lyunee commited on 7 days ago

Commit

aa4f2f3

verified ·

1 Parent(s): 43b8bb6

Upload continuous evaluation checkpoints, batch 18

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +3 -0
continuous/qwen3/pe_lang_l14_448/finetune/config.json +89 -0
continuous/qwen3/pe_lang_l14_448/finetune/generation_config.json +12 -0
continuous/qwen3/pe_lang_l14_448/finetune/merges.txt +0 -0
continuous/qwen3/pe_lang_l14_448/finetune/model.safetensors +3 -0
continuous/qwen3/pe_lang_l14_448/finetune/special_tokens_map.json +31 -0
continuous/qwen3/pe_lang_l14_448/finetune/tokenizer.json +3 -0
continuous/qwen3/pe_lang_l14_448/finetune/tokenizer_config.json +240 -0
continuous/qwen3/pe_lang_l14_448/finetune/trainer_state.json +1856 -0
continuous/qwen3/pe_lang_l14_448/finetune/training_args.bin +3 -0
continuous/qwen3/pe_lang_l14_448/finetune/vocab.json +0 -0
continuous/qwen3/pe_lang_l14_448/pretrain/config.json +89 -0
continuous/qwen3/pe_lang_l14_448/pretrain/mm_projector.bin +3 -0
continuous/qwen3/pe_lang_l14_448/pretrain/trainer_state.json +421 -0
continuous/qwen3/pixio_vitb16/finetune/added_tokens.json +28 -0
continuous/qwen3/pixio_vitb16/finetune/chat_template.jinja +89 -0
continuous/qwen3/pixio_vitb16/finetune/config.json +89 -0
continuous/qwen3/pixio_vitb16/finetune/generation_config.json +12 -0
continuous/qwen3/pixio_vitb16/finetune/merges.txt +0 -0
continuous/qwen3/pixio_vitb16/finetune/model.safetensors +3 -0
continuous/qwen3/pixio_vitb16/finetune/special_tokens_map.json +31 -0
continuous/qwen3/pixio_vitb16/finetune/tokenizer.json +3 -0
continuous/qwen3/pixio_vitb16/finetune/tokenizer_config.json +240 -0
continuous/qwen3/pixio_vitb16/finetune/trainer_state.json +1856 -0
continuous/qwen3/pixio_vitb16/finetune/training_args.bin +3 -0
continuous/qwen3/pixio_vitb16/finetune/vocab.json +0 -0
continuous/qwen3/pixio_vitb16/pretrain/config.json +89 -0
continuous/qwen3/pixio_vitb16/pretrain/mm_projector.bin +3 -0
continuous/qwen3/pixio_vitb16/pretrain/trainer_state.json +421 -0
continuous/qwen3/pixio_vith16/finetune/added_tokens.json +28 -0
continuous/qwen3/pixio_vith16/finetune/chat_template.jinja +89 -0
continuous/qwen3/pixio_vith16/finetune/config.json +89 -0
continuous/qwen3/pixio_vith16/finetune/generation_config.json +12 -0
continuous/qwen3/pixio_vith16/finetune/merges.txt +0 -0
continuous/qwen3/pixio_vith16/finetune/model-00001-of-00002.safetensors +3 -0
continuous/qwen3/pixio_vith16/finetune/model-00002-of-00002.safetensors +3 -0
continuous/qwen3/pixio_vith16/finetune/model.safetensors.index.json +713 -0
continuous/qwen3/pixio_vith16/finetune/special_tokens_map.json +31 -0
continuous/qwen3/pixio_vith16/finetune/tokenizer.json +3 -0
continuous/qwen3/pixio_vith16/finetune/tokenizer_config.json +240 -0
continuous/qwen3/pixio_vith16/finetune/trainer_state.json +1856 -0
continuous/qwen3/pixio_vith16/finetune/training_args.bin +3 -0
continuous/qwen3/pixio_vith16/finetune/vocab.json +0 -0
continuous/qwen3/pixio_vith16/pretrain/config.json +89 -0
continuous/qwen3/pixio_vith16/pretrain/mm_projector.bin +3 -0
continuous/qwen3/pixio_vith16/pretrain/trainer_state.json +421 -0
continuous/qwen3/pixio_vitl16/finetune/added_tokens.json +28 -0
continuous/qwen3/pixio_vitl16/finetune/chat_template.jinja +89 -0
continuous/qwen3/pixio_vitl16/finetune/config.json +89 -0
continuous/qwen3/pixio_vitl16/finetune/generation_config.json +12 -0

.gitattributes CHANGED Viewed

@@ -152,3 +152,6 @@ continuous/qwen3/mc2_s16_224_mt5/finetune/tokenizer.json filter=lfs diff=lfs mer
 continuous/qwen3/mc2_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/pe_core_b16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/pe_core_g14_448/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text

 continuous/qwen3/mc2_s16_384/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/pe_core_b16_224/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 continuous/qwen3/pe_core_g14_448/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/pe_lang_l14_448/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/pixio_vitb16/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+continuous/qwen3/pixio_vith16/finetune/tokenizer.json filter=lfs diff=lfs merge=lfs -text

continuous/qwen3/pe_lang_l14_448/finetune/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1024,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pe",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Lang-L14-448/PE-Lang-L14-448.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/pe_lang_l14_448/finetune/generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

continuous/qwen3/pe_lang_l14_448/finetune/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pe_lang_l14_448/finetune/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9767843ca0267ee4b2d885ed08cacf64ac54fc58625f94091d2ed1213a456601
+size 4671575880

continuous/qwen3/pe_lang_l14_448/finetune/special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

continuous/qwen3/pe_lang_l14_448/finetune/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/pe_lang_l14_448/finetune/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,240 @@

+{
+  "add_bos_token": false,
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/pe_lang_l14_448/finetune/trainer_state.json ADDED Viewed

	@@ -0,0 +1,1856 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 8.983656883239746,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.2524,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 3.613579750061035,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.8703,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 2.4462645053863525,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.5431,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 0.7268947958946228,
+      "learning_rate": 5e-06,
+      "loss": 1.2055,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.5148277282714844,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0918,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.287834107875824,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 1.0103,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.2765061855316162,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9682,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.20728878676891327,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.966,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.21578505635261536,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.9389,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.18091362714767456,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.9139,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.19271612167358398,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8899,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.16553795337677002,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8976,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.19260285794734955,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8901,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.18735480308532715,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8855,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.18936938047409058,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8808,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.17896144092082977,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8752,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.14387047290802002,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.873,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.15775512158870697,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8975,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.17344997823238373,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8961,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.18243922293186188,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8763,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.15731239318847656,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8806,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.15631213784217834,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8596,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.1860397607088089,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.8661,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.18715539574623108,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.8518,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.17203088104724884,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8695,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.17871658504009247,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8729,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.1545071005821228,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8564,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.16246885061264038,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8615,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.15942038595676422,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8723,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.14702153205871582,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.8331,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.14975108206272125,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.8496,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.16052740812301636,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.845,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.14850488305091858,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.8471,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.16886191070079803,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8561,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.16768817603588104,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8623,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.15061359107494354,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.8448,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.16633588075637817,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8697,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.1494802087545395,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.8376,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.1527533382177353,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.8436,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.14311324059963226,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.8452,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.14049780368804932,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.8248,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.14435116946697235,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.8412,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.1456582248210907,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.8327,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.1607123613357544,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.8345,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.15344735980033875,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.8166,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.1607331484556198,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.8322,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.16661641001701355,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.8387,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.1424146443605423,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.8313,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.1448192298412323,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.8216,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.13636605441570282,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.8223,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.16728368401527405,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.8094,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.17045363783836365,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.851,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.1683395802974701,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.8167,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.16305501759052277,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.8358,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.1355074644088745,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.8389,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.1515197902917862,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.8409,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.166497141122818,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.8507,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.1550341248512268,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.8251,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.15957126021385193,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.8435,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.16718445718288422,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.8381,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.15419799089431763,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8473,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.15386518836021423,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.8389,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.15561215579509735,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8457,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.148520827293396,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.8384,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.13988392055034637,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7928,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.16009320318698883,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.8241,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.1600862443447113,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.8372,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.14990198612213135,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.8129,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.1402786821126938,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.8272,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.1427982598543167,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.833,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.14239689707756042,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.8161,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.13763000071048737,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.8193,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.16037723422050476,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.83,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.15452855825424194,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.812,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.14178051054477692,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.8115,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.151132270693779,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.8033,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.14493459463119507,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.822,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.1519833356142044,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.8142,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.15966126322746277,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.8044,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.15894798934459686,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.8301,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.14962676167488098,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.8165,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.13465532660484314,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.8177,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.1556989550590515,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.8059,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.16687655448913574,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.811,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.13974909484386444,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.8103,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.14594179391860962,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.8037,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.14746487140655518,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.8018,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.13242001831531525,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.8074,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.1415431648492813,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.797,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.14291822910308838,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.8034,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.16204380989074707,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.8034,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.1427868902683258,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7894,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.158547505736351,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7841,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.1535254567861557,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.8204,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.1409526765346527,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.8316,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.1686495840549469,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.8083,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.15082965791225433,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7898,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.13587555289268494,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7972,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.16878525912761688,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7867,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.15033861994743347,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.8084,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.1568111777305603,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.8268,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.1527828723192215,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.8053,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.1450463831424713,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.8156,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.1613481044769287,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.8134,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.12989093363285065,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.8046,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.16792036592960358,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.8093,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.1502060890197754,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7915,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.14412380754947662,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.8233,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.15967492759227753,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.7982,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.16143138706684113,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.8196,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.1518375128507614,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.8117,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.15355651080608368,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.807,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.14946557581424713,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7959,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.13937361538410187,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.8011,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.133304163813591,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7963,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.15985776484012604,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.8221,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.1524534821510315,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.8304,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.13211843371391296,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.8016,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.15448518097400665,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7851,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.15138569474220276,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7903,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.14866697788238525,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.796,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.15434804558753967,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.8117,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.14212892949581146,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.8127,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.14137737452983856,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.7906,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.14186714589595795,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7896,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.15466487407684326,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7886,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.16447831690311432,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7806,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.15393772721290588,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7853,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.14493580162525177,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.8066,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.15177667140960693,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.7988,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.14839522540569305,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.8132,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.17136250436306,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7908,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.1678478866815567,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7933,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.15124930441379547,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.7972,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.1495599001646042,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.786,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.1671813577413559,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.8009,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.15661947429180145,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.8093,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.14204415678977966,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.8109,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.14937324821949005,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7875,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.17098397016525269,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.792,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.15240785479545593,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.8078,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.15286804735660553,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7949,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.17646850645542145,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.8041,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.15596939623355865,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.8069,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.17235246300697327,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7912,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.14095816016197205,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7936,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.14955677092075348,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7919,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.15368784964084625,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7909,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.15427203476428986,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.7953,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.1471899151802063,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.8028,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.14893831312656403,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.7932,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.154947429895401,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.8019,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.184886634349823,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.8026,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.1417616307735443,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.8085,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.15651361644268036,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.8018,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.1635960340499878,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.8166,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.1637229472398758,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.8018,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.1459609717130661,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.8023,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.12913350760936737,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.8003,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.14453399181365967,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7832,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.14411425590515137,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7667,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.1414259970188141,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7692,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.14177753031253815,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.8049,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.12948943674564362,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7869,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.15213561058044434,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.7973,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.15236367285251617,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7825,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.16562288999557495,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.8038,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.15325389802455902,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.7926,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.1592833399772644,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7811,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.14350610971450806,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7772,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.16486018896102905,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.7967,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.14875562489032745,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7878,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.14021459221839905,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.7944,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.14696872234344482,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.7969,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.157878577709198,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7909,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.13698357343673706,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7783,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.15590886771678925,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.8175,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.15500202775001526,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.8022,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.1430884748697281,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.814,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.14152120053768158,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7803,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.14661620557308197,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7749,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.14184923470020294,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.8003,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.15738268196582794,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7939,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.16089344024658203,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7922,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.15473903715610504,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.8014,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.14782410860061646,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.7978,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.15410199761390686,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7939,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.14905719459056854,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.7968,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.140086367726326,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7844,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.16245412826538086,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7924,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.1363338977098465,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7945,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.14895491302013397,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7835,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.15701377391815186,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.8023,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.15383070707321167,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.8113,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.14835937321186066,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.7966,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.1531568318605423,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.8127,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.14763982594013214,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.8051,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.15567347407341003,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.7929,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.16552627086639404,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.7944,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.13748575747013092,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7923,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.13749653100967407,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7905,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.14274956285953522,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7789,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.14960098266601562,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7694,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.1558050662279129,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7863,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.1374468058347702,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7899,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.13421845436096191,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7756,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.17204496264457703,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.7896,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.14076612889766693,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7703,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.14668774604797363,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.7965,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.149245485663414,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.7891,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.14892755448818207,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.7987,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.14928607642650604,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.7979,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.15351924300193787,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7849,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.14545957744121552,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7966,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.1637723445892334,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7818,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.13823632895946503,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.796,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.143104687333107,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.8003,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.14211294054985046,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7878,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.16701310873031616,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.8007,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.149369478225708,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.782,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.17100262641906738,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7699,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.14083322882652283,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.7935,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.15880805253982544,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7836,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.14443498849868774,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.8018,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.14928892254829407,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7869,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.158816859126091,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7752,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.13694262504577637,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7825,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.1464136242866516,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.7933,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.1486819088459015,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.7998,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.14810587465763092,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7807,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.14018933475017548,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.7825,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.13893163204193115,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.7927,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.14829111099243164,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.8029,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.14471571147441864,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.7953,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.14410720765590668,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.774,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.14064079523086548,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7938,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.14978598058223724,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7774,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.1490211933851242,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7834,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.14105632901191711,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.7997,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.16041439771652222,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.7908,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.14502812922000885,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7803,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.13531196117401123,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.8041,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.1463036686182022,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.8012,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.16597026586532593,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7888,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.15845650434494019,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7888,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.15593385696411133,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.8059,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.14426776766777039,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.7923,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.15435950458049774,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.788,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.16449430584907532,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.79,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.15000708401203156,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7801,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.14870676398277283,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7789,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.13646729290485382,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.7935,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.15419462323188782,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7823,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.1332712173461914,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7873,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.14288438856601715,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.7983,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.13352099061012268,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.7775,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.1485169380903244,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7808,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.12827730178833008,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7704,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.13946734368801117,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.7948,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 3.402368232412152e+18,
+      "train_loss": 0.8272731492369736,
+      "train_runtime": 20228.8011,
+      "train_samples_per_second": 32.869,
+      "train_steps_per_second": 0.128
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 332174164,
+  "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": 3.402368232412152e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pe_lang_l14_448/finetune/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c2fa4dcd5b69f5194cab70a85c9c08ed9dfb08ec86d6647ba6765eb909eb28
+size 6264

