Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: peft
+---
+
+# 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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37581067fb5d266b77b4dc0637e3eb926635cfa645cf2cc9ff074bd5f45235f6
+size 238492088

added_tokens.json

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

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 -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb79f8b5de4a02da011164d80aa3ee3260c33f34ce31684f72a43c06cd4caf7
+size 121642438

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfd1d6f91e2b424a94d63c6a65efb6e73df07b6f0951e03ef3030c2256e4eb1
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea8c33528ed85211ccdb7f8564520ece0df82eadcf8eec3cf5d0eb1aa2173a3
+size 1064

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:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
+size 33384722

tokenizer.model

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

trainer_state.json

@@ -0,0 +1,846 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.12625992042012513,
+      "epoch": 0.03571428571428571,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.5207030773162842,
+      "kl": 0.029890698788585725,
+      "learning_rate": 4.8392857142857146e-05,
+      "loss": 0.0003,
+      "num_tokens": 46564.0,
+      "reward": 0.24375,
+      "reward_std": 0.38889276385307314,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.24375,
+      "rewards/format_reward/std": 0.38889277875423434,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.12813723259605467,
+      "epoch": 0.07142857142857142,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.5805707573890686,
+      "kl": 0.14628016483038664,
+      "learning_rate": 4.660714285714286e-05,
+      "loss": 0.0015,
+      "num_tokens": 92372.0,
+      "reward": 0.31875,
+      "reward_std": 0.44964262247085574,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.31875,
+      "rewards/format_reward/std": 0.4496426522731781,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.13213527642656117,
+      "epoch": 0.10714285714285714,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.452333003282547,
+      "kl": 0.14923681337386369,
+      "learning_rate": 4.482142857142857e-05,
+      "loss": 0.0015,
+      "num_tokens": 137784.0,
+      "reward": 0.4125,
+      "reward_std": 0.480369633436203,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.4125,
+      "rewards/format_reward/std": 0.48036965131759646,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.13474671822041273,
+      "epoch": 0.14285714285714285,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.6397606730461121,
+      "kl": 0.17617695135995745,
+      "learning_rate": 4.303571428571429e-05,
+      "loss": 0.0018,
+      "num_tokens": 184512.0,
+      "reward": 0.29375,
+      "reward_std": 0.4483493506908417,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.29375,
+      "rewards/format_reward/std": 0.4483493685722351,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.13772077192552387,
+      "epoch": 0.17857142857142858,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.023568596690893173,
+      "kl": 0.20543135565239937,
+      "learning_rate": 4.125e-05,
+      "loss": 0.0021,
+      "num_tokens": 230810.0,
+      "reward": 0.40625,
+      "reward_std": 0.46784973740577696,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.40625,
+      "rewards/format_reward/std": 0.4678497463464737,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.1001779991784133,
+      "epoch": 0.21428571428571427,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.3460525572299957,
+      "kl": 0.22092539798468352,
+      "learning_rate": 3.946428571428571e-05,
+      "loss": 0.0022,
+      "num_tokens": 276958.0,
+      "reward": 0.63125,
+      "reward_std": 0.4759595632553101,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.63125,
+      "rewards/format_reward/std": 0.4759595781564713,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.09113281725440174,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.27182736992836,
+      "kl": 0.2702178731560707,
+      "learning_rate": 3.767857142857143e-05,
+      "loss": 0.0027,
+      "num_tokens": 322870.0,
+      "reward": 0.74375,
