rate": 7.66990291262136e-06,
+      "loss": 1.2398,
+      "step": 80
+    },
+    {
+      "epoch": 0.0880841693173477,
+      "grad_norm": 1.0808024406433105,
+      "learning_rate": 8.640776699029127e-06,
+      "loss": 1.2031,
+      "step": 90
+    },
+    {
+      "epoch": 0.09787129924149743,
+      "grad_norm": 1.1380928754806519,
+      "learning_rate": 9.611650485436894e-06,
+      "loss": 1.2039,
+      "step": 100
+    },
+    {
+      "epoch": 0.10765842916564718,
+      "grad_norm": 1.0566169023513794,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 1.1918,
+      "step": 110
+    },
+    {
+      "epoch": 0.11744555908979691,
+      "grad_norm": 1.080167293548584,
+      "learning_rate": 9.992506480404137e-06,
+      "loss": 1.1916,
+      "step": 120
+    },
+    {
+      "epoch": 0.12723268901394666,
+      "grad_norm": 1.0032321214675903,
+      "learning_rate": 9.980220534903889e-06,
+      "loss": 1.1654,
+      "step": 130
+    },
+    {
+      "epoch": 0.1370198189380964,
+      "grad_norm": 1.101294994354248,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 1.1627,
+      "step": 140
+    },
+    {
+      "epoch": 0.14680694886224616,
+      "grad_norm": 1.1083616018295288,
+      "learning_rate": 9.938173737671531e-06,
+      "loss": 1.1622,
+      "step": 150
+    },
+    {
+      "epoch": 0.1565940787863959,
+      "grad_norm": 0.9857867360115051,
+      "learning_rate": 9.908462124451152e-06,
+      "loss": 1.1588,
+      "step": 160
+    },
+    {
+      "epoch": 0.16638120871054562,
+      "grad_norm": 1.0299389362335205,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 1.1774,
+      "step": 170
+    },
+    {
+      "epoch": 0.1761683386346954,
+      "grad_norm": 1.0562578439712524,
+      "learning_rate": 9.831836395602164e-06,
+      "loss": 1.1632,
+      "step": 180
+    },
+    {
+      "epoch": 0.18595546855884512,
+      "grad_norm": 1.0918824672698975,
+      "learning_rate": 9.78501201182228e-06,
+      "loss": 1.1575,
+      "step": 190
+    },
+    {
+      "epoch": 0.19574259848299486,
+      "grad_norm": 0.9658213257789612,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 1.145,
+      "step": 200
+    },
+    {
+      "epoch": 0.20552972840714462,
+      "grad_norm": 0.9882791042327881,
+      "learning_rate": 9.674614307640368e-06,
+      "loss": 1.1595,
+      "step": 210
+    },
+    {
+      "epoch": 0.21531685833129435,
+      "grad_norm": 1.0786079168319702,
+      "learning_rate": 9.611170267445401e-06,
+      "loss": 1.1383,
+      "step": 220
+    },
+    {
+      "epoch": 0.2251039882554441,
+      "grad_norm": 1.0685032606124878,
+      "learning_rate": 9.542326359097619e-06,
+      "loss": 1.1329,
+      "step": 230
+    },
+    {
+      "epoch": 0.23489111817959382,
+      "grad_norm": 1.0679073333740234,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 1.1323,
+      "step": 240
+    },
+    {
+      "epoch": 0.24467824810374358,
+      "grad_norm": 0.9797915816307068,
+      "learning_rate": 9.388767643081109e-06,
+      "loss": 1.1332,
+      "step": 250
+    },
+    {
+      "epoch": 0.2544653780278933,
+      "grad_norm": 1.055120587348938,
+      "learning_rate": 9.30423265892184e-06,
+      "loss": 1.1301,
+      "step": 260
+    },
+    {
+      "epoch": 0.2642525079520431,
+      "grad_norm": 1.034970998764038,
+      "learning_rate": 9.214657243048021e-06,
+      "loss": 1.1483,
+      "step": 270
+    },
+    {
