Training in progress, step 120, checkpoint

.gitattributes

@@ -39,3 +39,4 @@ checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-120/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/medgemma-4b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/medgemma-4b-it
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.16.0

checkpoint-120/adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/medgemma-4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "o_proj",
+    "fc2",
+    "out_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f5e32520f602559d1812b9b759f89623aa7e9d2bf3d127cd4cf3725feb3c23
+size 2839126480

checkpoint-120/added_tokens.json

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

checkpoint-120/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 -%}

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896c1fdb6e3a11b4931131ee22f573a38df4f8305dd1afeaf7674880d997f47e
+size 5678690152

checkpoint-120/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
+  }
+}

checkpoint-120/processor_config.json

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

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8e35257b925609abb03a76ad395821029b9b299dc630b06e0b1c249a47cf0a
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359035db901350e6692bfa0c1e8308dbca72b6327cca2b50042a03782c5d81f7
+size 1064

checkpoint-120/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
+  }
+}

checkpoint-120/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebf1915455f8237564395182c49e3c685cfe3533b3d50ec6d49ce65ec43c32e
+size 33384723

checkpoint-120/tokenizer.model

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

checkpoint-120/trainer_state.json

@@ -0,0 +1,262 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3076923076923075,
+  "eval_steps": 10,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 21.498493194580078,
+      "learning_rate": 0.00019470198675496689,
+      "loss": 14.4551,
+      "mean_token_accuracy": 0.6612499989569187,
+      "num_tokens": 49120.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "eval_loss": 1.0248602628707886,
+      "eval_mean_token_accuracy": 0.8969230560156015,
+      "eval_num_tokens": 49120.0,
+      "eval_runtime": 17.9265,
+      "eval_samples_per_second": 2.789,
+      "eval_steps_per_second": 0.725,
+      "step": 10
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 6.777862071990967,
+      "learning_rate": 0.00018145695364238411,
+      "loss": 2.185,
+      "mean_token_accuracy": 0.9445000052452087,
+      "num_tokens": 98240.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "eval_loss": 0.13720029592514038,
+      "eval_mean_token_accuracy": 0.9761538688953106,
+      "eval_num_tokens": 98240.0,
+      "eval_runtime": 17.8731,
+      "eval_samples_per_second": 2.797,
+      "eval_steps_per_second": 0.727,
+      "step": 20
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 4.832788467407227,
+      "learning_rate": 0.00016821192052980132,
+      "loss": 0.2858,
+      "mean_token_accuracy": 0.9777500212192536,
+      "num_tokens": 147360.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "eval_loss": 0.03728929162025452,
+      "eval_mean_token_accuracy": 0.9765384839131281,
+      "eval_num_tokens": 147360.0,
+      "eval_runtime": 18.2308,
+      "eval_samples_per_second": 2.743,
+      "eval_steps_per_second": 0.713,
+      "step": 30
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 6.547402858734131,
+      "learning_rate": 0.00015496688741721855,
+      "loss": 0.1824,
+      "mean_token_accuracy": 0.9781250208616257,
+      "num_tokens": 196480.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "eval_loss": 0.05031127855181694,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 196480.0,
+      "eval_runtime": 17.8889,
+      "eval_samples_per_second": 2.795,
+      "eval_steps_per_second": 0.727,
+      "step": 40
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 4.728590965270996,
+      "learning_rate": 0.00014172185430463575,
+      "loss": 0.1721,
+      "mean_token_accuracy": 0.9783750206232071,
+      "num_tokens": 245600.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "eval_loss": 0.04732300713658333,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 245600.0,
+      "eval_runtime": 18.0023,
+      "eval_samples_per_second": 2.777,
+      "eval_steps_per_second": 0.722,
+      "step": 50
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.990704894065857,
+      "learning_rate": 0.00012847682119205298,
+      "loss": 0.1396,
+      "mean_token_accuracy": 0.9791250199079513,
+      "num_tokens": 294413.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "eval_loss": 0.040356263518333435,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 294413.0,
+      "eval_runtime": 17.8824,
+      "eval_samples_per_second": 2.796,
+      "eval_steps_per_second": 0.727,
+      "step": 60
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 0.9954031109809875,
+      "learning_rate": 0.0001152317880794702,
+      "loss": 0.1391,
+      "mean_token_accuracy": 0.9780000209808349,
+      "num_tokens": 343533.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "eval_loss": 0.03649154305458069,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 343533.0,
+      "eval_runtime": 18.0872,
+      "eval_samples_per_second": 2.764,
+      "eval_steps_per_second": 0.719,
+      "step": 70
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.5908142328262329,
+      "learning_rate": 0.00010198675496688744,
+      "loss": 0.1376,
+      "mean_token_accuracy": 0.9785000190138817,
+      "num_tokens": 392653.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 0.03940116986632347,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 392653.0,
+      "eval_runtime": 17.8649,
+      "eval_samples_per_second": 2.799,
+      "eval_steps_per_second": 0.728,
+      "step": 80
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 1.166898250579834,
+      "learning_rate": 8.874172185430464e-05,
+      "loss": 0.1379,
+      "mean_token_accuracy": 0.9782500207424164,
+      "num_tokens": 441773.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "eval_loss": 0.03707318380475044,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 441773.0,
+      "eval_runtime": 18.0365,
+      "eval_samples_per_second": 2.772,
+      "eval_steps_per_second": 0.721,
+      "step": 90
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.38323092460632324,
+      "learning_rate": 7.549668874172185e-05,
+      "loss": 0.1415,
+      "mean_token_accuracy": 0.9765000149607659,
+      "num_tokens": 490893.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "eval_loss": 0.036779891699552536,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 490893.0,
+      "eval_runtime": 17.8928,
+      "eval_samples_per_second": 2.794,
+      "eval_steps_per_second": 0.727,
+      "step": 100
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 1.039596676826477,
+      "learning_rate": 6.225165562913907e-05,
+      "loss": 0.1391,
+      "mean_token_accuracy": 0.9800000190734863,
+      "num_tokens": 539706.0,
+      "step": 110
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "eval_loss": 0.036059826612472534,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 539706.0,
+      "eval_runtime": 17.9952,
+      "eval_samples_per_second": 2.779,
+      "eval_steps_per_second": 0.722,
+      "step": 110
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.8448509573936462,
+      "learning_rate": 4.900662251655629e-05,
+      "loss": 0.1347,
+      "mean_token_accuracy": 0.9772500187158585,
+      "num_tokens": 588826.0,
+      "step": 120
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "eval_loss": 0.035431090742349625,
+      "eval_mean_token_accuracy": 0.9769230989309458,
+      "eval_num_tokens": 588826.0,
+      "eval_runtime": 17.9637,
+      "eval_samples_per_second": 2.783,
+      "eval_steps_per_second": 0.724,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 156,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5311331998394432e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652c8ce42c66ba23561de837fae1da08a712795400ecc170511dcf7fa6b44940
+size 5816