Add files using upload-large-folder tool

.gitattributes

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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

args.json

@@ -0,0 +1,329 @@
+{
+  "model": "google/gemma-3-12b-it",
+  "model_type": "gemma3_vision",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "sdpa",
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "gemma3_vision",
+  "system": null,
+  "max_length": 4096,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "response_prefix": null,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "use_chat_template": true,
+  "template_backend": "swift",
+  "dataset": [
+    "kaamd/translation-instructions"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "data_seed": 42,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "remove_unused_columns": true,
+  "model_name": [
+    "xyz"
+  ],
+  "model_author": [
+    "kaamd"
+  ],
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": null,
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "use_hf": true,
+  "hub_token": null,
+  "custom_register_path": [],
+  "ddp_timeout": 1800,
+  "ddp_backend": null,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "output_dir": "/workspace/output/v1-20250525-165028",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "eval_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 2,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 16,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 1.0,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/workspace/output/v1-20250525-165028/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 256,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 1000.0,
+  "save_total_limit": 2,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": -1,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": null,
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 16,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/workspace/output/v1-20250525-165028",
+  "disable_tqdm": null,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": "",
+  "fsdp_min_num_params": 0,
+  "fsdp_config": null,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": true,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "max_epochs": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "acc_steps": 1,
+  "eval_use_evalscope": false,
+  "eval_datasets": [],
+  "eval_limit": null,
+  "eval_datasets_args": null,
+  "eval_generation_config": null,
+  "freeze_parameters": [
+    "vision_tower",
+    "multi_modal_projector"
+  ],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": null,
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "resume_only_model": false,
+  "create_checkpoint_symlink": false,
+  "packing": false,
+  "lazy_tokenize": true,
+  "loss_type": null,
+  "optimizer": null,
+  "metric": null,
+  "zero_hpz_partition_size": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "gemma-3-12b-it",
+  "model_info": "ModelInfo(model_type='gemma3_vision', model_dir='/workspace/hf_artifacts/hub/models--google--gemma-3-12b-it/snapshots/96b6f1eccf38110c56df3a15bffe176da04bfd80', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling={'factor': 8.0, 'rope_type': 'linear'}, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='gemma3_vision', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/gemma-3-4b-pt', hf_model_id='google/gemma-3-4b-pt', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-4b-it', hf_model_id='google/gemma-3-4b-it', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-12b-pt', hf_model_id='google/gemma-3-12b-pt', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-12b-it', hf_model_id='google/gemma-3-12b-it', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-27b-pt', hf_model_id='google/gemma-3-27b-pt', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-27b-it', hf_model_id='google/gemma-3-27b-it', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='gemma3_vision', get_function=<function get_model_tokenizer_gemma3_vision at 0x7871341a8720>, model_arch='gemma3_vision', architectures=['Gemma3ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49'], tags=[])",
+  "model_dir": "/workspace/hf_artifacts/hub/models--google--gemma-3-12b-it/snapshots/96b6f1eccf38110c56df3a15bffe176da04bfd80",
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "no",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/output/v1-20250525-165028', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/output/v1-20250525-165028/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=256, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=1000, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=None, dataloader_num_workers=16, dataloader_prefetch_factor=10, past_index=-1, run_name='/workspace/output/v1-20250525-165028', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "hidden_size": 3840,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "keys_to_ignore_at_inference": [
+    "past_key_values"
+  ],
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "pad_token_id": 0,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8234b624ed30cd1009c18eec6b17e69b871677bf0961bd4f536d74fb0174fbcd
+size 4979904832

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f19f2546b9d41ea08ec4def7877b753e8fe5d4287e8129f74f6195ba779b5ec
+size 4931296592

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ce9c5c38ea2a90ad745c6a80ac8e6aaffb1a590de31d3778b05cd5719da50d
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3245beec71bc3153b7d476e8a1216fa9130c72bfa6e156ca8d59c75f8e6ca6
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165b8fa83e095850c6e2e264a85bd3867c9e20139e8007a2e6bf20262bafe2d4
+size 4601000928

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d74ecc63752cb05678942ce33dabb293ccd77343f71ae62f596e9a671395eb
+size 47064687693

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957c30050b1e3bbdade4a005f33adfc511222834de98cb984f534ec4c7979a10
+size 1465

