Upload LoRA adapter

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "k_proj",
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e064b92015dfb763f9b640d8f4daec91f028e5db15f295cac826ccdc7b55c5e8
+oid sha256:f79b13154564b4b4e3647087ee6551f3f9617db2efe599a58c6125cb1d4c2a46
 size 39364256

checkpoint-25/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+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 0.13.2

checkpoint-25/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
+  },
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-25/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79b13154564b4b4e3647087ee6551f3f9617db2efe599a58c6125cb1d4c2a46
+size 39364256

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c71f820d8e28ecbd128e13f51deac86bdecc3f136daabe27a5a66f543a82e62
+size 78911674

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce498d3141fef6ce4d3e66f036aca00f916e19d55fde98a399e42f2c07c9e58
+size 14244

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
+size 1064

checkpoint-25/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-25/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b683455b72e91976efe257b30522811edd3c926bb4302846670897ba1e57fe45
+size 17078556

checkpoint-25/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4377137422561646,
+      "learning_rate": 9.6e-05,
+      "loss": 1.3893,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0715755224227905,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.3208,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3223804235458374,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.2325,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0086308717727661,
+      "learning_rate": 8.4e-05,
+      "loss": 1.1514,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9249104261398315,
+      "learning_rate": 8e-05,
+      "loss": 1.0826,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.9513036012649536,
+      "learning_rate": 7.6e-05,
+      "loss": 1.02,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.0480144023895264,
+      "learning_rate": 7.2e-05,
+      "loss": 0.9592,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1185643672943115,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.8972,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.1805726289749146,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.8332,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2669492959976196,
+      "learning_rate": 6e-05,
+      "loss": 0.7677,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.3598390817642212,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.7044,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.8499770164489746,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6446,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 1.916239857673645,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5817,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.4864529371261597,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5206,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.3958476781845093,
+      "learning_rate": 4e-05,
+      "loss": 0.469,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.4041638374328613,
+      "learning_rate": 3.6e-05,
+      "loss": 0.4259,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.3738752603530884,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.3871,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.2662386894226074,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.353,
+      "step": 18
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 1.2382030487060547,
+      "learning_rate": 2.4e-05,
+      "loss": 0.325,
+      "step": 19
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.215654969215393,
+      "learning_rate": 2e-05,
+      "loss": 0.302,
+      "step": 20
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 1.1050209999084473,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2824,
+      "step": 21
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 1.004746675491333,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2666,
+      "step": 22
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.944015622138977,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2544,
+      "step": 23
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.8987796902656555,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.2456,
+      "step": 24
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.8577855825424194,
+      "learning_rate": 0.0,
+      "loss": 0.2397,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "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": 7.57758680064e+16,
+  "train_batch_size": 100,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85e37b4ffa98e7848d7fca9828e9a2fe7231e25a7885525f80ed04a61307fbf
+size 5496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea180ad24740a4771e5d3378f01b69357b1576ad4d4379c5fc6a684073de531a
+oid sha256:b85e37b4ffa98e7848d7fca9828e9a2fe7231e25a7885525f80ed04a61307fbf
 size 5496