continuous/qwen3/pe_lang_l14_448/finetune/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pe_lang_l14_448/pretrain/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1024,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pe",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pe/PE-Lang-L14-448/PE-Lang-L14-448.pt",
+  "vocab_size": 151936
+}

continuous/qwen3/pe_lang_l14_448/pretrain/mm_projector.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40ce855d06a3a3401416bdbe0afd70a13b11b1c3772ff9339f32bf0080e1fefb
+size 25184312

continuous/qwen3/pe_lang_l14_448/pretrain/trainer_state.json ADDED Viewed

	@@ -0,0 +1,421 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 1.7847304344177246,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 9.7064,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.702887773513794,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 6.3277,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.14399047195911407,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 5.3892,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.08835718780755997,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 5.0182,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.05830550193786621,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.8738,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.04404463246464729,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.8067,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.04485964775085449,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.7555,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.05894707143306732,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.7246,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.06919288635253906,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.6891,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.12855830788612366,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.6722,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.09686558693647385,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.6403,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.1343153417110443,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.6322,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.12495464086532593,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.6443,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.06237492337822914,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.6031,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.05899127200245857,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.5852,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.06902807950973511,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.5629,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.0747721940279007,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.5485,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.10747170448303223,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.5329,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.05314281955361366,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.5275,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.0621262788772583,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.4995,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.07969923317432404,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.4919,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.06255118548870087,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.4987,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.08356881886720657,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.4966,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.09230270981788635,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.4834,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.08239135146141052,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.462,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.08882539719343185,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.4731,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0829402431845665,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.4501,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07304266840219498,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.4436,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.0577813945710659,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.428,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.07081466168165207,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.4228,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.05602002143859863,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.4355,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.07421141117811203,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.4282,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.05809858813881874,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.405,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.06882057338953018,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.4029,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.05863144248723984,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.4123,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.07516765594482422,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.4148,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.0667661726474762,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.3955,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.05464077368378639,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.4102,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.07743982970714569,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.3941,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.04599236696958542,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.3913,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.07145291566848755,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.3911,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.07556144893169403,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.3829,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.05379655957221985,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.3858,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08739788085222244,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.3939,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.05930650606751442,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.3878,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.04721808433532715,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.3756,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.06266219913959503,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.3657,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.04508576542139053,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.3753,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.04325716197490692,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.377,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.044036805629730225,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.3878,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.04276112839579582,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.3772,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.04170047864317894,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.3698,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.041936613619327545,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.3687,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.03956892341375351,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.377,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 3.13496508039168e+17,
+      "train_loss": 4.642065475183889,
+      "train_runtime": 6623.0297,
+      "train_samples_per_second": 84.271,
+      "train_steps_per_second": 0.082
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 30606752,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.13496508039168e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pixio_vitb16/finetune/added_tokens.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

continuous/qwen3/pixio_vitb16/finetune/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,89 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

continuous/qwen3/pixio_vitb16/finetune/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 768,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pixio",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pixio/pixio-vitb16/pixio_vitb16.pth",
+  "vocab_size": 151936
+}

continuous/qwen3/pixio_vitb16/finetune/generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

continuous/qwen3/pixio_vitb16/finetune/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pixio_vitb16/finetune/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:63fb8b3d07ecdc643481d66f2765c4ae4066e97f9d3050bdf2adc7f98712a59e
+size 4258331320

continuous/qwen3/pixio_vitb16/finetune/special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

continuous/qwen3/pixio_vitb16/finetune/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/pixio_vitb16/finetune/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,240 @@

+{
+  "add_bos_token": false,
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/pixio_vitb16/finetune/trainer_state.json ADDED Viewed

