Training in progress, epoch 1
Browse files- .gitattributes +1 -0
 - adapter_config.json +45 -0
 - adapter_model.safetensors +3 -0
 - added_tokens.json +3 -0
 - chat_template.jinja +47 -0
 - preprocessor_config.json +29 -0
 - processor_config.json +4 -0
 - runs/May28_07-18-03_7e6b4d0f2b96/events.out.tfevents.1748416699.7e6b4d0f2b96.655.0 +3 -0
 - special_tokens_map.json +33 -0
 - tokenizer.json +3 -0
 - tokenizer.model +3 -0
 - tokenizer_config.json +0 -0
 - training_args.bin +3 -0
 
    	
        .gitattributes
    CHANGED
    
    | 
         @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
     | 
|
| 33 | 
         
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         
     | 
| 34 | 
         
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         
     | 
| 35 | 
         
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         
     | 
| 
         | 
| 
         | 
|
| 33 | 
         
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         
     | 
| 34 | 
         
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         
     | 
| 35 | 
         
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         
     | 
| 36 | 
         
            +
            tokenizer.json filter=lfs diff=lfs merge=lfs -text
         
     | 
    	
        adapter_config.json
    ADDED
    
    | 
         @@ -0,0 +1,45 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "alpha_pattern": {},
         
     | 
| 3 | 
         
            +
              "auto_mapping": null,
         
     | 
| 4 | 
         
            +
              "base_model_name_or_path": "google/medgemma-4b-it",
         
     | 
| 5 | 
         
            +
              "bias": "none",
         
     | 
| 6 | 
         
            +
              "corda_config": null,
         
     | 
| 7 | 
         
            +
              "eva_config": null,
         
     | 
| 8 | 
         
            +
              "exclude_modules": null,
         
     | 
| 9 | 
         
            +
              "fan_in_fan_out": false,
         
     | 
| 10 | 
         
            +
              "inference_mode": true,
         
     | 
| 11 | 
         
            +
              "init_lora_weights": true,
         
     | 
| 12 | 
         
            +
              "layer_replication": null,
         
     | 
| 13 | 
         
            +
              "layers_pattern": null,
         
     | 
| 14 | 
         
            +
              "layers_to_transform": null,
         
     | 
| 15 | 
         
            +
              "loftq_config": {},
         
     | 
| 16 | 
         
            +
              "lora_alpha": 16,
         
     | 
| 17 | 
         
            +
              "lora_bias": false,
         
     | 
| 18 | 
         
            +
              "lora_dropout": 0.05,
         
     | 
| 19 | 
         
            +
              "megatron_config": null,
         
     | 
| 20 | 
         
            +
              "megatron_core": "megatron.core",
         
     | 
| 21 | 
         
            +
              "modules_to_save": [
         
     | 
| 22 | 
         
            +
                "lm_head",
         
     | 
| 23 | 
         
            +
                "embed_tokens"
         
     | 
| 24 | 
         
            +
              ],
         
     | 
| 25 | 
         
            +
              "peft_type": "LORA",
         
     | 
| 26 | 
         
            +
              "r": 16,
         
     | 
| 27 | 
         
            +
              "rank_pattern": {},
         
     | 
| 28 | 
         
            +
              "revision": null,
         
     | 
| 29 | 
         
            +
              "target_modules": [
         
     | 
| 30 | 
         
            +
                "out_proj",
         
     | 
| 31 | 
         
            +
                "gate_proj",
         
     | 
| 32 | 
         
            +
                "up_proj",
         
     | 
| 33 | 
         
            +
                "down_proj",
         
     | 
| 34 | 
         
            +
                "o_proj",
         
     | 
| 35 | 
         
            +
                "fc2",
         
     | 
| 36 | 
         
            +
                "k_proj",
         
     | 
| 37 | 
         
            +
                "v_proj",
         
     | 
| 38 | 
         
            +
                "q_proj",
         
     | 
| 39 | 
         
            +
                "fc1"
         
     | 
| 40 | 
         
            +
              ],
         
     | 
| 41 | 
         
            +
              "task_type": "CAUSAL_LM",
         
     | 
| 42 | 
         
            +
              "trainable_token_indices": null,
         
     | 
| 43 | 
         
            +
              "use_dora": false,
         
     | 
| 44 | 
         
            +
              "use_rslora": false
         
     | 
| 45 | 
         
            +
            }
         
     | 
    	
        adapter_model.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:d8e23bef34d4f984cae99e950944ab0522753f1d738cc8016d6ddcfbe9023ea2
         
     | 
| 3 | 
         
            +
            size 2839126480
         
     | 
    	
        added_tokens.json
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "<image_soft_token>": 262144
         
