Initial commit: MNLP M3 quantized model

checkpoint-2920/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B-Base
+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

checkpoint-2920/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2920/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5de4aa9dd2e16a0060e7b9acf796565d8b71866783e02693bbda68124fadb4c
+size 20243136

checkpoint-2920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5a5bb09609fa391e2551bfe3ae0c14825e85e2d445826904a7f55950fa98a2
+size 40699434

checkpoint-2920/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa97fc9b063006cc6bcdf131798cea432909ea2f2220b8fe6e8bc31d0c50de4
+size 14244

checkpoint-2920/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2eaaaaf5815db44a661f66210e20f3a680d1bf0b436d2736ca7d9f00c88bc2
+size 988

checkpoint-2920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f795bd5ea5956824d06a80f137ec4ef011ad8f19d22f0c13e5ae4ad34613f72
+size 1064

checkpoint-2920/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17123287671232876,
+      "grad_norm": 0.17268113791942596,
+      "learning_rate": 0.00018867579908675802,
+      "loss": 0.1977,
+      "step": 500
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 0.2097366750240326,
+      "learning_rate": 0.00017726027397260274,
+      "loss": 0.1371,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5136986301369864,
+      "grad_norm": 0.2663485109806061,
+      "learning_rate": 0.0001658447488584475,
+      "loss": 0.1345,
+      "step": 1500
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 0.16753822565078735,
+      "learning_rate": 0.00015442922374429225,
+      "loss": 0.1346,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8561643835616438,
+      "grad_norm": 0.1972370743751526,
+      "learning_rate": 0.00014301369863013697,
+      "loss": 0.1346,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.13700313866138458,
+      "eval_runtime": 31.6412,
+      "eval_samples_per_second": 31.604,
+      "eval_steps_per_second": 7.901,
+      "step": 2920
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.5984091635646464e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2920/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc6388a55757ce5665684824eadd7c5966aa9a90a365b1ad9889095f87c1661
+size 5240

checkpoint-5840/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B-Base
+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

checkpoint-5840/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-5840/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46114335d2b47ffa9f7844b0aecba79d9f77f582d0b5cad47c04ac84b887c7ce
+size 20243136

checkpoint-5840/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08feb87e4165e138b481d48683682fc7ad63230eac5c93f48c64e7444cb85946
+size 40699434

checkpoint-5840/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a74d40b0ead9be50c997ebf3c00d8b7e467dd4d5739e50443b7c6dc09737d99
+size 14244

checkpoint-5840/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c926fa54b546197c53c3639a2007a050fa3aa6ea1e28a7ffaf777071fd633f
+size 988

checkpoint-5840/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed3d494718eb468072818e91d3af98faccaaa0196837d4c945079721e62b8aa
+size 1064

checkpoint-5840/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5840,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17123287671232876,
+      "grad_norm": 0.17268113791942596,
+      "learning_rate": 0.00018867579908675802,
+      "loss": 0.1977,
+      "step": 500
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 0.2097366750240326,
+      "learning_rate": 0.00017726027397260274,
+      "loss": 0.1371,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5136986301369864,
+      "grad_norm": 0.2663485109806061,
+      "learning_rate": 0.0001658447488584475,
+      "loss": 0.1345,
+      "step": 1500
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 0.16753822565078735,
+      "learning_rate": 0.00015442922374429225,
+      "loss": 0.1346,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8561643835616438,
+      "grad_norm": 0.1972370743751526,
+      "learning_rate": 0.00014301369863013697,
+      "loss": 0.1346,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.13700313866138458,
+      "eval_runtime": 31.6412,
+      "eval_samples_per_second": 31.604,
+      "eval_steps_per_second": 7.901,
+      "step": 2920
+    },
+    {
+      "epoch": 1.0273972602739727,
+      "grad_norm": 0.22729772329330444,
+      "learning_rate": 0.00013159817351598174,
+      "loss": 0.1305,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1986301369863013,
+      "grad_norm": 0.2352839708328247,
+      "learning_rate": 0.00012018264840182649,
+      "loss": 0.1164,
+      "step": 3500
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 0.1942291408777237,
+      "learning_rate": 0.00010876712328767125,
+      "loss": 0.1177,
+      "step": 4000
+    },
+    {
+      "epoch": 1.541095890410959,
+      "grad_norm": 0.19947709143161774,
+      "learning_rate": 9.735159817351599e-05,
+      "loss": 0.1193,
+      "step": 4500
+    },
+    {
+      "epoch": 1.7123287671232876,
+      "grad_norm": 0.23757582902908325,
+      "learning_rate": 8.593607305936074e-05,
+      "loss": 0.1158,
+      "step": 5000
+    },
+    {
+      "epoch": 1.8835616438356164,
+      "grad_norm": 0.27170926332473755,
+      "learning_rate": 7.452054794520548e-05,
+      "loss": 0.1183,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1377769559621811,
+      "eval_runtime": 31.7008,
+      "eval_samples_per_second": 31.545,
+      "eval_steps_per_second": 7.886,
+      "step": 5840
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.196818327129293e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5840/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc6388a55757ce5665684824eadd7c5966aa9a90a365b1ad9889095f87c1661
+size 5240