+      "epoch": 0.2740396378761928,
+      "grad_norm": 1.105406641960144,
+      "learning_rate": 9.120146291919206e-06,
+      "loss": 1.1249,
+      "step": 280
+    },
+    {
+      "epoch": 0.28382676780034255,
+      "grad_norm": 0.9189131259918213,
+      "learning_rate": 9.020810481707709e-06,
+      "loss": 1.1385,
+      "step": 290
+    },
+    {
+      "epoch": 0.2936138977244923,
+      "grad_norm": 1.0855603218078613,
+      "learning_rate": 8.916766138692303e-06,
+      "loss": 1.1326,
+      "step": 300
+    },
+    {
+      "epoch": 0.303401027648642,
+      "grad_norm": 0.9882815480232239,
+      "learning_rate": 8.808135103035407e-06,
+      "loss": 1.1223,
+      "step": 310
+    },
+    {
+      "epoch": 0.3131881575727918,
+      "grad_norm": 0.9927927255630493,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 1.1314,
+      "step": 320
+    },
+    {
+      "epoch": 0.32297528749694154,
+      "grad_norm": 1.0153377056121826,
+      "learning_rate": 8.577627021496413e-06,
+      "loss": 1.1254,
+      "step": 330
+    },
+    {
+      "epoch": 0.33276241742109125,
+      "grad_norm": 0.9959344267845154,
+      "learning_rate": 8.456019909964224e-06,
+      "loss": 1.1115,
+      "step": 340
+    },
+    {
+      "epoch": 0.342549547345241,
+      "grad_norm": 1.044042706489563,
+      "learning_rate": 8.330365658386252e-06,
+      "loss": 1.142,
+      "step": 350
+    },
+    {
+      "epoch": 0.3523366772693908,
+      "grad_norm": 0.9094734787940979,
+      "learning_rate": 8.200811413007808e-06,
+      "loss": 1.1254,
+      "step": 360
+    },
+    {
+      "epoch": 0.3621238071935405,
+      "grad_norm": 1.0200663805007935,
+      "learning_rate": 8.06750888712576e-06,
+      "loss": 1.127,
+      "step": 370
+    },
+    {
+      "epoch": 0.37191093711769024,
+      "grad_norm": 1.0179405212402344,
+      "learning_rate": 7.930614183426074e-06,
+      "loss": 1.0985,
+      "step": 380
+    },
+    {
+      "epoch": 0.38169806704184,
+      "grad_norm": 0.9346506595611572,
+      "learning_rate": 7.790287611181217e-06,
+      "loss": 1.1061,
+      "step": 390
+    },
+    {
+      "epoch": 0.3914851969659897,
+      "grad_norm": 0.9131274223327637,
+      "learning_rate": 7.646693498521472e-06,
+      "loss": 1.1178,
+      "step": 400
+    },
+    {
+      "epoch": 0.4012723268901395,
+      "grad_norm": 1.1208817958831787,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1076,
+      "step": 410
+    },
+    {
+      "epoch": 0.41105945681428924,
+      "grad_norm": 0.9498858451843262,
+      "learning_rate": 7.35037889967702e-06,
+      "loss": 1.123,
+      "step": 420
+    },
+    {
+      "epoch": 0.42084658673843894,
+      "grad_norm": 0.9704530239105225,
+      "learning_rate": 7.19800540995367e-06,
+      "loss": 1.1142,
+      "step": 430
+    },
+    {
+      "epoch": 0.4306337166625887,
+      "grad_norm": 1.083723545074463,
+      "learning_rate": 7.043057966391158e-06,
+      "loss": 1.1068,
+      "step": 440
+    },
+    {
+      "epoch": 0.4404208465867384,
+      "grad_norm": 0.959192156791687,
+      "learning_rate": 6.885718018755448e-06,
+      "loss": 1.1024,
+      "step": 450
+    },
+    {
+      "epoch": 0.4502079765108882,
+      "grad_norm": 0.9829457402229309,
+      "learning_rate": 6.7261698185322e-06,
+      "loss": 1.0918,
+      "step": 460
+    },
+    {
+      "epoch": 0.45999510643503794,
+      "grad_norm": 0.9769061207771301,
