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.dev0

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": [
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "lm_head",
+    "k_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 sha256:4853d09cd4a4a59b9a40f7a7016eaa2cb9cb196af71fcc80ae44166efb5bff4e
+size 2710625064

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b27923e2a96e81c7f573276e954c2cd4f6bad7bd24d4c2b3dad71386d1f0089
+size 833909276

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99e72f26847e5442b0f9d795e41d6cc76bbc7b50e710067fc58e39338c5371f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0ee2cbca85ee25c26efbb3861bf614dd90a5f45920131fa5ec469244f585d4
+size 1064

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.038461538461538,
+  "eval_steps": 210,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019427890345649585,
+      "loss": 1.0041,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018831942789034566,
+      "loss": 0.9074,
+      "step": 50
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018235995232419546,
+      "loss": 0.9026,
+      "step": 75
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001764004767580453,
+      "loss": 1.0049,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00017044100119189512,
+      "loss": 0.722,
+      "step": 125
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00016448152562574496,
+      "loss": 0.5386,
+      "step": 150
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00015852205005959479,
+      "loss": 0.5596,
+      "step": 175
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00015256257449344456,
+      "loss": 0.5727,
+      "step": 200
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.25414443016052246,
+      "eval_runtime": 539.3917,
+      "eval_samples_per_second": 0.384,
+      "eval_steps_per_second": 0.048,
+      "step": 210
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.0001466030989272944,
+      "loss": 0.3522,
+      "step": 225
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00014064362336114423,
+      "loss": 0.2049,
+      "step": 250
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.00013468414779499406,
+      "loss": 0.2453,
+      "step": 275
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.0001287246722288439,
+      "loss": 0.2045,
+      "step": 300
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.0001227651966626937,
+      "loss": 0.1815,
+      "step": 325
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 0.00011680572109654351,
+      "loss": 0.093,
+      "step": 350
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.00011084624553039333,
+      "loss": 0.1013,
+      "step": 375
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.00010488676996424316,
+      "loss": 0.0648,
+      "step": 400
+    },
+    {
+      "epoch": 4.04,
+      "eval_loss": 0.03103998862206936,
+      "eval_runtime": 535.4733,
+      "eval_samples_per_second": 0.387,
+      "eval_steps_per_second": 0.049,
+      "step": 420
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 210,
+  "total_flos": 7.101562243598254e+17,
+  "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 sha256:004068874946d8a7b286448676c0533bfd6ffaedb325c715e7348c0e9098c513
+size 4728