Upload task output 1

README.md

@@ -0,0 +1,209 @@
+---
+base_model: None
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen2.5-3B-Instruct
+- grpo
+- lora
+- 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 0.18.2.dev0

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.2.dev0@1d08144b855d3a58442a4f17187c5a8ebcf3b237",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902a520b378fd449cc223d1921d7418b46a32eae7d58a0f95faf008d6f6df1c7
+size 957942768

loss.txt

@@ -0,0 +1 @@
+4,-0.52875

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "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": 0.0,
+      "completions/max_length": 10.0,
+      "completions/max_terminated_length": 10.0,
+      "completions/mean_length": 2.4166667461395264,
+      "completions/mean_terminated_length": 2.4166667461395264,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.7551832646131516,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 3.3013529777526855,
+      "learning_rate": 0.0,
+      "loss": -0.0108,
+      "num_tokens": 117740.0,
+      "reward": 0.550595223903656,
+      "reward_std": 0.49517032504081726,
+      "rewards/env_game_reward/mean": 0.550595223903656,
+      "rewards/env_game_reward/std": 0.49517035484313965,
+      "sampling/importance_sampling_ratio/max": 2.689040184020996,
+      "sampling/importance_sampling_ratio/mean": 0.9900985360145569,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 1.06956148147583,
+      "sampling/sampling_logp_difference/mean": 0.10877184569835663,
+      "step": 1,
+      "step_time": 88.36924512299811
+    },
+    {
+      "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": 0.0,
+      "completions/max_length": 9.0,
+      "completions/max_terminated_length": 9.0,
+      "completions/mean_length": 2.3482143878936768,
+      "completions/mean_terminated_length": 2.3482143878936768,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.5951707661151886,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.4761904776096344,
+      "grad_norm": 3.6701693534851074,
+      "learning_rate": 2.84304e-07,
+      "loss": 0.0178,
+      "num_tokens": 222521.0,
+      "reward": 0.5074405074119568,
+      "reward_std": 0.4893840253353119,
+      "rewards/env_game_reward/mean": 0.507440447807312,
+      "rewards/env_game_reward/std": 0.4893840253353119,
+      "sampling/importance_sampling_ratio/max": 1.7845207452774048,
+      "sampling/importance_sampling_ratio/mean": 0.9994808435440063,
+      "sampling/importance_sampling_ratio/min": 0.5518327951431274,
+      "sampling/sampling_logp_difference/max": 0.7131795883178711,
+      "sampling/sampling_logp_difference/mean": 0.08745051920413971,
+      "step": 2,
+      "step_time": 49.22992679999879
+    },
+    {
+      "clip_ratio/high_max": 0.01794770290143788,
+      "clip_ratio/high_mean": 0.00897385145071894,
+      "clip_ratio/low_mean": 0.009698691545054317,
+      "clip_ratio/low_min": 0.005136268446221948,
+      "clip_ratio/region_mean": 0.018672542879357934,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 50.0,
+      "completions/max_terminated_length": 50.0,
+      "completions/mean_length": 2.3839285373687744,
+      "completions/mean_terminated_length": 2.3839285373687744,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6667436063289642,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.4583333432674408,
+      "grad_norm": 4.131317138671875,
+      "learning_rate": 5.68608e-07,
+      "loss": 0.056,
+      "num_tokens": 334874.0,
+      "reward": 0.5461309552192688,
+      "reward_std": 0.4903090000152588,
+      "rewards/env_game_reward/mean": 0.5461309552192688,
+      "rewards/env_game_reward/std": 0.4903090000152588,
+      "sampling/importance_sampling_ratio/max": 2.887385368347168,
+      "sampling/importance_sampling_ratio/mean": 0.9982833862304688,
+      "sampling/importance_sampling_ratio/min": 0.5404163599014282,
+      "sampling/sampling_logp_difference/max": 1.0797624588012695,
+      "sampling/sampling_logp_difference/mean": 0.06731995940208435,
+      "step": 3,
+      "step_time": 78.03542665400164
+    },
+    {
+      "clip_ratio/high_max": 0.013787210453301668,
+      "clip_ratio/high_mean": 0.009407755453139544,
+      "clip_ratio/low_mean": 0.011533747077919543,
+      "clip_ratio/low_min": 0.007629886502400041,
+      "clip_ratio/region_mean": 0.020941501948982477,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 52.0,
+      "completions/max_terminated_length": 52.0,
+      "completions/mean_length": 2.4732143878936768,
+      "completions/mean_terminated_length": 2.4732143878936768,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "entropy": 0.6175597459077835,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.4940476417541504,
+      "grad_norm": 1.6108940839767456,
+      "learning_rate": 8.529119999999999e-07,
+      "loss": 0.024,
+      "num_tokens": 439697.0,
+      "reward": 0.5729166865348816,
+      "reward_std": 0.48550185561180115,
+      "rewards/env_game_reward/mean": 0.5729166865348816,
+      "rewards/env_game_reward/std": 0.48550188541412354,
+      "sampling/importance_sampling_ratio/max": 2.209211587905884,
+      "sampling/importance_sampling_ratio/mean": 0.9964304566383362,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 1.3181190490722656,
+      "sampling/sampling_logp_difference/mean": 0.0983412116765976,
+      "step": 4,
+      "step_time": 50.542828030993405
+    },
+    {
+      "epoch": 1.0,
+      "eval_clip_ratio/high_max": 0.0,
+      "eval_clip_ratio/high_mean": 0.0,
+      "eval_clip_ratio/low_mean": 0.0,
+      "eval_clip_ratio/low_min": 0.0,
+      "eval_clip_ratio/region_mean": 0.0,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 2.96,
+      "eval_completions/max_terminated_length": 2.96,
+      "eval_completions/mean_length": 2.2675,
+      "eval_completions/mean_terminated_length": 2.2675,
+      "eval_completions/min_length": 2.0,
+      "eval_completions/min_terminated_length": 2.0,
+      "eval_entropy": 0.667363337278366,
+      "eval_frac_reward_zero_std": 0.56,
+      "eval_loss": 0.011317968368530273,
+      "eval_num_tokens": 439697.0,
+      "eval_reward": 0.52875,
+      "eval_reward_std": 0.4869813323020935,
+      "eval_rewards/env_game_reward/mean": 0.52875,
+      "eval_rewards/env_game_reward/std": 0.48698135375976564,
+      "eval_runtime": 70.8359,
+      "eval_samples_per_second": 2.823,
+      "eval_sampling/importance_sampling_ratio/max": 1.3801123309135437,
+      "eval_sampling/importance_sampling_ratio/mean": 0.9903592157363892,
+      "eval_sampling/importance_sampling_ratio/min": 0.7618612945079803,
+      "eval_sampling/sampling_logp_difference/max": 0.3690467220544815,
+      "eval_sampling/sampling_logp_difference/mean": 0.0842927821725607,
+      "eval_steps_per_second": 0.353,
+      "step": 4
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 8,
+  "num_input_tokens_seen": 439697,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 42,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fb712fa715bdf0d55194ac1b921b8d9127d487753c08c6bd73309e9368e2a1
+size 7825