+      "reward_std": 0.4677943289279938,
+      "rewards/accuracy_reward/mean": 0.01875,
+      "rewards/accuracy_reward/std": 0.05915650427341461,
+      "rewards/format_reward/mean": 0.725,
+      "rewards/format_reward/std": 0.44086891412734985,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.07283033218700438,
+      "epoch": 0.2857142857142857,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.4305204153060913,
+      "kl": 0.30486682509072127,
+      "learning_rate": 3.589285714285715e-05,
+      "loss": 0.003,
+      "num_tokens": 368898.0,
+      "reward": 0.875,
+      "reward_std": 0.2758632004261017,
+      "rewards/accuracy_reward/mean": 0.00625,
+      "rewards/accuracy_reward/std": 0.025,
+      "rewards/format_reward/mean": 0.86875,
+      "rewards/format_reward/std": 0.26565522849559786,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.06701735492097213,
+      "epoch": 0.32142857142857145,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 0.007617300376296043,
+      "kl": 0.32528871656395497,
+      "learning_rate": 3.410714285714286e-05,
+      "loss": 0.0033,
+      "num_tokens": 415134.0,
+      "reward": 0.8875,
+      "reward_std": 0.33791992366313933,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.05,
+      "rewards/format_reward/mean": 0.875,
+      "rewards/format_reward/std": 0.31671638786792755,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.06509439181536436,
+      "epoch": 0.35714285714285715,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.010140369646251202,
+      "kl": 0.298904563812539,
+      "learning_rate": 3.2321428571428574e-05,
+      "loss": 0.003,
+      "num_tokens": 460524.0,
+      "reward": 0.9375,
+      "reward_std": 0.2313473641872406,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.034156504273414615,
+      "rewards/format_reward/mean": 0.925,
+      "rewards/format_reward/std": 0.19719087481498718,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.0780115590954665,
+      "epoch": 0.39285714285714285,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.6102597117424011,
+      "kl": 0.314992543682456,
+      "learning_rate": 3.053571428571429e-05,
+      "loss": 0.0031,
+      "num_tokens": 506718.0,
+      "reward": 0.95,
+      "reward_std": 0.2625021517276764,
+      "rewards/accuracy_reward/mean": 0.025,
+      "rewards/accuracy_reward/std": 0.06831300854682923,
+      "rewards/format_reward/mean": 0.925,
+      "rewards/format_reward/std": 0.19418915510177612,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.06869765471710707,
+      "epoch": 0.42857142857142855,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.18664264678955078,
+      "kl": 0.3312602242454886,
+      "learning_rate": 2.8749999999999997e-05,
+      "loss": 0.0033,
+      "num_tokens": 551914.0,
+      "reward": 0.975,
+      "reward_std": 0.23939219117164612,
+      "rewards/accuracy_reward/mean": 0.03125,
+      "rewards/accuracy_reward/std": 0.09331300854682922,
+      "rewards/format_reward/mean": 0.94375,
+      "rewards/format_reward/std": 0.17446779310703278,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.07147310696454952,
+      "epoch": 0.4642857142857143,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.02365143969655037,
+      "kl": 0.35637650578282776,
+      "learning_rate": 2.6964285714285714e-05,
+      "loss": 0.0036,
+      "num_tokens": 597752.0,
+      "reward": 0.95625,
+      "reward_std": 0.17910928130149842,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.034156504273414615,
+      "rewards/format_reward/mean": 0.94375,
+      "rewards/format_reward/std": 0.16162601709365845,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.06830690645729191,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.02468046173453331,
+      "kl": 0.3641864719800651,
+      "learning_rate": 2.5178571428571428e-05,
+      "loss": 0.0036,
+      "num_tokens": 643248.0,
+      "reward": 0.95625,
+      "reward_std": 0.2526991993188858,
+      "rewards/accuracy_reward/mean": 0.025,
+      "rewards/accuracy_reward/std": 0.08415650427341462,
+      "rewards/format_reward/mean": 0.93125,
+      "rewards/format_reward/std": 0.18202786147594452,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.07277907942188903,
