Upload 8 files

README.md

@@ -1,3 +1,204 @@
 ---
-license: cc-by-nc-4.0
+library_name: peft
+base_model: 152334H/miqu-1-70b-sf
 ---
+
+# 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 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "152334H/miqu-1-70b-sf",
+  "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": 64,
+  "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": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "lm_head",
+    "up_proj",
+    "q_proj",
+    "k_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:c7f5acb93c294b3d2f0070b2bf2cc290d3c73bfe6014ec6bb77484fc650b8411
+size 2710625064

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e22afff18775a8824d72f233eb79135c919b10bf7ba15985480b36becdfbfaf
+size 833909276

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f5d31f85d862c79e4fd8a9dfd0a973fea3fbf5071f5e3e85af4a1b956992df
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cd360820c5930ab2dd6815a5f5f2ef77ba4d7ad7f2ae4ef7613493d20690ef
+size 1064

trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0848329048843186,
+  "eval_steps": 400,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019903980796159233,
+      "loss": 1.2412,
+      "step": 25
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019803960792158433,
+      "loss": 1.2101,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019703940788157634,
+      "loss": 1.1308,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019603920784156832,
+      "loss": 1.1847,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019503900780156033,
+      "loss": 1.183,
+      "step": 125
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001940388077615523,
+      "loss": 1.1129,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00019303860772154432,
+      "loss": 1.2248,
+      "step": 175
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00019203840768153632,
+      "loss": 1.1082,
+      "step": 200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001910382076415283,
+      "loss": 1.2025,
+      "step": 225
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001900380076015203,
+      "loss": 1.2208,
+      "step": 250
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001890378075615123,
+      "loss": 1.1124,
+      "step": 275
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001880376075215043,
+      "loss": 1.0934,
+      "step": 300
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00018703740748149633,
+      "loss": 1.2967,
+      "step": 325
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001860372074414883,
+      "loss": 1.1463,
+      "step": 350
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00018503700740148032,
+      "loss": 1.1978,
+      "step": 375
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001840368073614723,
+      "loss": 1.0147,
+      "step": 400
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.8289958238601685,
+      "eval_runtime": 1938.2766,
+      "eval_samples_per_second": 0.401,
+      "eval_steps_per_second": 0.051,
+      "step": 400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001830366073214643,
+      "loss": 0.7315,
+      "step": 425
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001820364072814563,
+      "loss": 0.8464,
+      "step": 450
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001810362072414483,
+      "loss": 0.7709,
+      "step": 475
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0001800360072014403,
+      "loss": 0.8396,
+      "step": 500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00017903580716143228,
+      "loss": 0.7598,
+      "step": 525
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00017803560712142429,
+      "loss": 0.7829,
+      "step": 550
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001770354070814163,
+      "loss": 0.8044,
+      "step": 575
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0001760352070414083,
+      "loss": 0.7746,
+      "step": 600
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0001750350070014003,
+      "loss": 0.8287,
+      "step": 625
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001740348069613923,
+      "loss": 0.7134,
+      "step": 650
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001730346069213843,
+      "loss": 0.7763,
+      "step": 675
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00017203440688137627,
+      "loss": 0.8097,
+      "step": 700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00017103420684136828,
+      "loss": 0.8152,
+      "step": 725
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0001700340068013603,
+      "loss": 0.7876,
+      "step": 750
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00016903380676135227,
+      "loss": 0.7261,
+      "step": 775
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00016803360672134428,
+      "loss": 0.3176,
+      "step": 800
+    },
+    {
+      "epoch": 2.06,
+      "eval_loss": 0.2893330454826355,
+      "eval_runtime": 1936.9393,
+      "eval_samples_per_second": 0.401,
+      "eval_steps_per_second": 0.051,
+      "step": 800
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00016703340668133626,
+      "loss": 0.3089,
+      "step": 825
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00016603320664132826,
+      "loss": 0.3265,
+      "step": 850
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00016503300660132027,
+      "loss": 0.2873,
+      "step": 875
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00016403280656131228,
+      "loss": 0.3553,
+      "step": 900
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00016303260652130428,
+      "loss": 0.3184,
+      "step": 925
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.00016203240648129626,
+      "loss": 0.2688,
+      "step": 950
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.00016103220644128827,
+      "loss": 0.2998,
+      "step": 975
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.00016003200640128028,
+      "loss": 0.283,
+      "step": 1000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00015903180636127226,
+      "loss": 0.313,
+      "step": 1025
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.00015803160632126427,
+      "loss": 0.3122,
+      "step": 1050
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00015703140628125625,
+      "loss": 0.2782,
+      "step": 1075
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00015603120624124825,
+      "loss": 0.2886,
+      "step": 1100
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00015503100620124026,
+      "loss": 0.2898,
+      "step": 1125
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.00015403080616123224,
+      "loss": 0.2956,
+      "step": 1150
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.00015303060612122427,
+      "loss": 0.2609,
+      "step": 1175
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00015203040608121625,
+      "loss": 0.115,
+      "step": 1200
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 0.10693752020597458,
+      "eval_runtime": 1938.4879,
+      "eval_samples_per_second": 0.401,
+      "eval_steps_per_second": 0.051,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 13,
+  "save_steps": 400,
+  "total_flos": 2.0361775954431836e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97f5d372239fffbc2799f93ef0e88bc166d8c8b227da843aaa9f40535d624c9
+size 4728