+      "learning_rate": 6.5646002031607726e-06,
+      "loss": 1.1092,
+      "step": 470
+    },
+    {
+      "epoch": 0.46978223635918764,
+      "grad_norm": 0.9248567223548889,
+      "learning_rate": 6.401198377239979e-06,
+      "loss": 1.1096,
+      "step": 480
+    },
+    {
+      "epoch": 0.4795693662833374,
+      "grad_norm": 1.0321615934371948,
+      "learning_rate": 6.236155690961795e-06,
+      "loss": 1.1118,
+      "step": 490
+    },
+    {
+      "epoch": 0.48935649620748717,
+      "grad_norm": 0.9511229395866394,
+      "learning_rate": 6.0696654160324875e-06,
+      "loss": 1.0969,
+      "step": 500
+    },
+    {
+      "epoch": 0.4991436261316369,
+      "grad_norm": 0.9163072109222412,
+      "learning_rate": 5.901922519343586e-06,
+      "loss": 1.107,
+      "step": 510
+    },
+    {
+      "epoch": 0.5089307560557866,
+      "grad_norm": 0.9588350653648376,
+      "learning_rate": 5.733123434657704e-06,
+      "loss": 1.1008,
+      "step": 520
+    },
+    {
+      "epoch": 0.5187178859799364,
+      "grad_norm": 0.9725273251533508,
+      "learning_rate": 5.5634658325766066e-06,
+      "loss": 1.1122,
+      "step": 530
+    },
+    {
+      "epoch": 0.5285050159040862,
+      "grad_norm": 0.954433798789978,
+      "learning_rate": 5.393148389060893e-06,
+      "loss": 1.1052,
+      "step": 540
+    },
+    {
+      "epoch": 0.5382921458282359,
+      "grad_norm": 1.1059950590133667,
+      "learning_rate": 5.222370552772353e-06,
+      "loss": 1.1014,
+      "step": 550
+    },
+    {
+      "epoch": 0.5480792757523856,
+      "grad_norm": 0.9268523454666138,
+      "learning_rate": 5.05133231151145e-06,
+      "loss": 1.0981,
+      "step": 560
+    },
+    {
+      "epoch": 0.5578664056765353,
+      "grad_norm": 0.9672321677207947,
+      "learning_rate": 4.880233958023486e-06,
+      "loss": 1.1086,
+      "step": 570
+    },
+    {
+      "epoch": 0.5676535356006851,
+      "grad_norm": 1.0383234024047852,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 1.0938,
+      "step": 580
+    },
+    {
+      "epoch": 0.5774406655248349,
+      "grad_norm": 0.9663616418838501,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 1.1038,
+      "step": 590
+    },
+    {
+      "epoch": 0.5872277954489846,
+      "grad_norm": 0.9746555685997009,
+      "learning_rate": 4.368580799950133e-06,
+      "loss": 1.0784,
+      "step": 600
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.8926970362663269,
+      "learning_rate": 4.199242814811807e-06,
+      "loss": 1.1028,
+      "step": 610
+    },
+    {
+      "epoch": 0.606802055297284,
+      "grad_norm": 0.9124487638473511,
+      "learning_rate": 4.03084254894465e-06,
+      "loss": 1.0938,
+      "step": 620
+    },
+    {
+      "epoch": 0.6165891852214338,
+      "grad_norm": 0.9407256841659546,
+      "learning_rate": 3.863577205917356e-06,
+      "loss": 1.0917,
+      "step": 630
+    },
+    {
+      "epoch": 0.6263763151455836,
+      "grad_norm": 0.9204623103141785,
+      "learning_rate": 3.6976426602577565e-06,
+      "loss": 1.0837,
+      "step": 640
+    },
+    {
+      "epoch": 0.6361634450697333,
+      "grad_norm": 0.9785788059234619,
+      "learning_rate": 3.5332332280757706e-06,
+      "loss": 1.0964,
+      "step": 650
+    },
+    {
+      "epoch": 0.6459505749938831,
+      "grad_norm": 0.9679555892944336,
+      "learning_rate": 3.3705414395113354e-06,
+      "loss": 1.0897,
+      "step": 660