     | 
| 3 | 
         
            +
            }
         
     | 
    	
        chat_template.jinja
    ADDED
    
    | 
         @@ -0,0 +1,47 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {{ bos_token }}
         
     | 
| 2 | 
         
            +
            {%- if messages[0]['role'] == 'system' -%}
         
     | 
| 3 | 
         
            +
                {%- if messages[0]['content'] is string -%}
         
     | 
| 4 | 
         
            +
                    {%- set first_user_prefix = messages[0]['content'] + '
         
     | 
| 5 | 
         
            +
             
     | 
| 6 | 
         
            +
            ' -%}
         
     | 
| 7 | 
         
            +
                {%- else -%}
         
     | 
| 8 | 
         
            +
                    {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
         
     | 
| 9 | 
         
            +
             
     | 
| 10 | 
         
            +
            ' -%}
         
     | 
| 11 | 
         
            +
                {%- endif -%}
         
     | 
| 12 | 
         
            +
                {%- set loop_messages = messages[1:] -%}
         
     | 
| 13 | 
         
            +
            {%- else -%}
         
     | 
| 14 | 
         
            +
                {%- set first_user_prefix = "" -%}
         
     | 
| 15 | 
         
            +
                {%- set loop_messages = messages -%}
         
     | 
| 16 | 
         
            +
            {%- endif -%}
         
     | 
| 17 | 
         
            +
            {%- for message in loop_messages -%}
         
     | 
| 18 | 
         
            +
                {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
         
     | 
| 19 | 
         
            +
                    {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
         
     | 
| 20 | 
         
            +
                {%- endif -%}
         
     | 
| 21 | 
         
            +
                {%- if (message['role'] == 'assistant') -%}
         
     | 
| 22 | 
         
            +
                    {%- set role = "model" -%}
         
     | 
| 23 | 
         
            +
                {%- else -%}
         
     | 
| 24 | 
         
            +
                    {%- set role = message['role'] -%}
         
     | 
| 25 | 
         
            +
                {%- endif -%}
         
     | 
| 26 | 
         
            +
                {{ '<start_of_turn>' + role + '
         
     | 
| 27 | 
         
            +
            ' + (first_user_prefix if loop.first else "") }}
         
     | 
| 28 | 
         
            +
                {%- if message['content'] is string -%}
         
     | 
| 29 | 
         
            +
                    {{ message['content'] | trim }}
         
     | 
| 30 | 
         
            +
                {%- elif message['content'] is iterable -%}
         
     | 
| 31 | 
         
            +
                    {%- for item in message['content'] -%}
         
     | 
| 32 | 
         
            +
                        {%- if item['type'] == 'image' -%}
         
     | 
| 33 | 
         
            +
                            {{ '<start_of_image>' }}
         
     | 
| 34 | 
         
            +
                        {%- elif item['type'] == 'text' -%}
         
     | 
| 35 | 
         
            +
                            {{ item['text'] | trim }}
         
     | 
| 36 | 
         
            +
                        {%- endif -%}
         
     | 
| 37 | 
         
            +
                    {%- endfor -%}
         
     | 
| 38 | 
         
            +
                {%- else -%}
         
     | 
| 39 | 
         
            +
                    {{ raise_exception("Invalid content type") }}
         
     | 
| 40 | 
         
            +
                {%- endif -%}
         
     | 
| 41 | 
         
            +
                {{ '<end_of_turn>
         
     | 
| 42 | 
         
            +
            ' }}
         
     | 
| 43 | 
         
            +
            {%- endfor -%}
         
     | 
| 44 | 
         
            +
            {%- if add_generation_prompt -%}
         
     | 
| 45 | 
         
            +
                {{'<start_of_turn>model
         
     | 
| 46 | 
         
            +
            '}}
         
     | 
| 47 | 
         
            +
            {%- endif -%}
         
     | 
    	
        preprocessor_config.json
    ADDED
    
    | 
         @@ -0,0 +1,29 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "do_convert_rgb": null,
         