	@@ -0,0 +1,1856 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 17.68060302734375,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.3327,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 6.763516426086426,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.8277,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 4.657994270324707,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.5003,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 1.2598919868469238,
+      "learning_rate": 5e-06,
+      "loss": 1.1695,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.7579506635665894,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0575,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.4062078595161438,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9756,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.32609686255455017,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9289,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.3203873038291931,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.9267,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.2826254963874817,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.8967,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.25966522097587585,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8793,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.27168282866477966,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8605,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.259246826171875,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8706,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.2615548372268677,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8679,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.29294514656066895,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8616,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.29793018102645874,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8479,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.26547005772590637,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8526,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.2267991304397583,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.8534,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.2712092995643616,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.8815,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.2678167223930359,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8699,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.2901546359062195,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8601,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.2531008720397949,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8544,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.254721999168396,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8429,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.26093077659606934,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.8433,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.2536775767803192,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.8389,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.28770941495895386,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8549,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.24536338448524475,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8519,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.2603645622730255,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8395,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.2429904341697693,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8398,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.2442338466644287,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8573,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.22176821529865265,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.818,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.23526303470134735,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.8319,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.2411828190088272,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.8311,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.25521335005760193,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.8308,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.24798855185508728,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8431,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.2938927114009857,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8425,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.24247314035892487,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.8287,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.2553194463253021,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8557,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.2436641901731491,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.8152,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.2452945113182068,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.8237,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.24093957245349884,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.8269,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.24223986268043518,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.8156,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.2370109111070633,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.8325,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.25710612535476685,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.8213,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.25533875823020935,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.8191,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.24935272336006165,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.8093,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.25080952048301697,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.8132,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.2517920136451721,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.8227,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.24482044577598572,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.8213,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.23926234245300293,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.807,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.22755469381809235,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.812,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.23818184435367584,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.8073,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.24739371240139008,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.8368,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.26311957836151123,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.8087,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.25490066409111023,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.23210987448692322,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.8236,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.22884313762187958,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.8288,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.2631301283836365,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.8375,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.2533043622970581,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.8173,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.25856560468673706,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.8277,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.23148949444293976,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.818,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.26481306552886963,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8387,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.24255697429180145,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.8227,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.25688764452934265,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8393,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.23614230751991272,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.8277,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.2274189591407776,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7849,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.25287631154060364,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.8226,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.2752828001976013,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.8273,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.24243588745594025,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.7967,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.23265127837657928,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.8231,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.24528513848781586,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.8271,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.24511520564556122,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.8069,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.2261049449443817,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.8105,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.24922892451286316,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.8169,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.23807953298091888,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.8054,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.23167791962623596,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.8046,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.24645772576332092,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.7977,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.23630490899085999,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.8139,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.23189812898635864,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.8112,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.24076765775680542,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.7959,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.23168160021305084,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.8236,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.24762657284736633,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.8162,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.23476092517375946,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.8086,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.2474631518125534,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.7956,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.2565646469593048,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.8016,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.24150779843330383,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.8114,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.23489029705524445,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.7955,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.23720455169677734,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.8053,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.22098591923713684,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.7999,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.22981536388397217,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.7994,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.22085130214691162,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.8059,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.23693594336509705,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.7959,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.24260444939136505,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.7943,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.25961676239967346,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7799,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.2610072195529938,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.814,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.2434077113866806,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.8286,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.2553349733352661,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.8127,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.23417483270168304,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.7933,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.2321857064962387,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.7989,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.24445883929729462,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.786,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.2514292001724243,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.8013,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.23736682534217834,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.8238,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.24868854880332947,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.8155,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.235308438539505,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.8126,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.24320198595523834,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.804,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.22177654504776,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.7995,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.22746087610721588,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.8069,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.24132980406284332,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.7991,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.2302085906267166,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.823,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.28021368384361267,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.8026,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.25155308842658997,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.8169,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.24980299174785614,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.8126,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.2755599915981293,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.8089,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.24604345858097076,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7888,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.24408282339572906,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.8098,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.2347336858510971,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.7997,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.2727557122707367,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.8224,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.2336239516735077,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.8341,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.22824540734291077,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.8089,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.25473228096961975,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.7894,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.2498379647731781,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.7991,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.2572908103466034,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.8029,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.24486681818962097,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.8192,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.24414803087711334,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.8207,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.22983726859092712,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.792,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.22728809714317322,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.7907,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.25463438034057617,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.7946,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.26413586735725403,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7838,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.26904287934303284,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7897,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.2353346049785614,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.8009,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.22661209106445312,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.8008,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.231617733836174,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.8158,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.24001625180244446,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7841,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.2548147439956665,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.7955,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.24447356164455414,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.8008,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.23908770084381104,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.7912,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.2608695924282074,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.8115,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.2576351761817932,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.8113,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.2306436151266098,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.8157,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.259555459022522,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.7949,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.23368364572525024,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.794,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.24801914393901825,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.8091,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.25146400928497314,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.7952,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.28247934579849243,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.8096,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.25513139367103577,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.812,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.264229416847229,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.7988,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.2448280304670334,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.7995,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.2398042380809784,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.7983,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.25409072637557983,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.7937,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.23594260215759277,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.8001,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.2352285087108612,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.8062,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.23229676485061646,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.801,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.2416253685951233,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.8089,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.238126739859581,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.8119,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.23888733983039856,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.814,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.23903244733810425,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.8008,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.23930685222148895,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.8218,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.2544718384742737,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.8129,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.25345054268836975,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.8034,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.20959816873073578,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.8058,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.23408107459545135,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.7927,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.22468121349811554,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7758,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.2410786896944046,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7756,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.23925447463989258,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.8057,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.21363946795463562,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.7952,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.23525173962116241,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.8039,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.23644697666168213,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.7836,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.2549464702606201,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.8048,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.2471502423286438,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.8042,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.2677442729473114,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.7932,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.22224029898643494,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.7913,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.25357353687286377,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.8063,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.25279250741004944,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.7962,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.24006164073944092,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.8035,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.23740209639072418,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.8,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.23864223062992096,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.7961,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.22931008040905,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7838,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.26523420214653015,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.827,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.23836569488048553,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.8138,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.23896102607250214,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.8242,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.23882192373275757,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7883,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.24297630786895752,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7792,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.23153263330459595,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.8049,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.24299921095371246,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.7922,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.2459711879491806,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.7965,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.25645050406455994,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.8096,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.23282258212566376,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.801,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.24719583988189697,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.7995,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.22952306270599365,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.8048,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.24892985820770264,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.7901,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.24024705588817596,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.7961,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.2379492223262787,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.7953,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.23615235090255737,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7867,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.24980758130550385,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.809,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.24282796680927277,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.8159,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.24588549137115479,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.8014,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.26155129075050354,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.8194,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.24780260026454926,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.807,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.2554953396320343,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.8079,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.26482003927230835,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.8005,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.23140351474285126,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.7918,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.23074446618556976,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.7993,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.23023633658885956,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7871,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.24207383394241333,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7752,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.23894651234149933,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.7907,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.2289685755968094,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.7949,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.21341226994991302,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7827,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.26178741455078125,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.804,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.22921819984912872,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7822,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.23780904710292816,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.8047,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.23435160517692566,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.793,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.24259017407894135,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.801,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.2363363802433014,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.8037,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.249486044049263,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.7928,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.239303320646286,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.7955,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.2454206496477127,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7887,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.23204901814460754,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.8046,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.23460811376571655,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.8065,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.24723953008651733,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.7961,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.23624655604362488,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.8054,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.2527509927749634,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.7975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.24115656316280365,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7692,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.2237437665462494,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.8038,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.24242357909679413,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.7954,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.2477048933506012,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.808,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.23448391258716583,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.7929,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.24446263909339905,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7817,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.23605334758758545,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.7937,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.23128555715084076,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.8005,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.23566403985023499,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.8072,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.22268056869506836,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7834,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.2265712469816208,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.796,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.2349291294813156,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.8023,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.23831821978092194,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.8064,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.24748541414737701,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.8017,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.23434555530548096,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7808,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.23230710625648499,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.7951,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.25937700271606445,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7857,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.23671714961528778,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.7952,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.23401865363121033,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.8031,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.25509655475616455,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.8052,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.23072004318237305,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7886,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.2327425479888916,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.8113,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.23793461918830872,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.8072,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.2569359838962555,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.7974,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.24836573004722595,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.7944,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.24016828835010529,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.8135,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.2438604086637497,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.809,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.2413855344057083,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.7917,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.2881578803062439,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.7975,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.23604850471019745,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.7889,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.2427082657814026,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7836,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.23719407618045807,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.805,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.2330656349658966,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.7898,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.2278108447790146,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.7936,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.22893758118152618,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.8035,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.24950122833251953,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.7956,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.23716677725315094,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7837,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.21694540977478027,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7791,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.2512294054031372,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.8081,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 3.772303777185399e+18,
+      "train_loss": 0.8254466042134869,
+      "train_runtime": 12865.8902,
+      "train_samples_per_second": 51.68,
+      "train_steps_per_second": 0.202
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 418855352,
+  "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": 3.772303777185399e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pixio_vitb16/finetune/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4413bf95f4aa5f3be88d61cf187407d501cad5d93fd59ac408e2dbce68ae4d8
+size 6264

continuous/qwen3/pixio_vitb16/finetune/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pixio_vitb16/pretrain/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 768,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pixio",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pixio/pixio-vitb16/pixio_vitb16.pth",
+  "vocab_size": 151936
+}

continuous/qwen3/pixio_vitb16/pretrain/mm_projector.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4df70fe52895663f499743689d14a7994c35eec303177ffb1f0ac96153ebad2a
+size 23087160

continuous/qwen3/pixio_vitb16/pretrain/trainer_state.json ADDED Viewed

	@@ -0,0 +1,421 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 2.6416704654693604,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 9.3363,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.7577583193778992,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 5.8757,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.2792778015136719,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 4.9672,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.10665500164031982,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.7677,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.0641157329082489,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.6892,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.055014580488204956,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.6488,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.08775725215673447,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.6051,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.09135745465755463,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.5893,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.06888291239738464,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.552,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.08810196071863174,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.5289,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.21098637580871582,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.502,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.09919853508472443,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.4978,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.18433034420013428,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.4652,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.12192869931459427,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.4466,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.10177429020404816,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.4419,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.1263597309589386,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.4225,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.09473112225532532,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.4045,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.08497000485658646,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.3861,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07819103449583054,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.3791,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.1307794451713562,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.10182595252990723,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.3459,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07522415369749069,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.357,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.08043169230222702,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.351,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.09895726293325424,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.3368,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.08518967777490616,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.317,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.08389557152986526,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.3273,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.09707918018102646,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.3065,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07562008500099182,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.3019,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.08209778368473053,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.2885,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.09251466393470764,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.2892,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.08615982532501221,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.3006,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.06763345748186111,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.292,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.07769164443016052,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.2723,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.08990345150232315,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.2719,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.07469776272773743,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.2801,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.09107119590044022,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.2865,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.07126908749341965,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.2654,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.06719757616519928,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.2824,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.07430710643529892,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.2618,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.06848102062940598,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.2647,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.06244271993637085,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.2646,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.06255532056093216,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.2573,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.06435045599937439,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.2644,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.06969118118286133,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.2688,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.058846365660429,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.2587,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.06595812737941742,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.251,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.06027515232563019,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.2401,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.06697991490364075,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.2488,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.060831811279058456,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.2512,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.05925348773598671,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.2655,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.061225276440382004,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.2527,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.061373308300971985,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.2431,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.05929708108305931,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.2469,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.0614313930273056,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.2523,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 2.8726731992989696e+17,
+      "train_loss": 4.487420209832147,
+      "train_runtime": 5084.8536,
+      "train_samples_per_second": 109.763,
+      "train_steps_per_second": 0.107
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 31896544,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8726731992989696e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pixio_vith16/finetune/added_tokens.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

continuous/qwen3/pixio_vith16/finetune/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,89 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

continuous/qwen3/pixio_vith16/finetune/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1280,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pixio",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pixio/pixio-vith16/pixio_vith16.pth",
+  "vocab_size": 151936
+}

continuous/qwen3/pixio_vith16/finetune/generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

continuous/qwen3/pixio_vith16/finetune/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pixio_vith16/finetune/model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:24b5afd86129a706a98fc8f58981824c7e5879dca3ac6f5137fc238a44a2407e
+size 4730542328

continuous/qwen3/pixio_vith16/finetune/model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0b238ee4affe5a89a885c6a43cf45b53e67c6cad2851420c32eec96e93d789e3
+size 622329984

continuous/qwen3/pixio_vith16/finetune/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,713 @@

+{
+  "metadata": {
+    "total_parameters": 2358407936,
+    "total_size": 5352785408
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00001-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.cls_token": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.norm.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.norm.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.vision_tower.pos_embed": "model-00001-of-00002.safetensors"
+  }
+}

continuous/qwen3/pixio_vith16/finetune/special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

continuous/qwen3/pixio_vith16/finetune/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

continuous/qwen3/pixio_vith16/finetune/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,240 @@

+{
+  "add_bos_token": false,
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