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.8785240054130554,
+      "learning_rate": 3.2097578132737716e-06,
+      "loss": 1.0986,
+      "step": 670
+    },
+    {
+      "epoch": 0.6655248348421825,
+      "grad_norm": 0.9295753240585327,
+      "learning_rate": 3.0510706335366034e-06,
+      "loss": 1.0877,
+      "step": 680
+    },
+    {
+      "epoch": 0.6753119647663323,
+      "grad_norm": 0.8944317102432251,
+      "learning_rate": 2.8946657294491452e-06,
+      "loss": 1.0941,
+      "step": 690
+    },
+    {
+      "epoch": 0.685099094690482,
+      "grad_norm": 0.9147707223892212,
+      "learning_rate": 2.740726257522987e-06,
+      "loss": 1.0857,
+      "step": 700
+    },
+    {
+      "epoch": 0.6948862246146318,
+      "grad_norm": 0.889441967010498,
+      "learning_rate": 2.5894324871482557e-06,
+      "loss": 1.0781,
+      "step": 710
+    },
+    {
+      "epoch": 0.7046733545387815,
+      "grad_norm": 0.8948488235473633,
+      "learning_rate": 2.4409615894908407e-06,
+      "loss": 1.0713,
+      "step": 720
+    },
+    {
+      "epoch": 0.7144604844629312,
+      "grad_norm": 0.881840169429779,
+      "learning_rate": 2.2954874300177197e-06,
+      "loss": 1.0765,
+      "step": 730
+    },
+    {
+      "epoch": 0.724247614387081,
+      "grad_norm": 0.9054113030433655,
+      "learning_rate": 2.1531803648934333e-06,
+      "loss": 1.0835,
+      "step": 740
+    },
+    {
+      "epoch": 0.7340347443112307,
+      "grad_norm": 0.8451863527297974,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 1.0836,
+      "step": 750
+    },
+    {
+      "epoch": 0.7438218742353805,
+      "grad_norm": 0.8607450127601624,
+      "learning_rate": 1.8787302032164168e-06,
+      "loss": 1.0816,
+      "step": 760
+    },
+    {
+      "epoch": 0.7536090041595302,
+      "grad_norm": 0.8773781657218933,
+      "learning_rate": 1.746908498978791e-06,
+      "loss": 1.0807,
+      "step": 770
+    },
+    {
+      "epoch": 0.76339613408368,
+      "grad_norm": 0.9455496668815613,
+      "learning_rate": 1.6188962973567068e-06,
+      "loss": 1.0828,
+      "step": 780
+    },
+    {
+      "epoch": 0.7731832640078297,
+      "grad_norm": 0.9180036783218384,
+      "learning_rate": 1.4948435058510036e-06,
+      "loss": 1.1013,
+      "step": 790
+    },
+    {
+      "epoch": 0.7829703939319794,
+      "grad_norm": 0.900719165802002,
+      "learning_rate": 1.374895395332037e-06,
+      "loss": 1.07,
+      "step": 800
+    },
+    {
+      "epoch": 0.7927575238561292,
+      "grad_norm": 0.8657832145690918,
+      "learning_rate": 1.259192429921584e-06,
+      "loss": 1.0796,
+      "step": 810
+    },
+    {
+      "epoch": 0.802544653780279,
+      "grad_norm": 1.0004676580429077,
+      "learning_rate": 1.1478701025036359e-06,
+      "loss": 1.1017,
+      "step": 820
+    },
+    {
+      "epoch": 0.8123317837044287,
+      "grad_norm": 0.9102425575256348,
+      "learning_rate": 1.0410587760567104e-06,
+      "loss": 1.0805,
+      "step": 830
+    },
+    {
+      "epoch": 0.8221189136285785,
+      "grad_norm": 0.8790053129196167,
+      "learning_rate": 9.388835309934985e-07,
+      "loss": 1.068,
+      "step": 840
+    },
+    {
+      "epoch": 0.8319060435527281,
+      "grad_norm": 0.8961747288703918,
+      "learning_rate": 8.414640186866063e-07,
+      "loss": 1.0832,
+      "step": 850
+    },
+    {
+      "epoch": 0.8416931734768779,