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8737651998737894,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.708502220819883e-05,
+      "grad_norm": 96.5,
+      "learning_rate": 1.9379844961240311e-07,
+      "loss": 4.2495036125183105,
+      "memory(GiB)": 112.92,
+      "step": 1,
+      "token_acc": 0.40126382306477093,
+      "train_speed(iter/s)": 0.130363
+    },
+    {
+      "epoch": 0.0248537656852989,
+      "grad_norm": 6.84375,
+      "learning_rate": 4.96124031007752e-05,
+      "loss": 2.0199908088235294,
+      "memory(GiB)": 138.16,
+      "step": 256,
+      "token_acc": 0.5958056756256362,
+      "train_speed(iter/s)": 0.135217
+    },
+    {
+      "epoch": 0.0497075313705978,
+      "grad_norm": 2.6875,
+      "learning_rate": 9.92248062015504e-05,
+      "loss": 1.4577598571777344,
+      "memory(GiB)": 138.17,
+      "step": 512,
+      "token_acc": 0.6785023086521644,
+      "train_speed(iter/s)": 0.135385
+    },
+    {
+      "epoch": 0.0745612970558967,
+      "grad_norm": 2.296875,
+      "learning_rate": 9.983643805989245e-05,
+      "loss": 1.4217802286148071,
+      "memory(GiB)": 138.17,
+      "step": 768,
+      "token_acc": 0.6849496734466487,
+      "train_speed(iter/s)": 0.134581
+    },
+    {
+      "epoch": 0.0994150627411956,
+      "grad_norm": 1.8984375,
+      "learning_rate": 9.933643638247476e-05,
+      "loss": 1.3426355123519897,
+      "memory(GiB)": 138.17,
+      "step": 1024,
+      "token_acc": 0.699673728686982,
+      "train_speed(iter/s)": 0.132515
+    },
+    {
+      "epoch": 0.1242688284264945,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.850332959964666e-05,
+      "loss": 1.2444982528686523,
+      "memory(GiB)": 138.17,
+      "step": 1280,
+      "token_acc": 0.7187271993751019,
+      "train_speed(iter/s)": 0.133056
+    },
+    {
+      "epoch": 0.1491225941117934,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.73427426033351e-05,
+      "loss": 1.1624003648757935,
+      "memory(GiB)": 138.17,
+      "step": 1536,
+      "token_acc": 0.7339836063834865,
+      "train_speed(iter/s)": 0.133627
+    },
+    {
+      "epoch": 0.1739763597970923,
+      "grad_norm": 1.7421875,
+      "learning_rate": 9.58625113355353e-05,
+      "loss": 1.095345377922058,
+      "memory(GiB)": 138.17,
+      "step": 1792,
+      "token_acc": 0.7477444378213578,
+      "train_speed(iter/s)": 0.133066
+    },
+    {
+      "epoch": 0.1988301254823912,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.407262988233549e-05,
+      "loss": 1.0396682024002075,
+      "memory(GiB)": 138.17,
+      "step": 2048,
+      "token_acc": 0.7577293820771361,
+      "train_speed(iter/s)": 0.132805
+    },
+    {
+      "epoch": 0.2236838911676901,
+      "grad_norm": 2.078125,
+      "learning_rate": 9.19851829967875e-05,
+      "loss": 0.9765125513076782,
+      "memory(GiB)": 138.17,
+      "step": 2304,
+      "token_acc": 0.7712227904219364,
+      "train_speed(iter/s)": 0.133242
+    },
+    {
+      "epoch": 0.248537656852989,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.961426450620912e-05,
+      "loss": 0.920336127281189,
+      "memory(GiB)": 138.17,
+      "step": 2560,
+      "token_acc": 0.7830755957422817,
+      "train_speed(iter/s)": 0.133383
+    },
+    {
+      "epoch": 0.2733914225382879,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.69758821548079e-05,
+      "loss": 0.8801365494728088,
+      "memory(GiB)": 138.17,
+      "step": 2816,
+      "token_acc": 0.7913349866408025,
+      "train_speed(iter/s)": 0.133433
+    },
+    {
