Uploaded checkpoint-4000

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: deepseek-ai/deepseek-math-7b-base
+---
+
+# 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 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15de7287ec1329fac47a23ddf4050a0a385f2cbdfe9f3de33a2ab0146983b921
+size 599711112

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7518dcfe16e47e4b8677f0d8b354c8eef5a5218b03a0e245b413d65a1d0cad69
+size 1199663358

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e7fca03d8516b5045a5a825f6d9a10c2f311321548c7d8fcdbf50095b470d5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fc8b33d81c27bb5cbc67a853dafb2be412606f08c305654654cb76d39a165c
+size 1064

trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 2000,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.9697519540786743,
+      "learning_rate": 1e-06,
+      "loss": 0.1629,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.3848124742507935,
+      "learning_rate": 9.898989898989898e-07,
+      "loss": 0.14,
+      "step": 200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.9986572265625,
+      "learning_rate": 9.797979797979797e-07,
+      "loss": 0.1354,
+      "step": 300
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.11438798904418945,
+      "learning_rate": 9.696969696969698e-07,
+      "loss": 0.1182,
+      "step": 400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8548241257667542,
+      "learning_rate": 9.595959595959596e-07,
+      "loss": 0.1192,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.5312464237213135,
+      "learning_rate": 9.494949494949495e-07,
+      "loss": 0.0997,
+      "step": 600
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9692059755325317,
+      "learning_rate": 9.393939393939395e-07,
+      "loss": 0.102,
+      "step": 700
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.42864611744880676,
+      "learning_rate": 9.292929292929292e-07,
+      "loss": 0.0901,
+      "step": 800
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.852543830871582,
+      "learning_rate": 9.191919191919192e-07,
+      "loss": 0.0937,
+      "step": 900
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5718303322792053,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.093,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9396565556526184,
+      "learning_rate": 8.98989898989899e-07,
+      "loss": 0.0892,
+      "step": 1100
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.08157779276371002,
+      "learning_rate": 8.888888888888888e-07,
+      "loss": 0.0934,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8076322078704834,
+      "learning_rate": 8.787878787878787e-07,
+      "loss": 0.0725,
+      "step": 1300
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5076119899749756,
+      "learning_rate": 8.686868686868687e-07,
+      "loss": 0.0835,
+      "step": 1400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.1567238569259644,
+      "learning_rate": 8.585858585858586e-07,
+      "loss": 0.0747,
+      "step": 1500
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6817927956581116,
+      "learning_rate": 8.484848484848484e-07,
+      "loss": 0.0903,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6467050313949585,
+      "learning_rate": 8.383838383838383e-07,
+      "loss": 0.0721,
+      "step": 1700
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.8435570001602173,
+      "learning_rate": 8.282828282828283e-07,
+      "loss": 0.0847,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6265794634819031,
+      "learning_rate": 8.181818181818182e-07,
+      "loss": 0.0687,
+      "step": 1900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.360060453414917,
+      "learning_rate": 8.08080808080808e-07,
+      "loss": 0.0748,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.06745574623346329,
+      "eval_runtime": 304.7718,
+      "eval_samples_per_second": 3.281,
+      "eval_steps_per_second": 0.82,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5074820518493652,
+      "learning_rate": 7.97979797979798e-07,
+      "loss": 0.0699,
+      "step": 2100
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.3634223937988281,
+      "learning_rate": 7.878787878787878e-07,
+      "loss": 0.0682,
+      "step": 2200
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.0763113498687744,
+      "learning_rate": 7.777777777777778e-07,
+      "loss": 0.0786,
+      "step": 2300
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5437021255493164,
+      "learning_rate": 7.676767676767675e-07,
+      "loss": 0.065,
+      "step": 2400
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5890172719955444,
+      "learning_rate": 7.575757575757575e-07,
+      "loss": 0.0772,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.9904383420944214,
+      "learning_rate": 7.474747474747475e-07,
+      "loss": 0.0735,
+      "step": 2600
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9233341813087463,
+      "learning_rate": 7.373737373737373e-07,
+      "loss": 0.0695,
+      "step": 2700
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.10603007674217224,
+      "learning_rate": 7.272727272727272e-07,
+      "loss": 0.0595,
+      "step": 2800
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9929779767990112,
+      "learning_rate": 7.171717171717171e-07,
+      "loss": 0.0595,
+      "step": 2900
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4711184799671173,
+      "learning_rate": 7.07070707070707e-07,
+      "loss": 0.0606,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5627967715263367,
+      "learning_rate": 6.96969696969697e-07,
+      "loss": 0.0713,
+      "step": 3100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7645086646080017,
+      "learning_rate": 6.868686868686868e-07,
+      "loss": 0.0672,
+      "step": 3200
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.8071433901786804,
+      "learning_rate": 6.767676767676767e-07,
+      "loss": 0.0809,
+      "step": 3300
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.281545877456665,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 0.0577,
+      "step": 3400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.15431547164917,
+      "learning_rate": 6.565656565656566e-07,
+      "loss": 0.0613,
+      "step": 3500
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.42522451281547546,
+      "learning_rate": 6.464646464646465e-07,
+      "loss": 0.0531,
+      "step": 3600
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2078278064727783,
+      "learning_rate": 6.363636363636363e-07,
+      "loss": 0.0692,
+      "step": 3700
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.207512855529785,
+      "learning_rate": 6.262626262626263e-07,
+      "loss": 0.0508,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.696768045425415,
+      "learning_rate": 6.161616161616161e-07,
+      "loss": 0.0655,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6295761466026306,
+      "learning_rate": 6.060606060606061e-07,
+      "loss": 0.0577,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.057661667466163635,
+      "eval_runtime": 304.4519,
+      "eval_samples_per_second": 3.285,
+      "eval_steps_per_second": 0.821,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 3.26411004936192e+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 sha256:248b0ebf1fbefbcf8838f5e2bceb96ade828e71616bf34f531f6b77403339857
+size 4920