+      "grad_norm": 0.874332845211029,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 1.0858,
+      "step": 860
+    },
+    {
+      "epoch": 0.8514803034010276,
+      "grad_norm": 0.9413198828697205,
+      "learning_rate": 6.613428184537235e-07,
+      "loss": 1.0938,
+      "step": 870
+    },
+    {
+      "epoch": 0.8612674333251774,
+      "grad_norm": 0.8453653454780579,
+      "learning_rate": 5.788520597878477e-07,
+      "loss": 1.0722,
+      "step": 880
+    },
+    {
+      "epoch": 0.8710545632493272,
+      "grad_norm": 0.880970299243927,
+      "learning_rate": 5.015386453917742e-07,
+      "loss": 1.0721,
+      "step": 890
+    },
+    {
+      "epoch": 0.8808416931734768,
+      "grad_norm": 0.8894344568252563,
+      "learning_rate": 4.29493112422007e-07,
+      "loss": 1.0691,
+      "step": 900
+    },
+    {
+      "epoch": 0.8906288230976266,
+      "grad_norm": 0.8694501519203186,
+      "learning_rate": 3.627998291313939e-07,
+      "loss": 1.086,
+      "step": 910
+    },
+    {
+      "epoch": 0.9004159530217763,
+      "grad_norm": 0.8791433572769165,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 1.0739,
+      "step": 920
+    },
+    {
+      "epoch": 0.9102030829459261,
+      "grad_norm": 0.9409059882164001,
+      "learning_rate": 2.4577605462847764e-07,
+      "loss": 1.0684,
+      "step": 930
+    },
+    {
+      "epoch": 0.9199902128700759,
+      "grad_norm": 0.9185978770256042,
+      "learning_rate": 1.9558260302139642e-07,
+      "loss": 1.0857,
+      "step": 940
+    },
+    {
+      "epoch": 0.9297773427942256,
+      "grad_norm": 0.8623930811882019,
+      "learning_rate": 1.510153198249531e-07,
+      "loss": 1.0742,
+      "step": 950
+    },
+    {
+      "epoch": 0.9395644727183753,
+      "grad_norm": 0.9032447338104248,
+      "learning_rate": 1.1212639514257829e-07,
+      "loss": 1.0909,
+      "step": 960
+    },
+    {
+      "epoch": 0.949351602642525,
+      "grad_norm": 0.9127726554870605,
+      "learning_rate": 7.896136948865429e-08,
+      "loss": 1.0675,
+      "step": 970
+    },
+    {
+      "epoch": 0.9591387325666748,
+      "grad_norm": 0.8940075635910034,
+      "learning_rate": 5.155908045872349e-08,
+      "loss": 1.0865,
+      "step": 980
+    },
+    {
+      "epoch": 0.9689258624908246,
+      "grad_norm": 0.8495497703552246,
+      "learning_rate": 2.995161724907658e-08,
+      "loss": 1.0787,
+      "step": 990
+    },
+    {
+      "epoch": 0.9787129924149743,
+      "grad_norm": 0.8723552227020264,
+      "learning_rate": 1.4164283079001196e-08,
+      "loss": 1.0988,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9885001223391241,
+      "grad_norm": 0.8567104935646057,
+      "learning_rate": 4.2155655596809455e-09,
+      "loss": 1.0825,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9982872522632737,
+      "grad_norm": 0.8691814541816711,
+      "learning_rate": 1.1711504444733567e-10,
+      "loss": 1.0754,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9992659652556888,
+      "step": 1021,
+      "total_flos": 2.8896472925732864e+18,
+      "train_loss": 1.1314670071662583,
+      "train_runtime": 7504.4933,
+      "train_samples_per_second": 17.424,
+      "train_steps_per_second": 0.136
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1021,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8896472925732864e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cb87b7ccd3f39914ae96409d8cac2350e17a6979a98173a6941b5dea478e86
+size 7480