+      "epoch": 0.2982451882235868,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.408784952410122e-05,
+      "loss": 0.8334779739379883,
+      "memory(GiB)": 138.17,
+      "step": 3072,
+      "token_acc": 0.8006175937055493,
+      "train_speed(iter/s)": 0.132889
+    },
+    {
+      "epoch": 0.3230989539088857,
+      "grad_norm": 1.6875,
+      "learning_rate": 8.096966576085406e-05,
+      "loss": 0.7884229421615601,
+      "memory(GiB)": 138.17,
+      "step": 3328,
+      "token_acc": 0.8102322071595001,
+      "train_speed(iter/s)": 0.133073
+    },
+    {
+      "epoch": 0.3479527195941846,
+      "grad_norm": 1.4921875,
+      "learning_rate": 7.764238392457582e-05,
+      "loss": 0.7397578954696655,
+      "memory(GiB)": 138.17,
+      "step": 3584,
+      "token_acc": 0.8212528591555482,
+      "train_speed(iter/s)": 0.133335
+    },
+    {
+      "epoch": 0.3728064852794835,
+      "grad_norm": 2.1875,
+      "learning_rate": 7.412846884345582e-05,
+      "loss": 0.7087571024894714,
+      "memory(GiB)": 138.17,
+      "step": 3840,
+      "token_acc": 0.8286589691203703,
+      "train_speed(iter/s)": 0.133468
+    },
+    {
+      "epoch": 0.3976602509647824,
+      "grad_norm": 1.1953125,
+      "learning_rate": 7.045164543845158e-05,
+      "loss": 0.6600534319877625,
+      "memory(GiB)": 138.17,
+      "step": 4096,
+      "token_acc": 0.8389953998490116,
+      "train_speed(iter/s)": 0.133269
+    },
+    {
+      "epoch": 0.4225140166500813,
+      "grad_norm": 1.984375,
+      "learning_rate": 6.663673853960154e-05,
+      "loss": 0.6196721196174622,
+      "memory(GiB)": 138.17,
+      "step": 4352,
+      "token_acc": 0.8484769522886115,
+      "train_speed(iter/s)": 0.133418
+    },
+    {
+      "epoch": 0.4473677823353802,
+      "grad_norm": 1.203125,
+      "learning_rate": 6.270950527607537e-05,
+      "loss": 0.5864973068237305,
+      "memory(GiB)": 138.17,
+      "step": 4608,
+      "token_acc": 0.8560292743162837,
+      "train_speed(iter/s)": 0.133475
+    },
+    {
+      "epoch": 0.4722215480206791,
+      "grad_norm": 1.203125,
+      "learning_rate": 5.86964611716145e-05,
+      "loss": 0.5385364294052124,
+      "memory(GiB)": 138.17,
+      "step": 4864,
+      "token_acc": 0.86720534525908,
+      "train_speed(iter/s)": 0.133422
+    },
+    {
+      "epoch": 0.497075313705978,
+      "grad_norm": 1.359375,
+      "learning_rate": 5.4624701119515856e-05,
+      "loss": 0.49772173166275024,
+      "memory(GiB)": 138.17,
+      "step": 5120,
+      "token_acc": 0.8767477774531491,
+      "train_speed(iter/s)": 0.133344
+    },
+    {
+      "epoch": 0.5219290793912769,
+      "grad_norm": 1.40625,
+      "learning_rate": 5.0521716445882614e-05,
+      "loss": 0.46582430601119995,
+      "memory(GiB)": 138.17,
+      "step": 5376,
+      "token_acc": 0.8850724068459814,
+      "train_speed(iter/s)": 0.13342
+    },
+    {
+      "epoch": 0.5467828450765758,
+      "grad_norm": 1.4140625,
+      "learning_rate": 4.64152092962774e-05,
+      "loss": 0.4441249668598175,
+      "memory(GiB)": 138.17,
+      "step": 5632,
+      "token_acc": 0.8896486479315997,
+      "train_speed(iter/s)": 0.133319
+    },
+    {
+      "epoch": 0.5716366107618747,
+      "grad_norm": 1.8203125,
+      "learning_rate": 4.2332905598984413e-05,
+      "loss": 0.40981537103652954,
+      "memory(GiB)": 138.17,
+      "step": 5888,
+      "token_acc": 0.8990366693094052,
+      "train_speed(iter/s)": 0.133434
+    },
+    {
+      "epoch": 0.5964903764471736,
+      "grad_norm": 1.5234375,
+      "learning_rate": 3.830236786769761e-05,
+      "loss": 0.3865773379802704,
