Upload model

.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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 71987160678400.0,
+    "train_loss": 0.33997809361009035,
+    "train_runtime": 8691.2958,
+    "train_samples_per_second": 0.739,
+    "train_steps_per_second": 0.006
+}

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 +1,64 @@
+{
+  "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,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "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": "float32",
+    "use_cache": false,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "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": "float32",
+    "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": "4.52.4"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a088a948680b9dd9dda3d4a1a96ddbb4cac8ddeb7fd24dc8df7b8cb177a69f4d
+size 4979902192

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3a1f7a5855700d3f684b49d52d960d764e16fcd4f60b8bd081f0b250d14ef1
+size 4931296592

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b461d0da4e0584bc6451e5ade89e4e0de4137a538963f77e24eb67e63f55cae
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe3ded71d8f61e613dee35fbf3d17e0b801134bcb2dd857ff80105678f5ac96
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33175a835f5438609dfb3e1ae33cf4cb7a180ae0211a4af0f8ca3595862866d
+size 4601000928

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"
+}

runs/Jun06_20-42-42_node9/events.out.tfevents.1749210393.node9.1568093.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c38aaa8a3189d04a013baffa8893b3384d432d7905942956bf71e163f30db7f
+size 7823

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": "<end_of_turn>",
+    "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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 71987160678400.0,
+    "train_loss": 0.33997809361009035,
+    "train_runtime": 8691.2958,
+    "train_samples_per_second": 0.739,
+    "train_steps_per_second": 0.006
+}

trainer_log.jsonl

@@ -0,0 +1,6 @@
+{"current_steps": 10, "total_steps": 51, "loss": 0.6594, "lr": 9.890738003669029e-06, "epoch": 0.19900497512437812, "percentage": 19.61, "elapsed_time": "0:28:38", "remaining_time": "1:57:26"}
+{"current_steps": 20, "total_steps": 51, "loss": 0.2957, "lr": 8.078307376628292e-06, "epoch": 0.39800995024875624, "percentage": 39.22, "elapsed_time": "0:57:08", "remaining_time": "1:28:34"}
+{"current_steps": 30, "total_steps": 51, "loss": 0.2682, "lr": 4.825502516487497e-06, "epoch": 0.5970149253731343, "percentage": 58.82, "elapsed_time": "1:26:02", "remaining_time": "1:00:13"}
+{"current_steps": 40, "total_steps": 51, "loss": 0.2472, "lr": 1.6543469682057105e-06, "epoch": 0.7960199004975125, "percentage": 78.43, "elapsed_time": "1:54:36", "remaining_time": "0:31:30"}
+{"current_steps": 50, "total_steps": 51, "loss": 0.257, "lr": 4.865965629214819e-08, "epoch": 0.9950248756218906, "percentage": 98.04, "elapsed_time": "2:23:05", "remaining_time": "0:02:51"}
+{"current_steps": 51, "total_steps": 51, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:24:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 51,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 1.2696179151535034,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.6594,
+      "step": 10
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 1.0009506940841675,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 0.2957,
+      "step": 20
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.816304624080658,
+      "learning_rate": 4.825502516487497e-06,
+      "loss": 0.2682,
+      "step": 30
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 0.7167808413505554,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 0.2472,
+      "step": 40
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 0.7434136271476746,
+      "learning_rate": 4.865965629214819e-08,
+      "loss": 0.257,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "step": 51,
+      "total_flos": 71987160678400.0,
+      "train_loss": 0.33997809361009035,
+      "train_runtime": 8691.2958,
+      "train_samples_per_second": 0.739,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 51,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 71987160678400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3748a3be49393d59a787ffd249850f0e6ab1cc5a85e2f2af33c56894ac05e22
+size 8145