Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-llm-7b-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

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
+  "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",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_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:b0a72a443b38a28f13bad12e24b881f2987d865462a81b7bfe9372363979f079
+size 299883760

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3658c0f9eade0d957cd5cb6ffe56c461a33e3ce68c43b271849275f6082dcb3
+size 600009423

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be5426eab8fdc2b502cc1a008ae4643de79d3fe6f42a14a1216306a3a610945
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf660b925a61f702d3b46324976d8b875ffa17eabff07494f5a6e8294bae329d
+size 1465

trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 500.0,
+  "eval_steps": 50,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.571428571428571,
+      "grad_norm": 0.26636427640914917,
+      "learning_rate": 0.00029265,
+      "loss": 0.5904,
+      "step": 50
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.16996383666992188,
+      "learning_rate": 0.00028514999999999997,
+      "loss": 0.034,
+      "step": 100
+    },
+    {
+      "epoch": 37.57142857142857,
+      "grad_norm": 0.0670333057641983,
+      "learning_rate": 0.00027764999999999995,
+      "loss": 0.016,
+      "step": 150
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.03331753611564636,
+      "learning_rate": 0.00027015,
+      "loss": 0.0105,
+      "step": 200
+    },
+    {
+      "epoch": 62.57142857142857,
+      "grad_norm": 0.014663901180028915,
+      "learning_rate": 0.00026264999999999996,
+      "loss": 0.0086,
+      "step": 250
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.02259993739426136,
+      "learning_rate": 0.00025515,
+      "loss": 0.0083,
+      "step": 300
+    },
+    {
+      "epoch": 87.57142857142857,
+      "grad_norm": 0.01287161372601986,
+      "learning_rate": 0.00024765,
+      "loss": 0.0082,
+      "step": 350
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.02039289101958275,
+      "learning_rate": 0.00024014999999999998,
+      "loss": 0.0082,
+      "step": 400
+    },
+    {
+      "epoch": 112.57142857142857,
+      "grad_norm": 0.012268965132534504,
+      "learning_rate": 0.00023264999999999996,
+      "loss": 0.0081,
+      "step": 450
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.023380041122436523,
+      "learning_rate": 0.00022514999999999997,
+      "loss": 0.0081,
+      "step": 500
+    },
+    {
+      "epoch": 137.57142857142858,
+      "grad_norm": 0.009437249973416328,
+      "learning_rate": 0.00021764999999999998,
+      "loss": 0.008,
+      "step": 550
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.015519071370363235,
+      "learning_rate": 0.00021014999999999999,
+      "loss": 0.008,
+      "step": 600
+    },
+    {
+      "epoch": 162.57142857142858,
+      "grad_norm": 0.008696269243955612,
+      "learning_rate": 0.00020264999999999997,
+      "loss": 0.008,
+      "step": 650
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.018794188275933266,
+      "learning_rate": 0.00019514999999999997,
+      "loss": 0.008,
+      "step": 700
+    },
+    {
+      "epoch": 187.57142857142858,
+      "grad_norm": 0.010213403962552547,
+      "learning_rate": 0.00018764999999999998,
+      "loss": 0.008,
+      "step": 750
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.01870943419635296,
+      "learning_rate": 0.00018015,
+      "loss": 0.008,
+      "step": 800
+    },
+    {
+      "epoch": 212.57142857142858,
+      "grad_norm": 0.007811392657458782,
+      "learning_rate": 0.00017265,
+      "loss": 0.008,
+      "step": 850
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.014662496745586395,
+      "learning_rate": 0.00016514999999999998,
+      "loss": 0.008,
+      "step": 900
+    },
+    {
+      "epoch": 237.57142857142858,