continuous/qwen3/pixio_vith16/finetune/trainer_state.json ADDED Viewed

	@@ -0,0 +1,1856 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999037443449803,
+  "eval_steps": 500,
+  "global_step": 2597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003850226200789296,
+      "grad_norm": 18.398836135864258,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.2795,
+      "step": 10
+    },
+    {
+      "epoch": 0.007700452401578592,
+      "grad_norm": 6.986608982086182,
+      "learning_rate": 2.435897435897436e-06,
+      "loss": 1.8304,
+      "step": 20
+    },
+    {
+      "epoch": 0.01155067860236789,
+      "grad_norm": 4.451385021209717,
+      "learning_rate": 3.7179487179487184e-06,
+      "loss": 1.4809,
+      "step": 30
+    },
+    {
+      "epoch": 0.015400904803157185,
+      "grad_norm": 1.219258427619934,
+      "learning_rate": 5e-06,
+      "loss": 1.1677,
+      "step": 40
+    },
+    {
+      "epoch": 0.019251131003946483,
+      "grad_norm": 0.7729339599609375,
+      "learning_rate": 6.282051282051282e-06,
+      "loss": 1.0667,
+      "step": 50
+    },
+    {
+      "epoch": 0.02310135720473578,
+      "grad_norm": 0.46129703521728516,
+      "learning_rate": 7.564102564102564e-06,
+      "loss": 0.9863,
+      "step": 60
+    },
+    {
+      "epoch": 0.026951583405525073,
+      "grad_norm": 0.3889714479446411,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9386,
+      "step": 70
+    },
+    {
+      "epoch": 0.03080180960631437,
+      "grad_norm": 0.35314515233039856,
+      "learning_rate": 9.999996111488723e-06,
+      "loss": 0.9367,
+      "step": 80
+    },
+    {
+      "epoch": 0.034652035807103666,
+      "grad_norm": 0.3233426511287689,
+      "learning_rate": 9.999529497453782e-06,
+      "loss": 0.9061,
+      "step": 90
+    },
+    {
+      "epoch": 0.038502262007892966,
+      "grad_norm": 0.32806527614593506,
+      "learning_rate": 9.998285264324193e-06,
+      "loss": 0.8887,
+      "step": 100
+    },
+    {
+      "epoch": 0.04235248820868226,
+      "grad_norm": 0.30368897318840027,
+      "learning_rate": 9.996263605626052e-06,
+      "loss": 0.8688,
+      "step": 110
+    },
+    {
+      "epoch": 0.04620271440947156,
+      "grad_norm": 0.32576969265937805,
+      "learning_rate": 9.99346483580503e-06,
+      "loss": 0.8793,
+      "step": 120
+    },
+    {
+      "epoch": 0.05005294061026085,
+      "grad_norm": 0.29984647035598755,
+      "learning_rate": 9.989889390177467e-06,
+      "loss": 0.8765,
+      "step": 130
+    },
+    {
+      "epoch": 0.053903166811050146,
+      "grad_norm": 0.32196202874183655,
+      "learning_rate": 9.985537824862647e-06,
+      "loss": 0.8698,
+      "step": 140
+    },
+    {
+      "epoch": 0.057753393011839446,
+      "grad_norm": 0.3475538194179535,
+      "learning_rate": 9.980410816696317e-06,
+      "loss": 0.8555,
+      "step": 150
+    },
+    {
+      "epoch": 0.06160361921262874,
+      "grad_norm": 0.3209484815597534,
+      "learning_rate": 9.97450916312541e-06,
+      "loss": 0.8606,
+      "step": 160
+    },
+    {
+      "epoch": 0.06545384541341803,
+      "grad_norm": 0.2558461129665375,
+      "learning_rate": 9.967833782084004e-06,
+      "loss": 0.8607,
+      "step": 170
+    },
+    {
+      "epoch": 0.06930407161420733,
+      "grad_norm": 0.3129828870296478,
+      "learning_rate": 9.960385711850554e-06,
+      "loss": 0.889,
+      "step": 180
+    },
+    {
+      "epoch": 0.07315429781499663,
+      "grad_norm": 0.29852616786956787,
+      "learning_rate": 9.952166110886394e-06,
+      "loss": 0.8781,
+      "step": 190
+    },
+    {
+      "epoch": 0.07700452401578593,
+      "grad_norm": 0.3297346830368042,
+      "learning_rate": 9.943176257655567e-06,
+      "loss": 0.8681,
+      "step": 200
+    },
+    {
+      "epoch": 0.08085475021657522,
+      "grad_norm": 0.28968751430511475,
+      "learning_rate": 9.933417550425952e-06,
+      "loss": 0.8623,
+      "step": 210
+    },
+    {
+      "epoch": 0.08470497641736452,
+      "grad_norm": 0.28054937720298767,
+      "learning_rate": 9.9228915070518e-06,
+      "loss": 0.8504,
+      "step": 220
+    },
+    {
+      "epoch": 0.08855520261815382,
+      "grad_norm": 0.3527531921863556,
+      "learning_rate": 9.911599764737632e-06,
+      "loss": 0.8509,
+      "step": 230
+    },
+    {
+      "epoch": 0.09240542881894312,
+      "grad_norm": 0.29711470007896423,
+      "learning_rate": 9.899544079783606e-06,
+      "loss": 0.8458,
+      "step": 240
+    },
+    {
+      "epoch": 0.0962556550197324,
+      "grad_norm": 0.31836822628974915,
+      "learning_rate": 9.886726327312338e-06,
+      "loss": 0.8625,
+      "step": 250
+    },
+    {
+      "epoch": 0.1001058812205217,
+      "grad_norm": 0.2927994728088379,
+      "learning_rate": 9.87314850097724e-06,
+      "loss": 0.8595,
+      "step": 260
+    },
+    {
+      "epoch": 0.103956107421311,
+      "grad_norm": 0.28095391392707825,
+      "learning_rate": 9.858812712652452e-06,
+      "loss": 0.8468,
+      "step": 270
+    },
+    {
+      "epoch": 0.10780633362210029,
+      "grad_norm": 0.2745492458343506,
+      "learning_rate": 9.843721192104341e-06,
+      "loss": 0.8472,
+      "step": 280
+    },
+    {
+      "epoch": 0.11165655982288959,
+      "grad_norm": 0.286895751953125,
+      "learning_rate": 9.827876286644698e-06,
+      "loss": 0.8642,
+      "step": 290
+    },
+    {
+      "epoch": 0.11550678602367889,
+      "grad_norm": 0.25512439012527466,
+      "learning_rate": 9.811280460765643e-06,
+      "loss": 0.8246,
+      "step": 300
+    },
+    {
+      "epoch": 0.11935701222446819,
+      "grad_norm": 0.2638566493988037,
+      "learning_rate": 9.793936295756292e-06,
+      "loss": 0.8385,
+      "step": 310
+    },
+    {
+      "epoch": 0.12320723842525748,
+      "grad_norm": 0.2715226709842682,
+      "learning_rate": 9.775846489301279e-06,
+      "loss": 0.8385,
+      "step": 320
+    },
+    {
+      "epoch": 0.12705746462604678,
+      "grad_norm": 0.2842342257499695,
+      "learning_rate": 9.757013855061157e-06,
+      "loss": 0.8387,
+      "step": 330
+    },
+    {
+      "epoch": 0.13090769082683607,
+      "grad_norm": 0.2704889476299286,
+      "learning_rate": 9.737441322234758e-06,
+      "loss": 0.8497,
+      "step": 340
+    },
+    {
+      "epoch": 0.13475791702762538,
+      "grad_norm": 0.295561283826828,
+      "learning_rate": 9.717131935103605e-06,
+      "loss": 0.8496,
+      "step": 350
+    },
+    {
+      "epoch": 0.13860814322841467,
+      "grad_norm": 0.26586639881134033,
+      "learning_rate": 9.696088852558398e-06,
+      "loss": 0.8357,
+      "step": 360
+    },
+    {
+      "epoch": 0.14245836942920398,
+      "grad_norm": 0.2953343391418457,
+      "learning_rate": 9.674315347607686e-06,
+      "loss": 0.8626,
+      "step": 370
+    },
+    {
+      "epoch": 0.14630859562999327,
+      "grad_norm": 0.25719645619392395,
+      "learning_rate": 9.651814806868796e-06,
+      "loss": 0.8227,
+      "step": 380
+    },
+    {
+      "epoch": 0.15015882183078255,
+      "grad_norm": 0.2690722644329071,
+      "learning_rate": 9.62859073004107e-06,
+      "loss": 0.8307,
+      "step": 390
+    },
+    {
+      "epoch": 0.15400904803157187,
+      "grad_norm": 0.29106849431991577,
+      "learning_rate": 9.604646729361547e-06,
+      "loss": 0.8342,
+      "step": 400
+    },
+    {
+      "epoch": 0.15785927423236115,
+      "grad_norm": 0.257255882024765,
+      "learning_rate": 9.579986529043099e-06,
+      "loss": 0.8226,
+      "step": 410
+    },
+    {
+      "epoch": 0.16170950043315044,
+      "grad_norm": 0.2759833335876465,
+      "learning_rate": 9.554613964695189e-06,
+      "loss": 0.8397,
+      "step": 420
+    },
+    {
+      "epoch": 0.16555972663393975,
+      "grad_norm": 0.287870854139328,
+      "learning_rate": 9.528532982727281e-06,
+      "loss": 0.8286,
+      "step": 430
+    },
+    {
+      "epoch": 0.16940995283472904,
+      "grad_norm": 0.2770979404449463,
+      "learning_rate": 9.501747639735018e-06,
+      "loss": 0.8269,
+      "step": 440
+    },
+    {
+      "epoch": 0.17326017903551832,
+      "grad_norm": 0.2949519753456116,
+      "learning_rate": 9.474262101869272e-06,
+      "loss": 0.8163,
+      "step": 450
+    },
+    {
+      "epoch": 0.17711040523630764,
+      "grad_norm": 0.2671734690666199,
+      "learning_rate": 9.446080644188141e-06,
+      "loss": 0.8212,
+      "step": 460
+    },
+    {
+      "epoch": 0.18096063143709692,
+      "grad_norm": 0.2706279754638672,
+      "learning_rate": 9.417207649992017e-06,
+      "loss": 0.8301,
+      "step": 470
+    },
+    {
+      "epoch": 0.18481085763788624,
+      "grad_norm": 0.27451440691947937,
+      "learning_rate": 9.387647610141816e-06,
+      "loss": 0.8281,
+      "step": 480
+    },
+    {
+      "epoch": 0.18866108383867553,
+      "grad_norm": 0.269765168428421,
+      "learning_rate": 9.35740512236047e-06,
+      "loss": 0.8146,
+      "step": 490
+    },
+    {
+      "epoch": 0.1925113100394648,
+      "grad_norm": 0.25978100299835205,
+      "learning_rate": 9.326484890517809e-06,
+      "loss": 0.8193,
+      "step": 500
+    },
+    {
+      "epoch": 0.19636153624025413,
+      "grad_norm": 0.26169267296791077,
+      "learning_rate": 9.294891723898926e-06,
+      "loss": 0.8148,
+      "step": 510
+    },
+    {
+      "epoch": 0.2002117624410434,
+      "grad_norm": 0.27979981899261475,
+      "learning_rate": 9.262630536456153e-06,
+      "loss": 0.8439,
+      "step": 520
+    },
+    {
+      "epoch": 0.2040619886418327,
+      "grad_norm": 0.2893049716949463,
+      "learning_rate": 9.229706346044749e-06,
+      "loss": 0.8158,
+      "step": 530
+    },
+    {
+      "epoch": 0.207912214842622,
+      "grad_norm": 0.2842508554458618,
+      "learning_rate": 9.196124273642422e-06,
+      "loss": 0.8301,
+      "step": 540
+    },
+    {
+      "epoch": 0.2117624410434113,
+      "grad_norm": 0.2560935914516449,
+      "learning_rate": 9.161889542552842e-06,
+      "loss": 0.8309,
+      "step": 550
+    },
+    {
+      "epoch": 0.21561266724420058,
+      "grad_norm": 0.25655651092529297,
+      "learning_rate": 9.127007477593193e-06,
+      "loss": 0.8365,
+      "step": 560
+    },
+    {
+      "epoch": 0.2194628934449899,
+      "grad_norm": 0.2819012999534607,
+      "learning_rate": 9.091483504265974e-06,
+      "loss": 0.8455,
+      "step": 570
+    },
+    {
+      "epoch": 0.22331311964577918,
+      "grad_norm": 0.2837015390396118,
+      "learning_rate": 9.055323147915116e-06,
+      "loss": 0.8249,
+      "step": 580
+    },
+    {
+      "epoch": 0.2271633458465685,
+      "grad_norm": 0.28323397040367126,
+      "learning_rate": 9.018532032866585e-06,
+      "loss": 0.8356,
+      "step": 590
+    },
+    {
+      "epoch": 0.23101357204735778,
+      "grad_norm": 0.26320621371269226,
+      "learning_rate": 8.981115881553579e-06,
+      "loss": 0.8263,
+      "step": 600
+    },
+    {
+      "epoch": 0.23486379824814707,
+      "grad_norm": 0.2979693114757538,
+      "learning_rate": 8.943080513626476e-06,
+      "loss": 0.8462,
+      "step": 610
+    },
+    {
+      "epoch": 0.23871402444893638,
+      "grad_norm": 0.2657105624675751,
+      "learning_rate": 8.904431845047641e-06,
+      "loss": 0.8304,
+      "step": 620
+    },
+    {
+      "epoch": 0.24256425064972567,
+      "grad_norm": 0.2956584393978119,
+      "learning_rate": 8.86517588717128e-06,
+      "loss": 0.8468,
+      "step": 630
+    },
+    {
+      "epoch": 0.24641447685051496,
+      "grad_norm": 0.2598516047000885,
+      "learning_rate": 8.82531874580844e-06,
+      "loss": 0.8356,
+      "step": 640
+    },
+    {
+      "epoch": 0.25026470305130427,
+      "grad_norm": 0.24076014757156372,
+      "learning_rate": 8.784866620277314e-06,
+      "loss": 0.7924,