checkpoint-8760/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B-Base
+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

checkpoint-8760/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-8760/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37e163a133309bccdc33c95c52cccd8cb57d8856a28484c2748dd498854a4f0
+size 20243136

checkpoint-8760/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474f6e1a86ad4b66d807fa2fdfdf1f71f88e18c0e7758c0381b3e9e5e863a15a
+size 40699434

checkpoint-8760/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62682eca5e982c117bf1e19e29e5d806537cc10147f0b30db2bc2e9c4124e81
+size 14244

checkpoint-8760/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c306449fc45f91eee7ce1495ee979c6e4ce2d01f5040d3c68a505dae0eec2a9
+size 988

checkpoint-8760/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa78658731a275cdea3ba83fbe14411d075dac045e23119ddf60e210cd07059c
+size 1064

checkpoint-8760/trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 8760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17123287671232876,
+      "grad_norm": 0.17268113791942596,
+      "learning_rate": 0.00018867579908675802,
+      "loss": 0.1977,
+      "step": 500
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 0.2097366750240326,
+      "learning_rate": 0.00017726027397260274,
+      "loss": 0.1371,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5136986301369864,
+      "grad_norm": 0.2663485109806061,
+      "learning_rate": 0.0001658447488584475,
+      "loss": 0.1345,
+      "step": 1500
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 0.16753822565078735,
+      "learning_rate": 0.00015442922374429225,
+      "loss": 0.1346,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8561643835616438,
+      "grad_norm": 0.1972370743751526,
+      "learning_rate": 0.00014301369863013697,
+      "loss": 0.1346,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.13700313866138458,
+      "eval_runtime": 31.6412,
+      "eval_samples_per_second": 31.604,
+      "eval_steps_per_second": 7.901,
+      "step": 2920
+    },
+    {
+      "epoch": 1.0273972602739727,
+      "grad_norm": 0.22729772329330444,
+      "learning_rate": 0.00013159817351598174,
+      "loss": 0.1305,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1986301369863013,
+      "grad_norm": 0.2352839708328247,
+      "learning_rate": 0.00012018264840182649,
+      "loss": 0.1164,
+      "step": 3500
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 0.1942291408777237,
+      "learning_rate": 0.00010876712328767125,
+      "loss": 0.1177,
+      "step": 4000
+    },
+    {
+      "epoch": 1.541095890410959,
+      "grad_norm": 0.19947709143161774,
+      "learning_rate": 9.735159817351599e-05,
+      "loss": 0.1193,
+      "step": 4500
+    },
+    {
+      "epoch": 1.7123287671232876,
+      "grad_norm": 0.23757582902908325,
+      "learning_rate": 8.593607305936074e-05,
+      "loss": 0.1158,
+      "step": 5000
+    },
+    {
+      "epoch": 1.8835616438356164,
+      "grad_norm": 0.27170926332473755,
+      "learning_rate": 7.452054794520548e-05,
+      "loss": 0.1183,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1377769559621811,
+      "eval_runtime": 31.7008,
+      "eval_samples_per_second": 31.545,
+      "eval_steps_per_second": 7.886,
+      "step": 5840
+    },
+    {
+      "epoch": 2.0547945205479454,
+      "grad_norm": 0.29543906450271606,
+      "learning_rate": 6.310502283105023e-05,
+      "loss": 0.1097,
+      "step": 6000
+    },
+    {
+      "epoch": 2.2260273972602738,
+      "grad_norm": 0.4334782063961029,
+      "learning_rate": 5.1689497716894973e-05,
+      "loss": 0.0995,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3972602739726026,
+      "grad_norm": 0.28854918479919434,
+      "learning_rate": 4.027397260273973e-05,
+      "loss": 0.0986,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5684931506849313,
+      "grad_norm": 0.2981366515159607,
+      "learning_rate": 2.8858447488584477e-05,
+      "loss": 0.0982,
+      "step": 7500
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 0.28199276328086853,
+      "learning_rate": 1.7442922374429226e-05,
+      "loss": 0.0985,
+      "step": 8000
+    },
+    {
+      "epoch": 2.910958904109589,
+      "grad_norm": 0.34423625469207764,
+      "learning_rate": 6.027397260273973e-06,
+      "loss": 0.0983,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.14507943391799927,
+      "eval_runtime": 31.6284,
+      "eval_samples_per_second": 31.617,
+      "eval_steps_per_second": 7.904,
+      "step": 8760
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.795227490693939e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8760/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc6388a55757ce5665684824eadd7c5966aa9a90a365b1ad9889095f87c1661
+size 5240