+      "epoch": 0.5357142857142857,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.3342110812664032,
+      "kl": 0.35218177605420353,
+      "learning_rate": 2.3392857142857145e-05,
+      "loss": 0.0035,
+      "num_tokens": 689174.0,
+      "reward": 0.96875,
+      "reward_std": 0.2683339625597,
+      "rewards/accuracy_reward/mean": 0.0375,
+      "rewards/accuracy_reward/std": 0.11831300854682922,
+      "rewards/format_reward/mean": 0.93125,
+      "rewards/format_reward/std": 0.21162601709365844,
+      "step": 150
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.07139425584464335,
+      "epoch": 0.5714285714285714,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.021100714802742004,
+      "kl": 0.3498226302675903,
+      "learning_rate": 2.1607142857142858e-05,
+      "loss": 0.0035,
+      "num_tokens": 735904.0,
+      "reward": 1.00625,
+      "reward_std": 0.025,
+      "rewards/accuracy_reward/mean": 0.00625,
+      "rewards/accuracy_reward/std": 0.025,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "step": 160
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.09096196873579174,
+      "epoch": 0.6071428571428571,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.36118584871292114,
+      "kl": 0.3759258924983442,
+      "learning_rate": 1.982142857142857e-05,
+      "loss": 0.0038,
+      "num_tokens": 782492.0,
+      "reward": 0.95,
+      "reward_std": 0.26942057013511655,
+      "rewards/accuracy_reward/mean": 0.025,
+      "rewards/accuracy_reward/std": 0.06831300854682923,
+      "rewards/format_reward/mean": 0.925,
+      "rewards/format_reward/std": 0.217780801653862,
+      "step": 170
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.11560409280937164,
+      "epoch": 0.6428571428571429,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.00570648955181241,
+      "kl": 0.382719272794202,
+      "learning_rate": 1.8035714285714285e-05,
+      "loss": 0.0038,
+      "num_tokens": 829112.0,
+      "reward": 0.98125,
+      "reward_std": 0.12840956151485444,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.05,
+      "rewards/format_reward/mean": 0.96875,
+      "rewards/format_reward/std": 0.09331300854682922,
+      "step": 180
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.10731171959778293,
+      "epoch": 0.6785714285714286,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.012304564006626606,
+      "kl": 0.3598832252435386,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.0036,
+      "num_tokens": 875390.0,
+      "reward": 0.95625,
+      "reward_std": 0.15684083700180054,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.034156504273414615,
+      "rewards/format_reward/mean": 0.94375,
+      "rewards/format_reward/std": 0.13977908194065095,
+      "step": 190
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.1362523474963382,
+      "epoch": 0.7142857142857143,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.5960667729377747,
+      "kl": 0.39577870490029454,
+      "learning_rate": 1.4464285714285717e-05,
+      "loss": 0.004,
+      "num_tokens": 922518.0,
+      "reward": 0.93125,
+      "reward_std": 0.22683832049369812,
+      "rewards/accuracy_reward/mean": 0.01875,
+      "rewards/accuracy_reward/std": 0.075,
+      "rewards/format_reward/mean": 0.9125,
+      "rewards/format_reward/std": 0.19454776644706726,
+      "step": 200
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.10914715133840218,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.006838708650320768,
+      "kl": 0.37330353884026407,
+      "learning_rate": 1.2678571428571429e-05,
+      "loss": 0.0037,
+      "num_tokens": 968198.0,
+      "reward": 0.99375,
+      "reward_std": 0.16918914914131164,
+      "rewards/accuracy_reward/mean": 0.03125,
+      "rewards/accuracy_reward/std": 0.09031128883361816,
+      "rewards/format_reward/mean": 0.9625,
+      "rewards/format_reward/std": 0.07887786626815796,
+      "step": 210
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.11798728982685133,
+      "epoch": 0.7857142857142857,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.020410774275660515,
+      "kl": 0.3922887581400573,
+      "learning_rate": 1.0892857142857144e-05,
+      "loss": 0.0039,
+      "num_tokens": 1014656.0,