+      "step": 650
+    },
+    {
+      "epoch": 0.25411492925209356,
+      "grad_norm": 0.2775667905807495,
+      "learning_rate": 8.743825802439018e-06,
+      "loss": 0.8301,
+      "step": 660
+    },
+    {
+      "epoch": 0.25796515545288284,
+      "grad_norm": 0.31721848249435425,
+      "learning_rate": 8.702202675718956e-06,
+      "loss": 0.8351,
+      "step": 670
+    },
+    {
+      "epoch": 0.26181538165367213,
+      "grad_norm": 0.2700018882751465,
+      "learning_rate": 8.660003714113959e-06,
+      "loss": 0.8057,
+      "step": 680
+    },
+    {
+      "epoch": 0.26566560785446147,
+      "grad_norm": 0.25533822178840637,
+      "learning_rate": 8.617235481185323e-06,
+      "loss": 0.8305,
+      "step": 690
+    },
+    {
+      "epoch": 0.26951583405525076,
+      "grad_norm": 0.26094838976860046,
+      "learning_rate": 8.573904629037931e-06,
+      "loss": 0.8348,
+      "step": 700
+    },
+    {
+      "epoch": 0.27336606025604004,
+      "grad_norm": 0.2598833441734314,
+      "learning_rate": 8.530017897285585e-06,
+      "loss": 0.815,
+      "step": 710
+    },
+    {
+      "epoch": 0.27721628645682933,
+      "grad_norm": 0.2452683448791504,
+      "learning_rate": 8.485582112002746e-06,
+      "loss": 0.8191,
+      "step": 720
+    },
+    {
+      "epoch": 0.2810665126576186,
+      "grad_norm": 0.26061567664146423,
+      "learning_rate": 8.440604184662811e-06,
+      "loss": 0.8256,
+      "step": 730
+    },
+    {
+      "epoch": 0.28491673885840796,
+      "grad_norm": 0.26468393206596375,
+      "learning_rate": 8.395091111063118e-06,
+      "loss": 0.8137,
+      "step": 740
+    },
+    {
+      "epoch": 0.28876696505919724,
+      "grad_norm": 0.2534913420677185,
+      "learning_rate": 8.349049970236822e-06,
+      "loss": 0.813,
+      "step": 750
+    },
+    {
+      "epoch": 0.29261719125998653,
+      "grad_norm": 0.2714790105819702,
+      "learning_rate": 8.302487923351842e-06,
+      "loss": 0.8052,
+      "step": 760
+    },
+    {
+      "epoch": 0.2964674174607758,
+      "grad_norm": 0.28246891498565674,
+      "learning_rate": 8.255412212597021e-06,
+      "loss": 0.823,
+      "step": 770
+    },
+    {
+      "epoch": 0.3003176436615651,
+      "grad_norm": 0.255435585975647,
+      "learning_rate": 8.207830160055688e-06,
+      "loss": 0.82,
+      "step": 780
+    },
+    {
+      "epoch": 0.3041678698623544,
+      "grad_norm": 0.2706385552883148,
+      "learning_rate": 8.159749166566786e-06,
+      "loss": 0.805,
+      "step": 790
+    },
+    {
+      "epoch": 0.30801809606314373,
+      "grad_norm": 0.2509203255176544,
+      "learning_rate": 8.11117671057377e-06,
+      "loss": 0.8327,
+      "step": 800
+    },
+    {
+      "epoch": 0.311868322263933,
+      "grad_norm": 0.2683849334716797,
+      "learning_rate": 8.062120346961404e-06,
+      "loss": 0.8242,
+      "step": 810
+    },
+    {
+      "epoch": 0.3157185484647223,
+      "grad_norm": 0.25757697224617004,
+      "learning_rate": 8.012587705880705e-06,
+      "loss": 0.8175,
+      "step": 820
+    },
+    {
+      "epoch": 0.3195687746655116,
+      "grad_norm": 0.2627410590648651,
+      "learning_rate": 7.962586491562146e-06,
+      "loss": 0.8043,
+      "step": 830
+    },
+    {
+      "epoch": 0.3234190008663009,
+      "grad_norm": 0.29739969968795776,
+      "learning_rate": 7.912124481117357e-06,
+      "loss": 0.8101,
+      "step": 840
+    },
+    {
+      "epoch": 0.3272692270670902,
+      "grad_norm": 0.2578446865081787,
+      "learning_rate": 7.861209523329494e-06,
+      "loss": 0.8198,
+      "step": 850
+    },
+    {
+      "epoch": 0.3311194532678795,
+      "grad_norm": 0.2690160870552063,
+      "learning_rate": 7.809849537432432e-06,
+      "loss": 0.8038,
+      "step": 860
+    },
+    {
+      "epoch": 0.3349696794686688,
+      "grad_norm": 0.2721980810165405,
+      "learning_rate": 7.758052511879035e-06,
+      "loss": 0.8143,
+      "step": 870
+    },
+    {
+      "epoch": 0.3388199056694581,
+      "grad_norm": 0.23226694762706757,
+      "learning_rate": 7.705826503098642e-06,
+      "loss": 0.8086,
+      "step": 880
+    },
+    {
+      "epoch": 0.34267013187024736,
+      "grad_norm": 0.24305321276187897,
+      "learning_rate": 7.653179634243979e-06,
+      "loss": 0.8081,
+      "step": 890
+    },
+    {
+      "epoch": 0.34652035807103665,
+      "grad_norm": 0.24421408772468567,
+      "learning_rate": 7.600120093927696e-06,
+      "loss": 0.8152,
+      "step": 900
+    },
+    {
+      "epoch": 0.350370584271826,
+      "grad_norm": 0.25989627838134766,
+      "learning_rate": 7.546656134948729e-06,
+      "loss": 0.8047,
+      "step": 910
+    },
+    {
+      "epoch": 0.3542208104726153,
+      "grad_norm": 0.26413819193840027,
+      "learning_rate": 7.492796073008661e-06,
+      "loss": 0.8023,
+      "step": 920
+    },
+    {
+      "epoch": 0.35807103667340456,
+      "grad_norm": 0.28184014558792114,
+      "learning_rate": 7.438548285418326e-06,
+      "loss": 0.7885,
+      "step": 930
+    },
+    {
+      "epoch": 0.36192126287419385,
+      "grad_norm": 0.3174017369747162,
+      "learning_rate": 7.3839212097948e-06,
+      "loss": 0.8221,
+      "step": 940
+    },
+    {
+      "epoch": 0.36577148907498314,
+      "grad_norm": 0.2580402195453644,
+      "learning_rate": 7.328923342749039e-06,
+      "loss": 0.8372,
+      "step": 950
+    },
+    {
+      "epoch": 0.3696217152757725,
+      "grad_norm": 0.28295907378196716,
+      "learning_rate": 7.273563238564319e-06,
+      "loss": 0.8215,
+      "step": 960
+    },
+    {
+      "epoch": 0.37347194147656176,
+      "grad_norm": 0.2699388861656189,
+      "learning_rate": 7.217849507865724e-06,
+      "loss": 0.8027,
+      "step": 970
+    },
+    {
+      "epoch": 0.37732216767735105,
+      "grad_norm": 0.2606251835823059,
+      "learning_rate": 7.161790816280858e-06,
+      "loss": 0.8074,
+      "step": 980
+    },
+    {
+      "epoch": 0.38117239387814034,
+      "grad_norm": 0.28082045912742615,
+      "learning_rate": 7.1053958830920125e-06,
+      "loss": 0.7949,
+      "step": 990
+    },
+    {
+      "epoch": 0.3850226200789296,
+      "grad_norm": 0.2589828372001648,
+      "learning_rate": 7.0486734798799715e-06,
+      "loss": 0.81,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3888728462797189,
+      "grad_norm": 0.2758364677429199,
+      "learning_rate": 6.991632429159708e-06,
+      "loss": 0.8328,
+      "step": 1010
+    },
+    {
+      "epoch": 0.39272307248050825,
+      "grad_norm": 0.276899129152298,
+      "learning_rate": 6.934281603008132e-06,
+      "loss": 0.8253,
+      "step": 1020
+    },
+    {
+      "epoch": 0.39657329868129754,
+      "grad_norm": 0.2616158425807953,
+      "learning_rate": 6.876629921684143e-06,
+      "loss": 0.8222,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4004235248820868,
+      "grad_norm": 0.2803502082824707,
+      "learning_rate": 6.818686352241199e-06,
+      "loss": 0.8133,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4042737510828761,
+      "grad_norm": 0.23917952179908752,
+      "learning_rate": 6.760459907132573e-06,
+      "loss": 0.809,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4081239772836654,
+      "grad_norm": 0.24806852638721466,
+      "learning_rate": 6.701959642809589e-06,
+      "loss": 0.8165,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41197420348445474,
+      "grad_norm": 0.262184202671051,
+      "learning_rate": 6.643194658312987e-06,
+      "loss": 0.8083,
+      "step": 1070
+    },
+    {
+      "epoch": 0.415824429685244,
+      "grad_norm": 0.2494860142469406,
+      "learning_rate": 6.584174093857676e-06,
+      "loss": 0.8321,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4196746558860333,
+      "grad_norm": 0.3048526346683502,
+      "learning_rate": 6.5249071294110735e-06,
+      "loss": 0.8116,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4235248820868226,
+      "grad_norm": 0.27249541878700256,
+      "learning_rate": 6.465402983265274e-06,
+      "loss": 0.8267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4273751082876119,
+      "grad_norm": 0.2680596709251404,
+      "learning_rate": 6.405670910603243e-06,
+      "loss": 0.8227,
+      "step": 1110
+    },
+    {
+      "epoch": 0.43122533448840117,
+      "grad_norm": 0.28797248005867004,
+      "learning_rate": 6.345720202059291e-06,
+      "loss": 0.8187,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4350755606891905,
+      "grad_norm": 0.259244829416275,
+      "learning_rate": 6.285560182274008e-06,
+      "loss": 0.7976,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4389257868899798,
+      "grad_norm": 0.25299155712127686,
+      "learning_rate": 6.225200208443936e-06,
+      "loss": 0.8194,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4427760130907691,
+      "grad_norm": 0.24135693907737732,
+      "learning_rate": 6.16464966886616e-06,
+      "loss": 0.8098,
+      "step": 1150
+    },
+    {
+      "epoch": 0.44662623929155837,
+      "grad_norm": 0.2942310869693756,
+      "learning_rate": 6.103917981478065e-06,
+      "loss": 0.8321,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45047646549234766,
+      "grad_norm": 0.24877654016017914,
+      "learning_rate": 6.043014592392489e-06,
+      "loss": 0.8446,
+      "step": 1170
+    },
+    {
+      "epoch": 0.454326691693137,
+      "grad_norm": 0.24991309642791748,
+      "learning_rate": 5.981948974428485e-06,
+      "loss": 0.8182,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4581769178939263,
+      "grad_norm": 0.2705898880958557,
+      "learning_rate": 5.920730625637934e-06,
+      "loss": 0.799,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46202714409471557,
+      "grad_norm": 0.2700374722480774,
+      "learning_rate": 5.8593690678282355e-06,
+      "loss": 0.8079,
+      "step": 1200
+    },
+    {
+      "epoch": 0.46587737029550486,
+      "grad_norm": 0.26900714635849,
+      "learning_rate": 5.797873845081301e-06,
+      "loss": 0.8113,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46972759649629414,
+      "grad_norm": 0.2601497769355774,
+      "learning_rate": 5.736254522269075e-06,
+      "loss": 0.8289,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47357782269708343,
+      "grad_norm": 0.25165992975234985,
+      "learning_rate": 5.6745206835658386e-06,
+      "loss": 0.83,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47742804889787277,
+      "grad_norm": 0.2410140335559845,
+      "learning_rate": 5.612681930957495e-06,
+      "loss": 0.8013,
+      "step": 1240
+    },
+    {
+      "epoch": 0.48127827509866206,
+      "grad_norm": 0.24769233167171478,
+      "learning_rate": 5.550747882748095e-06,
+      "loss": 0.8007,
+      "step": 1250
+    },
+    {
+      "epoch": 0.48512850129945134,
+      "grad_norm": 0.28397151827812195,
+      "learning_rate": 5.4887281720638195e-06,
+      "loss": 0.8046,
+      "step": 1260
+    },
+    {
+      "epoch": 0.48897872750024063,
+      "grad_norm": 0.290617972612381,
+      "learning_rate": 5.42663244535466e-06,
+      "loss": 0.7939,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4928289537010299,
+      "grad_norm": 0.2762424647808075,
+      "learning_rate": 5.3644703608940205e-06,
+      "loss": 0.7993,
+      "step": 1280
+    },
+    {
+      "epoch": 0.49667917990181926,
+      "grad_norm": 0.26204755902290344,
+      "learning_rate": 5.302251587276491e-06,
+      "loss": 0.811,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5005294061026085,
+      "grad_norm": 0.25625428557395935,
+      "learning_rate": 5.2399858019140005e-06,
+      "loss": 0.8112,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5043796323033978,
+      "grad_norm": 0.24832060933113098,
+      "learning_rate": 5.177682689530615e-06,