     | 
| 3 | 
         
            +
              "do_normalize": true,
         
     | 
| 4 | 
         
            +
              "do_pan_and_scan": null,
         
     | 
| 5 | 
         
            +
              "do_rescale": true,
         
     | 
| 6 | 
         
            +
              "do_resize": true,
         
     | 
| 7 | 
         
            +
              "image_mean": [
         
     | 
| 8 | 
         
            +
                0.5,
         
     | 
| 9 | 
         
            +
                0.5,
         
     | 
| 10 | 
         
            +
                0.5
         
     | 
| 11 | 
         
            +
              ],
         
     | 
| 12 | 
         
            +
              "image_processor_type": "Gemma3ImageProcessor",
         
     | 
| 13 | 
         
            +
              "image_seq_length": 256,
         
     | 
| 14 | 
         
            +
              "image_std": [
         
     | 
| 15 | 
         
            +
                0.5,
         
     | 
| 16 | 
         
            +
                0.5,
         
     | 
| 17 | 
         
            +
                0.5
         
     | 
| 18 | 
         
            +
              ],
         
     | 
| 19 | 
         
            +
              "pan_and_scan_max_num_crops": null,
         
     | 
| 20 | 
         
            +
              "pan_and_scan_min_crop_size": null,
         
     | 
| 21 | 
         
            +
              "pan_and_scan_min_ratio_to_activate": null,
         
     | 
| 22 | 
         
            +
              "processor_class": "Gemma3Processor",
         
     | 
| 23 | 
         
            +
              "resample": 2,
         
     | 
| 24 | 
         
            +
              "rescale_factor": 0.00392156862745098,
         
     | 
| 25 | 
         
            +
              "size": {
         
     | 
| 26 | 
         
            +
                "height": 896,
         
     | 
| 27 | 
         
            +
                "width": 896
         
     | 
| 28 | 
         
            +
              }
         
     | 
| 29 | 
         
            +
            }
         
     | 
    	
        processor_config.json
    ADDED
    
    | 
         @@ -0,0 +1,4 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "image_seq_length": 256,
         
     | 
| 3 | 
         
            +
              "processor_class": "Gemma3Processor"
         
     | 
| 4 | 
         
            +
            }
         
     | 
    	
        runs/May28_07-18-03_7e6b4d0f2b96/events.out.tfevents.1748416699.7e6b4d0f2b96.655.0
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:a8ced5e7400d68fe12e6ed751219e97e89cde7e91afbca5c9dd54ba1605b1522
         
     | 
| 3 | 
         
            +
            size 15217
         
     | 
    	
        special_tokens_map.json
    ADDED
    
    | 
         @@ -0,0 +1,33 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "boi_token": "<start_of_image>",
         
     | 
| 3 | 
         
            +
              "bos_token": {
         
     | 
| 4 | 
         
            +
                "content": "<bos>",
         
     | 
| 5 | 
         
            +
                "lstrip": false,
         
     | 
| 6 | 
         
            +
                "normalized": false,
         
     | 
| 7 | 
         
            +
                "rstrip": false,
         
     | 
| 8 | 
         
            +
                "single_word": false
         
     | 
| 9 | 
         
            +
              },
         
     | 
| 10 | 
         
            +
              "eoi_token": "<end_of_image>",
         
     | 
| 11 | 
         
            +
              "eos_token": {
         
     | 
| 12 | 
         
            +
                "content": "<eos>",
         
     | 
| 13 | 
         
            +
                "lstrip": false,
         
     | 
| 14 | 
         
            +
                "normalized": false,
         
     | 
| 15 | 
         
            +
                "rstrip": false,
         
     | 
| 16 | 
         
            +
                "single_word": false
         
     | 
| 17 | 
         
            +
              },
         
     | 
| 18 | 
         
            +
              "image_token": "<image_soft_token>",
         
     | 
| 19 | 
         
            +
              "pad_token": {
         
     | 
| 20 | 
         
            +
                "content": "<pad>",
         
     | 
| 21 | 
         
            +
                "lstrip": false,
         
     | 
| 22 | 
         
            +
                "normalized": false,
         
     | 
| 23 | 
         
            +
                "rstrip": false,
         
     | 
| 24 | 
         
            +
                "single_word": false
         
     | 
| 25 | 
         
            +
              },
         
     | 
| 26 | 
         
            +
              "unk_token": {
         
     | 
| 27 | 
         
            +
                "content": "<unk>",
         
     | 
| 28 | 
         
            +
                "lstrip": false,
         
     | 
| 29 | 
         
            +
                "normalized": false,
         
     | 
| 30 | 
         
            +
                "rstrip": false,
         
     | 
| 31 | 
         
            +
                "single_word": false
         
     | 
| 32 | 
         
            +
              }
         
     | 
| 33 | 
         
            +
            }
         
     | 
    	
        tokenizer.json
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:1ebf1915455f8237564395182c49e3c685cfe3533b3d50ec6d49ce65ec43c32e
         
     | 
| 3 | 
         
            +
            size 33384723
         
     | 
    	
        tokenizer.model
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
         
     | 
| 3 | 
         
            +
            size 4689074
         
     | 
    	
        tokenizer_config.json
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        training_args.bin
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:e4122b8ccedf1d836f67da7b4b7bbc70915a4e960ffd9bb15356ebd5ffc78323
         
     | 
| 3 | 
         
            +
            size 5688
         
     |