+      "grad_norm": 0.008589034900069237,
+      "learning_rate": 0.00015764999999999998,
+      "loss": 0.008,
+      "step": 950
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.015834109857678413,
+      "learning_rate": 0.00015014999999999996,
+      "loss": 0.008,
+      "step": 1000
+    },
+    {
+      "epoch": 262.57142857142856,
+      "grad_norm": 0.007818593643605709,
+      "learning_rate": 0.00014264999999999997,
+      "loss": 0.0079,
+      "step": 1050
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.01577523909509182,
+      "learning_rate": 0.00013514999999999998,
+      "loss": 0.0079,
+      "step": 1100
+    },
+    {
+      "epoch": 287.57142857142856,
+      "grad_norm": 0.010020360350608826,
+      "learning_rate": 0.00012764999999999999,
+      "loss": 0.0079,
+      "step": 1150
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.013038736768066883,
+      "learning_rate": 0.00012014999999999999,
+      "loss": 0.0079,
+      "step": 1200
+    },
+    {
+      "epoch": 312.57142857142856,
+      "grad_norm": 0.007050866261124611,
+      "learning_rate": 0.00011264999999999999,
+      "loss": 0.0079,
+      "step": 1250
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.01592850126326084,
+      "learning_rate": 0.00010514999999999998,
+      "loss": 0.0079,
+      "step": 1300
+    },
+    {
+      "epoch": 337.57142857142856,
+      "grad_norm": 0.0075027476996183395,
+      "learning_rate": 9.764999999999999e-05,
+      "loss": 0.0079,
+      "step": 1350
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.011593643575906754,
+      "learning_rate": 9.014999999999998e-05,
+      "loss": 0.0079,
+      "step": 1400
+    },
+    {
+      "epoch": 362.57142857142856,
+      "grad_norm": 0.007643813267350197,
+      "learning_rate": 8.265e-05,
+      "loss": 0.0079,
+      "step": 1450
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.013792463578283787,
+      "learning_rate": 7.515e-05,
+      "loss": 0.0079,
+      "step": 1500
+    },
+    {
+      "epoch": 387.57142857142856,
+      "grad_norm": 0.00813667569309473,
+      "learning_rate": 6.764999999999999e-05,
+      "loss": 0.0079,
+      "step": 1550
+    },
+    {
+      "epoch": 400.0,
+      "grad_norm": 0.011745907366275787,
+      "learning_rate": 6.015e-05,
+      "loss": 0.0079,
+      "step": 1600
+    },
+    {
+      "epoch": 412.57142857142856,
+      "grad_norm": 0.006887589581310749,
+      "learning_rate": 5.264999999999999e-05,
+      "loss": 0.0079,
+      "step": 1650
+    },
+    {
+      "epoch": 425.0,
+      "grad_norm": 0.012646987102925777,
+      "learning_rate": 4.514999999999999e-05,
+      "loss": 0.0079,
+      "step": 1700
+    },
+    {
+      "epoch": 437.57142857142856,
+      "grad_norm": 0.0065942066721618176,
+      "learning_rate": 3.7649999999999994e-05,
+      "loss": 0.0079,
+      "step": 1750
+    },
+    {
+      "epoch": 450.0,
+      "grad_norm": 0.010179451666772366,
+      "learning_rate": 3.0149999999999998e-05,
+      "loss": 0.0079,
+      "step": 1800
+    },
+    {
+      "epoch": 462.57142857142856,
+      "grad_norm": 0.008461065590381622,
+      "learning_rate": 2.2649999999999998e-05,
+      "loss": 0.0079,
+      "step": 1850
+    },
+    {
+      "epoch": 475.0,
+      "grad_norm": 0.014076176099479198,
+      "learning_rate": 1.5149999999999999e-05,
+      "loss": 0.0079,
+      "step": 1900
+    },
+    {
+      "epoch": 487.57142857142856,
+      "grad_norm": 0.006570025812834501,
+      "learning_rate": 7.65e-06,
+      "loss": 0.0078,
+      "step": 1950
+    },
+    {
+      "epoch": 500.0,
+      "grad_norm": 0.0165297482162714,
+      "learning_rate": 1.5e-07,
+      "loss": 0.0078,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 667,
+  "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": 5.5468656427008e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e51c375a9af5ba2cbaec6b87a4df7055c8fe0451dfb6d4156f6a7508185b083
+size 5777