+      "loss": 0.825,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5082298585041871,
+      "grad_norm": 0.2715055048465729,
+      "learning_rate": 5.11535194065619e-06,
+      "loss": 0.7932,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5120800847049765,
+      "grad_norm": 0.28562864661216736,
+      "learning_rate": 5.053003250119113e-06,
+      "loss": 0.8051,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5159303109057657,
+      "grad_norm": 0.2645500898361206,
+      "learning_rate": 4.9906463155383925e-06,
+      "loss": 0.8107,
+      "step": 1340
+    },
+    {
+      "epoch": 0.519780537106555,
+      "grad_norm": 0.25817441940307617,
+      "learning_rate": 4.9282908358153046e-06,
+      "loss": 0.8015,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5236307633073443,
+      "grad_norm": 0.2950255572795868,
+      "learning_rate": 4.8659465096248345e-06,
+      "loss": 0.8215,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5274809895081336,
+      "grad_norm": 0.28061336278915405,
+      "learning_rate": 4.803623033907169e-06,
+      "loss": 0.8212,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5313312157089229,
+      "grad_norm": 0.24569891393184662,
+      "learning_rate": 4.741330102359441e-06,
+      "loss": 0.8255,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5351814419097122,
+      "grad_norm": 0.2755064070224762,
+      "learning_rate": 4.679077403927996e-06,
+      "loss": 0.8059,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5390316681105015,
+      "grad_norm": 0.26330769062042236,
+      "learning_rate": 4.616874621301373e-06,
+      "loss": 0.8047,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5428818943112907,
+      "grad_norm": 0.28450316190719604,
+      "learning_rate": 4.554731429404293e-06,
+      "loss": 0.8195,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5467321205120801,
+      "grad_norm": 0.2859039008617401,
+      "learning_rate": 4.492657493892822e-06,
+      "loss": 0.8058,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5505823467128694,
+      "grad_norm": 0.3009839653968811,
+      "learning_rate": 4.430662469650999e-06,
+      "loss": 0.8201,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5544325729136587,
+      "grad_norm": 0.2866976857185364,
+      "learning_rate": 4.368755999289118e-06,
+      "loss": 0.8216,
+      "step": 1440
+    },
+    {
+      "epoch": 0.558282799114448,
+      "grad_norm": 0.303892582654953,
+      "learning_rate": 4.306947711643949e-06,
+      "loss": 0.809,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5621330253152372,
+      "grad_norm": 0.2659822106361389,
+      "learning_rate": 4.245247220281068e-06,
+      "loss": 0.8102,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5659832515160266,
+      "grad_norm": 0.25798124074935913,
+      "learning_rate": 4.183664121999587e-06,
+      "loss": 0.8092,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5698334777168159,
+      "grad_norm": 0.27675485610961914,
+      "learning_rate": 4.122207995339474e-06,
+      "loss": 0.8038,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5736837039176051,
+      "grad_norm": 0.26654717326164246,
+      "learning_rate": 4.060888399091734e-06,
+      "loss": 0.8103,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5775339301183945,
+      "grad_norm": 0.24358715116977692,
+      "learning_rate": 3.999714870811639e-06,
+      "loss": 0.817,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5813841563191837,
+      "grad_norm": 0.25320959091186523,
+      "learning_rate": 3.938696925335275e-06,
+      "loss": 0.8115,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5852343825199731,
+      "grad_norm": 0.2536487281322479,
+      "learning_rate": 3.87784405329962e-06,
+      "loss": 0.8185,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5890846087207623,
+      "grad_norm": 0.2713620960712433,
+      "learning_rate": 3.817165719666382e-06,
+      "loss": 0.8227,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5929348349215516,
+      "grad_norm": 0.2582155466079712,
+      "learning_rate": 3.756671362249841e-06,
+      "loss": 0.8244,
+      "step": 1540
+    },
+    {
+      "epoch": 0.596785061122341,
+      "grad_norm": 0.25831568241119385,
+      "learning_rate": 3.6963703902488907e-06,
+      "loss": 0.8122,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6006352873231302,
+      "grad_norm": 0.2677266299724579,
+      "learning_rate": 3.6362721827835655e-06,
+      "loss": 0.8318,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6044855135239195,
+      "grad_norm": 0.2744590938091278,
+      "learning_rate": 3.576386087436212e-06,
+      "loss": 0.8241,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6083357397247088,
+      "grad_norm": 0.2780584394931793,
+      "learning_rate": 3.5167214187975913e-06,
+      "loss": 0.8143,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6121859659254981,
+      "grad_norm": 0.24003905057907104,
+      "learning_rate": 3.457287457018086e-06,
+      "loss": 0.8162,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6160361921262875,
+      "grad_norm": 0.25149521231651306,
+      "learning_rate": 3.3980934463643003e-06,
+      "loss": 0.8033,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6198864183270767,
+      "grad_norm": 0.24153059720993042,
+      "learning_rate": 3.3391485937812053e-06,
+      "loss": 0.7863,
+      "step": 1610
+    },
+    {
+      "epoch": 0.623736644527866,
+      "grad_norm": 0.2628701627254486,
+      "learning_rate": 3.280462067460115e-06,
+      "loss": 0.7858,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6275868707286553,
+      "grad_norm": 0.26264509558677673,
+      "learning_rate": 3.222042995412669e-06,
+      "loss": 0.8153,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6314370969294446,
+      "grad_norm": 0.2389419674873352,
+      "learning_rate": 3.163900464051089e-06,
+      "loss": 0.8054,
+      "step": 1640
+    },
+    {
+      "epoch": 0.635287323130234,
+      "grad_norm": 0.2567588686943054,
+      "learning_rate": 3.1060435167748826e-06,
+      "loss": 0.8145,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6391375493310232,
+      "grad_norm": 0.2678077816963196,
+      "learning_rate": 3.048481152564253e-06,
+      "loss": 0.794,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6429877755318125,
+      "grad_norm": 0.2808184325695038,
+      "learning_rate": 2.9912223245804017e-06,
+      "loss": 0.8159,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6468380017326018,
+      "grad_norm": 0.2707509696483612,
+      "learning_rate": 2.934275938772981e-06,
+      "loss": 0.8148,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6506882279333911,
+      "grad_norm": 0.2754411995410919,
+      "learning_rate": 2.8776508524948676e-06,
+      "loss": 0.8035,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6545384541341804,
+      "grad_norm": 0.23698505759239197,
+      "learning_rate": 2.821355873124503e-06,
+      "loss": 0.8026,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6583886803349697,
+      "grad_norm": 0.2842792868614197,
+      "learning_rate": 2.7653997566960144e-06,
+      "loss": 0.8159,
+      "step": 1710
+    },
+    {
+      "epoch": 0.662238906535759,
+      "grad_norm": 0.2643272876739502,
+      "learning_rate": 2.709791206537309e-06,
+      "loss": 0.8062,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6660891327365482,
+      "grad_norm": 0.2622954547405243,
+      "learning_rate": 2.6545388719163747e-06,
+      "loss": 0.8139,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6699393589373376,
+      "grad_norm": 0.2567506432533264,
+      "learning_rate": 2.599651346695979e-06,
+      "loss": 0.8111,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6737895851381268,
+      "grad_norm": 0.2610611915588379,
+      "learning_rate": 2.545137167997007e-06,
+      "loss": 0.8066,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6776398113389162,
+      "grad_norm": 0.24663598835468292,
+      "learning_rate": 2.4910048148705972e-06,
+      "loss": 0.7952,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6814900375397055,
+      "grad_norm": 0.2778531610965729,
+      "learning_rate": 2.4372627069793327e-06,
+      "loss": 0.838,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6853402637404947,
+      "grad_norm": 0.25635775923728943,
+      "learning_rate": 2.3839192032876486e-06,
+      "loss": 0.825,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6891904899412841,
+      "grad_norm": 0.25631511211395264,
+      "learning_rate": 2.3309826007617047e-06,
+      "loss": 0.8346,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6930407161420733,
+      "grad_norm": 0.2577073574066162,
+      "learning_rate": 2.278461133078881e-06,
+      "loss": 0.7988,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6968909423428626,
+      "grad_norm": 0.26177361607551575,
+      "learning_rate": 2.2263629693471258e-06,
+      "loss": 0.7898,
+      "step": 1810
+    },
+    {
+      "epoch": 0.700741168543652,
+      "grad_norm": 0.2475704848766327,
+      "learning_rate": 2.1746962128343414e-06,
+      "loss": 0.8154,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7045913947444412,
+      "grad_norm": 0.27056577801704407,
+      "learning_rate": 2.1234688997080183e-06,
+      "loss": 0.8028,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7084416209452306,
+      "grad_norm": 0.271970272064209,
+      "learning_rate": 2.0726889977853053e-06,
+      "loss": 0.8073,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7122918471460198,
+      "grad_norm": 0.26976990699768066,
+      "learning_rate": 2.022364405293703e-06,
+      "loss": 0.82,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7161420733468091,
+      "grad_norm": 0.25280308723449707,
+      "learning_rate": 1.9725029496425814e-06,
+      "loss": 0.8125,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7199922995475985,
+      "grad_norm": 0.26316967606544495,
+      "learning_rate": 1.923112386205727e-06,
+      "loss": 0.8104,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7238425257483877,
+      "grad_norm": 0.24402229487895966,
+      "learning_rate": 1.874200397115079e-06,
+      "loss": 0.8163,
+      "step": 1880
+    },
+    {
+      "epoch": 0.727692751949177,
+      "grad_norm": 0.26190996170043945,
+      "learning_rate": 1.825774590065857e-06,
+      "loss": 0.8014,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7315429781499663,
+      "grad_norm": 0.2743520438671112,
+      "learning_rate": 1.7778424971332813e-06,
+      "loss": 0.8076,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7353932043507556,
+      "grad_norm": 0.24974942207336426,
+      "learning_rate": 1.7304115736010407e-06,
+      "loss": 0.8066,
+      "step": 1910
+    },
+    {
+      "epoch": 0.739243430551545,
+      "grad_norm": 0.25792479515075684,
+      "learning_rate": 1.6834891968017108e-06,
+      "loss": 0.7982,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7430936567523342,
+      "grad_norm": 0.2730746567249298,
+      "learning_rate": 1.6370826649692884e-06,
+      "loss": 0.8205,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7469438829531235,
+      "grad_norm": 0.25457608699798584,
+      "learning_rate": 1.5911991961040463e-06,
+      "loss": 0.8263,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7507941091539128,
+      "grad_norm": 0.25829651951789856,
+      "learning_rate": 1.545845926849851e-06,
+      "loss": 0.811,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7546443353547021,
+      "grad_norm": 0.278825044631958,
+      "learning_rate": 1.5010299113841397e-06,
+      "loss": 0.8307,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7584945615554913,
+      "grad_norm": 0.2804868817329407,
+      "learning_rate": 1.4567581203207238e-06,