+      "memory(GiB)": 138.17,
+      "step": 6144,
+      "token_acc": 0.9034815882027802,
+      "train_speed(iter/s)": 0.133189
+    },
+    {
+      "epoch": 0.6213441421324725,
+      "grad_norm": 1.03125,
+      "learning_rate": 3.4350809107536214e-05,
+      "loss": 0.36623093485832214,
+      "memory(GiB)": 138.17,
+      "step": 6400,
+      "token_acc": 0.9082446782242596,
+      "train_speed(iter/s)": 0.133233
+    },
+    {
+      "epoch": 0.6461979078177714,
+      "grad_norm": 2.203125,
+      "learning_rate": 3.0504909080839294e-05,
+      "loss": 0.34115397930145264,
+      "memory(GiB)": 138.17,
+      "step": 6656,
+      "token_acc": 0.914435132291292,
+      "train_speed(iter/s)": 0.133334
+    },
+    {
+      "epoch": 0.6710516735030703,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.6790634173258577e-05,
+      "loss": 0.3342404067516327,
+      "memory(GiB)": 138.17,
+      "step": 6912,
+      "token_acc": 0.916860246202295,
+      "train_speed(iter/s)": 0.133453
+    },
+    {
+      "epoch": 0.6959054391883692,
+      "grad_norm": 1.3515625,
+      "learning_rate": 2.323306207636102e-05,
+      "loss": 0.3142353296279907,
+      "memory(GiB)": 138.17,
+      "step": 7168,
+      "token_acc": 0.9221213834353058,
+      "train_speed(iter/s)": 0.133271
+    },
+    {
+      "epoch": 0.7207592048736681,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.9856212470432345e-05,
+      "loss": 0.30621492862701416,
+      "memory(GiB)": 138.17,
+      "step": 7424,
+      "token_acc": 0.9249788937888913,
+      "train_speed(iter/s)": 0.133231
+    },
+    {
+      "epoch": 0.745612970558967,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.6682884850661395e-05,
+      "loss": 0.2921682596206665,
+      "memory(GiB)": 138.17,
+      "step": 7680,
+      "token_acc": 0.9275989615640866,
+      "train_speed(iter/s)": 0.133307
+    },
+    {
+      "epoch": 0.7704667362442659,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.3734504591655495e-05,
+      "loss": 0.2854159474372864,
+      "memory(GiB)": 138.17,
+      "step": 7936,
+      "token_acc": 0.9285902741314146,
+      "train_speed(iter/s)": 0.133282
+    },
+    {
+      "epoch": 0.7953205019295648,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.1030978289613726e-05,
+      "loss": 0.28136610984802246,
+      "memory(GiB)": 138.17,
+      "step": 8192,
+      "token_acc": 0.9303321847535716,
+      "train_speed(iter/s)": 0.132989
+    },
+    {
+      "epoch": 0.8201742676148637,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.590559358845118e-06,
+      "loss": 0.2735920548439026,
+      "memory(GiB)": 138.17,
+      "step": 8448,
+      "token_acc": 0.931173780136838,
+      "train_speed(iter/s)": 0.13298
+    },
+    {
+      "epoch": 0.8450280333001626,
+      "grad_norm": 1.3671875,
+      "learning_rate": 6.4297247900848125e-06,
+      "loss": 0.2691897451877594,
+      "memory(GiB)": 138.17,
+      "step": 8704,
+      "token_acc": 0.9327428202220522,
+      "train_speed(iter/s)": 0.132967
+    },
+    {
+      "epoch": 0.8698817989854615,
+      "grad_norm": 1.5234375,
+      "learning_rate": 4.563063902699582e-06,
+      "loss": 0.26750853657722473,
+      "memory(GiB)": 138.17,
+      "step": 8960,
+      "token_acc": 0.9330804530345964,
+      "train_speed(iter/s)": 0.132959
+    }
+  ],
+  "logging_steps": 256,
+  "max_steps": 10301,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1037325459482546e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73152c350c8c2b706a89033781bc1307b4a09a80c865a2fefafcd6f1d2840cf
+size 6289