+      "reward": 0.9625,
+      "reward_std": 0.1187208503484726,
+      "rewards/accuracy_reward/mean": 0.00625,
+      "rewards/accuracy_reward/std": 0.025,
+      "rewards/format_reward/mean": 0.95625,
+      "rewards/format_reward/std": 0.10862429738044739,
+      "step": 220
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.1181378597393632,
+      "epoch": 0.8214285714285714,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.011710015125572681,
+      "kl": 0.38200892861932517,
+      "learning_rate": 9.107142857142858e-06,
+      "loss": 0.0038,
+      "num_tokens": 1061108.0,
+      "reward": 0.99375,
+      "reward_std": 0.1616260051727295,
+      "rewards/accuracy_reward/mean": 0.025,
+      "rewards/accuracy_reward/std": 0.06831300854682923,
+      "rewards/format_reward/mean": 0.96875,
+      "rewards/format_reward/std": 0.09331300854682922,
+      "step": 230
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.1463294762186706,
+      "epoch": 0.8571428571428571,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.007682339753955603,
+      "kl": 0.40318670785054567,
+      "learning_rate": 7.321428571428572e-06,
+      "loss": 0.004,
+      "num_tokens": 1108338.0,
+      "reward": 0.925,
+      "reward_std": 0.25421872138977053,
+      "rewards/accuracy_reward/mean": 0.01875,
+      "rewards/accuracy_reward/std": 0.05915650427341461,
+      "rewards/format_reward/mean": 0.90625,
+      "rewards/format_reward/std": 0.1950622320175171,
+      "step": 240
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.12144056173274294,
+      "epoch": 0.8928571428571429,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.01580824889242649,
+      "kl": 0.384551886562258,
+      "learning_rate": 5.535714285714285e-06,
+      "loss": 0.0038,
+      "num_tokens": 1153978.0,
+      "reward": 0.9625,
+      "reward_std": 0.16303436160087587,
+      "rewards/accuracy_reward/mean": 0.0125,
+      "rewards/accuracy_reward/std": 0.05,
+      "rewards/format_reward/mean": 0.95,
+      "rewards/format_reward/std": 0.11303437054157257,
+      "step": 250
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.13457293838728218,
+      "epoch": 0.9285714285714286,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.018065791577100754,
+      "kl": 0.38744454458355904,
+      "learning_rate": 3.75e-06,
+      "loss": 0.0039,
+      "num_tokens": 1200028.0,
+      "reward": 0.99375,
+      "reward_std": 0.19331300258636475,
+      "rewards/accuracy_reward/mean": 0.025,
+      "rewards/accuracy_reward/std": 0.06831300854682923,
+      "rewards/format_reward/mean": 0.96875,
+      "rewards/format_reward/std": 0.125,
+      "step": 260
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.12677656556479633,
+      "epoch": 0.9642857142857143,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.008128122426569462,
+      "kl": 0.3681739863939583,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 0.0037,
+      "num_tokens": 1246390.0,
+      "reward": 0.91875,
+      "reward_std": 0.17746950387954713,
+      "rewards/accuracy_reward/mean": 0.0,
+      "rewards/accuracy_reward/std": 0.0,
+      "rewards/format_reward/mean": 0.91875,
+      "rewards/format_reward/std": 0.17746951282024384,
+      "step": 270
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 160.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 160.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 160.0,
+      "completions/min_terminated_length": 0.0,
+      "entropy": 0.1310231292503886,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.3009057939052582,
+      "kl": 0.42363901240751145,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 0.0042,
+      "num_tokens": 1292538.0,
+      "reward": 0.98125,
+      "reward_std": 0.10915650129318237,
+      "rewards/accuracy_reward/mean": 0.00625,
+      "rewards/accuracy_reward/std": 0.025,
+      "rewards/format_reward/mean": 0.975,
+      "rewards/format_reward/std": 0.08415650427341462,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 280,
+  "num_input_tokens_seen": 1292538,
+  "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": 0.0,
+  "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:a845fbc64b7d8106568ed5d1a3ccddb2d6bef397567ea23c23ec1e77ba8fd358
+size 6776