+      "loss": 0.8185,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7623447877562807,
+      "grad_norm": 0.2708275020122528,
+      "learning_rate": 1.413037439625593e-06,
+      "loss": 0.8182,
+      "step": 1980
+    },
+    {
+      "epoch": 0.76619501395707,
+      "grad_norm": 0.277474582195282,
+      "learning_rate": 1.3698746695458847e-06,
+      "loss": 0.811,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7700452401578592,
+      "grad_norm": 0.253671795129776,
+      "learning_rate": 1.3272765235521745e-06,
+      "loss": 0.8027,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7738954663586486,
+      "grad_norm": 0.2473001927137375,
+      "learning_rate": 1.2852496272942877e-06,
+      "loss": 0.8097,
+      "step": 2010
+    },
+    {
+      "epoch": 0.7777456925594378,
+      "grad_norm": 0.24260517954826355,
+      "learning_rate": 1.2438005175707396e-06,
+      "loss": 0.7983,
+      "step": 2020
+    },
+    {
+      "epoch": 0.7815959187602272,
+      "grad_norm": 0.2584003508090973,
+      "learning_rate": 1.2029356413120297e-06,
+      "loss": 0.7856,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7854461449610165,
+      "grad_norm": 0.25385016202926636,
+      "learning_rate": 1.1626613545778786e-06,
+      "loss": 0.802,
+      "step": 2040
+    },
+    {
+      "epoch": 0.7892963711618057,
+      "grad_norm": 0.24844267964363098,
+      "learning_rate": 1.1229839215686294e-06,
+      "loss": 0.8059,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7931465973625951,
+      "grad_norm": 0.2495056688785553,
+      "learning_rate": 1.0839095136509188e-06,
+      "loss": 0.7934,
+      "step": 2060
+    },
+    {
+      "epoch": 0.7969968235633843,
+      "grad_norm": 0.28321436047554016,
+      "learning_rate": 1.045444208397791e-06,
+      "loss": 0.8148,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8008470497641736,
+      "grad_norm": 0.2550027072429657,
+      "learning_rate": 1.007593988643402e-06,
+      "loss": 0.7929,
+      "step": 2080
+    },
+    {
+      "epoch": 0.804697275964963,
+      "grad_norm": 0.2520841658115387,
+      "learning_rate": 9.703647415524613e-07,
+      "loss": 0.8153,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8085475021657522,
+      "grad_norm": 0.25942012667655945,
+      "learning_rate": 9.337622577045485e-07,
+      "loss": 0.8047,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8123977283665416,
+      "grad_norm": 0.26703941822052,
+      "learning_rate": 8.977922301934588e-07,
+      "loss": 0.8122,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8162479545673308,
+      "grad_norm": 0.2538417875766754,
+      "learning_rate": 8.624602537417009e-07,
+      "loss": 0.8139,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8200981807681201,
+      "grad_norm": 0.27343836426734924,
+      "learning_rate": 8.277718238303123e-07,
+      "loss": 0.8039,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8239484069689095,
+      "grad_norm": 0.2593398988246918,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.8063,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8277986331696987,
+      "grad_norm": 0.265997976064682,
+      "learning_rate": 7.603470842324223e-07,
+      "loss": 0.7993,
+      "step": 2150
+    },
+    {
+      "epoch": 0.831648859370488,
+      "grad_norm": 0.2503928542137146,
+      "learning_rate": 7.276212616857575e-07,
+      "loss": 0.8159,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8354990855712773,
+      "grad_norm": 0.2465638965368271,
+      "learning_rate": 6.955599583279837e-07,
+      "loss": 0.8178,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8393493117720666,
+      "grad_norm": 0.26089972257614136,
+      "learning_rate": 6.641681609246981e-07,
+      "loss": 0.807,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8431995379728559,
+      "grad_norm": 0.27608776092529297,
+      "learning_rate": 6.334507521075711e-07,
+      "loss": 0.8162,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8470497641736452,
+      "grad_norm": 0.2839866876602173,
+      "learning_rate": 6.034125096149179e-07,
+      "loss": 0.8081,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8508999903744345,
+      "grad_norm": 0.257762610912323,
+      "learning_rate": 5.740581055485722e-07,
+      "loss": 0.7802,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8547502165752238,
+      "grad_norm": 0.2402620166540146,
+      "learning_rate": 5.453921056471961e-07,
+      "loss": 0.8151,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8586004427760131,
+      "grad_norm": 0.27869755029678345,
+      "learning_rate": 5.174189685761288e-07,
+      "loss": 0.807,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8624506689768023,
+      "grad_norm": 0.2538870871067047,
+      "learning_rate": 4.901430452338979e-07,
+      "loss": 0.8186,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8663008951775917,
+      "grad_norm": 0.26168933510780334,
+      "learning_rate": 4.6356857807548286e-07,
+      "loss": 0.8039,
+      "step": 2250
+    },
+    {
+      "epoch": 0.870151121378381,
+      "grad_norm": 0.2704218327999115,
+      "learning_rate": 4.376997004524541e-07,
+      "loss": 0.7926,
+      "step": 2260
+    },
+    {
+      "epoch": 0.8740013475791703,
+      "grad_norm": 0.2600269019603729,
+      "learning_rate": 4.12540435970073e-07,
+      "loss": 0.8049,
+      "step": 2270
+    },
+    {
+      "epoch": 0.8778515737799596,
+      "grad_norm": 0.25159603357315063,
+      "learning_rate": 3.880946978614703e-07,
+      "loss": 0.8113,
+      "step": 2280
+    },
+    {
+      "epoch": 0.8817017999807488,
+      "grad_norm": 0.26296156644821167,
+      "learning_rate": 3.643662883789878e-07,
+      "loss": 0.8186,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8855520261815382,
+      "grad_norm": 0.23490454256534576,
+      "learning_rate": 3.41358898202781e-07,
+      "loss": 0.7946,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8894022523823275,
+      "grad_norm": 0.24461697041988373,
+      "learning_rate": 3.190761058667741e-07,
+      "loss": 0.8057,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8932524785831167,
+      "grad_norm": 0.24544700980186462,
+      "learning_rate": 2.9752137720206463e-07,
+      "loss": 0.8134,
+      "step": 2320
+    },
+    {
+      "epoch": 0.8971027047839061,
+      "grad_norm": 0.2598903179168701,
+      "learning_rate": 2.7669806479785067e-07,
+      "loss": 0.8169,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9009529309846953,
+      "grad_norm": 0.2675010561943054,
+      "learning_rate": 2.566094074799763e-07,
+      "loss": 0.813,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9048031571854847,
+      "grad_norm": 0.24954746663570404,
+      "learning_rate": 2.3725852980716557e-07,
+      "loss": 0.7918,
+      "step": 2350
+    },
+    {
+      "epoch": 0.908653383386274,
+      "grad_norm": 0.2450980395078659,
+      "learning_rate": 2.1864844158503983e-07,
+      "loss": 0.8051,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9125036095870632,
+      "grad_norm": 0.28384408354759216,
+      "learning_rate": 2.007820373979702e-07,
+      "loss": 0.7968,
+      "step": 2370
+    },
+    {
+      "epoch": 0.9163538357878526,
+      "grad_norm": 0.2600160539150238,
+      "learning_rate": 1.8366209615886532e-07,
+      "loss": 0.8057,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9202040619886418,
+      "grad_norm": 0.2505420446395874,
+      "learning_rate": 1.6729128067693613e-07,
+      "loss": 0.8145,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9240542881894311,
+      "grad_norm": 0.2665855586528778,
+      "learning_rate": 1.5167213724353426e-07,
+      "loss": 0.8165,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9279045143902205,
+      "grad_norm": 0.25142332911491394,
+      "learning_rate": 1.3680709523610058e-07,
+      "loss": 0.7996,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9317547405910097,
+      "grad_norm": 0.24778512120246887,
+      "learning_rate": 1.2269846674030418e-07,
+      "loss": 0.822,
+      "step": 2420
+    },
+    {
+      "epoch": 0.935604966791799,
+      "grad_norm": 0.25996315479278564,
+      "learning_rate": 1.0934844619042595e-07,
+      "loss": 0.8186,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9394551929925883,
+      "grad_norm": 0.2621021568775177,
+      "learning_rate": 9.675911002803961e-08,
+      "loss": 0.8078,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9433054191933776,
+      "grad_norm": 0.27563199400901794,
+      "learning_rate": 8.493241637904381e-08,
+      "loss": 0.8054,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9471556453941669,
+      "grad_norm": 0.2631632387638092,
+      "learning_rate": 7.387020474909689e-08,
+      "loss": 0.8243,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9510058715949562,
+      "grad_norm": 0.2770576775074005,
+      "learning_rate": 6.357419573750856e-08,
+      "loss": 0.8196,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9548560977957455,
+      "grad_norm": 0.26730117201805115,
+      "learning_rate": 5.4045990769613365e-08,
+      "loss": 0.8028,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9587063239965348,
+      "grad_norm": 0.30196863412857056,
+      "learning_rate": 4.5287071847694434e-08,
+      "loss": 0.8077,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9625565501973241,
+      "grad_norm": 0.24815882742404938,
+      "learning_rate": 3.7298801320467817e-08,
+      "loss": 0.8002,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9664067763981133,
+      "grad_norm": 0.2602055072784424,
+      "learning_rate": 3.0082421671192576e-08,
+      "loss": 0.7938,
+      "step": 2510
+    },
+    {
+      "epoch": 0.9702570025989027,
+      "grad_norm": 0.25386691093444824,
+      "learning_rate": 2.3639055324410355e-08,
+      "loss": 0.8158,
+      "step": 2520
+    },
+    {
+      "epoch": 0.974107228799692,
+      "grad_norm": 0.25517213344573975,
+      "learning_rate": 1.7969704471369477e-08,
+      "loss": 0.8005,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9779574550004813,
+      "grad_norm": 0.24236544966697693,
+      "learning_rate": 1.3075250914142413e-08,
+      "loss": 0.8041,
+      "step": 2540
+    },
+    {
+      "epoch": 0.9818076812012706,
+      "grad_norm": 0.2504887878894806,
+      "learning_rate": 8.956455928476049e-09,
+      "loss": 0.8145,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9856579074020598,
+      "grad_norm": 0.258695513010025,
+      "learning_rate": 5.6139601453786275e-09,
+      "loss": 0.8064,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9895081336028492,
+      "grad_norm": 0.25111350417137146,
+      "learning_rate": 3.0482834514805602e-09,
+      "loss": 0.7936,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9933583598036385,
+      "grad_norm": 0.2394329011440277,
+      "learning_rate": 1.2598249081713366e-09,
+      "loss": 0.7896,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9972085860044277,
+      "grad_norm": 0.2594875693321228,
+      "learning_rate": 2.488626895302826e-10,
+      "loss": 0.8184,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9999037443449803,
+      "step": 2597,
+      "total_flos": 5.144992163406283e+18,
+      "train_loss": 0.8345755722874351,
+      "train_runtime": 13106.0504,
+      "train_samples_per_second": 50.733,
+      "train_steps_per_second": 0.198
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2597,
+  "num_input_tokens_seen": 418855352,
+  "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": 5.144992163406283e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pixio_vith16/finetune/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b74e43d419223ddc5c06d15b3d29d72690bdafbff4ec98426681d1367f361b33
+size 6264

