holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu: holdout, DiT+TextDecoder, scratch-2B: 88.7%

.gitattributes

@@ -38,3 +38,4 @@ noemit-2x2/arith_multidigit_noemit_puremse_mseDITandTE_pretrained_10ep_1gpu/proc
 seeds/arith_multidigit_noemit_puremse_mseDITandTE_scratch2B_eb2lr1e4_10ep_1gpu_seed44/processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seeds/arith_multidigit_noemit_puremse_mseDITandTE_scratch2B_eb2lr1e4_10ep_1gpu_seed45/processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 t2i/qwenimage_t2i_arith_multidigit_noemit_MSEonly_trainMMDiTandTE_ViTfrozen_embedfrozen_scratchDiT2B_10ep_1gpu/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/meta.json

@@ -0,0 +1 @@
+{"global_step": 45000, "freeze_te": false}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/processor/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/processor/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7aabe7a3b44651592a99607bb33066e6965260336be9218cccd53af161491d
+size 11422060

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/processor/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/text_encoder/config.json

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen2_5_vl",
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_theta": 1000000.0,
+      "rope_type": "default",
+      "type": "default"
+    },
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "bfloat16",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl_vision",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654
+}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/text_encoder/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": "5.8.0"
+}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6b0aaad0573eb18e1aaa47063f393dbb866916afde79ffaf88b61fc0633a02
+size 16584415608

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/transformer/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "QwenImageTransformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    16,
+    56,
+    56
+  ],
+  "guidance_embeds": false,
+  "in_channels": 64,
+  "joint_attention_dim": 3584,
+  "num_attention_heads": 12,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "use_additional_t_cond": false,
+  "use_layer3d_rope": false,
+  "zero_cond_t": false
+}

holdout/arith_multidigit_holdout_noemit_MSEonly_trainMMDiTandTextDecoder_ViTfrozen_embedfrozen_scratch2B_10ep_1gpu/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1232b6219345866b6b440e27cc725db4934e078dcf238de1d70498f4cc6e4a80
+size 4105561640