continuous/qwen3/pixio_vith16/finetune/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

continuous/qwen3/pixio_vith16/pretrain/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1280,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pixio",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pixio/pixio-vith16/pixio_vith16.pth",
+  "vocab_size": 151936
+}

continuous/qwen3/pixio_vith16/pretrain/mm_projector.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cf2b61cf208fb8360a97e3cba631a13b9eeddf29a720141e0208474a723508
+size 27281464

continuous/qwen3/pixio_vith16/pretrain/trainer_state.json ADDED Viewed

	@@ -0,0 +1,421 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 6.366962909698486,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 10.2415,
+      "step": 10
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.8550082445144653,
+      "learning_rate": 0.0006785714285714287,
+      "loss": 6.6908,
+      "step": 20
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.11682027578353882,
+      "learning_rate": 0.0009999907688176173,
+      "loss": 5.2014,
+      "step": 30
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.09595301747322083,
+      "learning_rate": 0.0009988834393115766,
+      "loss": 4.8833,
+      "step": 40
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.07158678770065308,
+      "learning_rate": 0.0009959345572940772,
+      "loss": 4.7705,
+      "step": 50
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.07049180567264557,
+      "learning_rate": 0.0009911550081155983,
+      "loss": 4.7171,
+      "step": 60
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.09211641550064087,
+      "learning_rate": 0.0009845624347566433,
+      "loss": 4.6657,
+      "step": 70
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.12747718393802643,
+      "learning_rate": 0.0009761811727013547,
+      "loss": 4.6402,
+      "step": 80
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.11239485442638397,
+      "learning_rate": 0.0009660421601067666,
+      "loss": 4.5972,
+      "step": 90
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.0866122841835022,
+      "learning_rate": 0.0009541828235992926,
+      "loss": 4.5763,
+      "step": 100
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.16907548904418945,
+      "learning_rate": 0.0009406469401200151,
+      "loss": 4.5459,
+      "step": 110
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.14272913336753845,
+      "learning_rate": 0.0009254844753287492,
+      "loss": 4.5308,
+      "step": 120
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.1099933460354805,
+      "learning_rate": 0.0009087513991633924,
+      "loss": 4.5023,
+      "step": 130
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.1346324235200882,
+      "learning_rate": 0.0008905094792353917,
+      "loss": 4.4817,
+      "step": 140
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.09965494275093079,
+      "learning_rate": 0.0008708260528239789,
+      "loss": 4.4736,
+      "step": 150
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.13058359920978546,
+      "learning_rate": 0.0008497737783108237,
+      "loss": 4.4576,
+      "step": 160
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.11693127453327179,
+      "learning_rate": 0.0008274303669726426,
+      "loss": 4.4419,
+      "step": 170
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.14802990853786469,
+      "learning_rate": 0.0008038782961218137,
+      "loss": 4.429,
+      "step": 180
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.10790305584669113,
+      "learning_rate": 0.000779204504653894,
+      "loss": 4.4249,
+      "step": 190
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.08258617669343948,
+      "learning_rate": 0.0007535000721258791,
+      "loss": 4.4018,
+      "step": 200
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.1219879686832428,
+      "learning_rate": 0.00072685988254984,
+      "loss": 4.3934,
+      "step": 210
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.09669341146945953,
+      "learning_rate": 0.0006993822741429906,
+      "loss": 4.4033,
+      "step": 220
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.10991968214511871,
+      "learning_rate": 0.0006711686763270818,
+      "loss": 4.4004,
+      "step": 230
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.0956064984202385,
+      "learning_rate": 0.0006423232353170831,
+      "loss": 4.3854,
+      "step": 240
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.10963226109743118,
+      "learning_rate": 0.0006129524296812335,
+      "loss": 4.3657,
+      "step": 250
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.1008874699473381,
+      "learning_rate": 0.0005831646772915651,
+      "loss": 4.3796,
+      "step": 260
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.08525964617729187,
+      "learning_rate": 0.0005530699351157809,
+      "loss": 4.3561,
+      "step": 270
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.11065991222858429,
+      "learning_rate": 0.0005227792933277943,
+      "loss": 4.3561,
+      "step": 280
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.09809140115976334,
+      "learning_rate": 0.0004924045652352092,
+      "loss": 4.3406,
+      "step": 290
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.09466829895973206,
+      "learning_rate": 0.0004620578745374633,
+      "loss": 4.3383,
+      "step": 300
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.1372118592262268,
+      "learning_rate": 0.0004318512414382059,
+      "loss": 4.3541,
+      "step": 310
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.08816927671432495,
+      "learning_rate": 0.0004018961691397148,
+      "loss": 4.3432,
+      "step": 320
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.07733528316020966,
+      "learning_rate": 0.0003723032322457458,
+      "loss": 4.323,
+      "step": 330
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.0884539932012558,
+      "learning_rate": 0.0003431816685921625,
+      "loss": 4.3247,
+      "step": 340
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.09453228861093521,
+      "learning_rate": 0.0003146389760120416,
+      "loss": 4.3335,
+      "step": 350
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.07507588714361191,
+      "learning_rate": 0.00028678051552373485,
+      "loss": 4.3381,
+      "step": 360
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.07539627701044083,
+      "learning_rate": 0.0002597091224066581,
+      "loss": 4.3181,
+      "step": 370
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.08389376848936081,
+      "learning_rate": 0.0002335247266004629,
+      "loss": 4.3355,
+      "step": 380
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.10362039506435394,
+      "learning_rate": 0.000208323983828828,
+      "loss": 4.3166,
+      "step": 390
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.07715170085430145,
+      "learning_rate": 0.0001841999188095224,
+      "loss": 4.3173,
+      "step": 400
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.08651094883680344,
+      "learning_rate": 0.00016124158186777676,
+      "loss": 4.3194,
+      "step": 410
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.09547345340251923,
+      "learning_rate": 0.0001395337202205211,
+      "loss": 4.3099,
+      "step": 420
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.07910577207803726,
+      "learning_rate": 0.00011915646514489292,
+      "loss": 4.3164,
+      "step": 430
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08254032582044601,
+      "learning_rate": 0.00010018503618578818,
+      "loss": 4.3199,
+      "step": 440
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.07713238149881363,
+      "learning_rate": 8.268946349432583e-05,
+      "loss": 4.3134,
+      "step": 450
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.06877965480089188,
+      "learning_rate": 6.673432932217117e-05,
+      "loss": 4.3058,
+      "step": 460
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.068770632147789,
+      "learning_rate": 5.2378529625954684e-05,
+      "loss": 4.294,
+      "step": 470
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.06582632660865784,
+      "learning_rate": 3.9675056661785556e-05,
+      "loss": 4.3043,
+      "step": 480
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.06618043780326843,
+      "learning_rate": 2.8670803372379538e-05,
+      "loss": 4.304,
+      "step": 490
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.06039930135011673,
+      "learning_rate": 1.9406390288876586e-05,
+      "loss": 4.3173,
+      "step": 500
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.06300649791955948,
+      "learning_rate": 1.191601558631461e-05,
+      "loss": 4.3045,
+      "step": 510
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.0640655905008316,
+      "learning_rate": 6.2273288462559305e-06,
+      "loss": 4.297,
+      "step": 520
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.06175054609775543,
+      "learning_rate": 2.361328992552314e-06,
+      "loss": 4.2981,
+      "step": 530
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.06396598368883133,
+      "learning_rate": 3.322867770044202e-07,
+      "loss": 4.3045,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 3.917998631147274e+17,
+      "train_loss": 4.571889306864607,
+      "train_runtime": 5105.0793,
+      "train_samples_per_second": 109.328,
+      "train_steps_per_second": 0.107
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 545,
+  "num_input_tokens_seen": 31896544,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.917998631147274e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

continuous/qwen3/pixio_vitl16/finetune/added_tokens.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

continuous/qwen3/pixio_vitl16/finetune/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,89 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

continuous/qwen3/pixio_vitl16/finetune/config.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 40960,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1024,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 0.0001,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "vtb_ssl:pixio",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": "/cache/ckpt/download/tokenizer/continuous/pixio/pixio-vitl16/pixio_vitl16.pth",
+  "vocab_size": 151936
+}

continuous/qwen3/pixio_vitl16/finetune/generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}