added finetuned checkpoint files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-alpha
+---
+
+# 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 0.10.1.dev0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-alpha",
+  "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": 16,
+  "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",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "lm_head",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79aed3d632ed8d6d7697bf8a7449397d56bc8f49e52e7902a03c74fbc94276b
+size 609389712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba655124ce3ddf9f80db07e3208e0f68b664908c81de2dfa99dfc0ea4def2e7c
+size 170351354

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a55f5806cf43246c6e34c526051e0fe9f7fbcc98ddf7875baf71560a7ce0c9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4782c3b37f124cfecd2499bd6610f5f2fe07660ea8f6546f95d443a6a63162
+size 1064

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.191996594295445,
+  "eval_steps": 2800,
+  "global_step": 14000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23839931885908897,
+      "grad_norm": 9.698241233825684,
+      "learning_rate": 1.2004287245444802e-05,
+      "loss": 1.746,
+      "step": 2800
+    },
+    {
+      "epoch": 0.23839931885908897,
+      "eval_loss": 1.6161515712738037,
+      "eval_runtime": 2098.002,
+      "eval_samples_per_second": 1.4,
+      "eval_steps_per_second": 0.175,
+      "step": 2800
+    },
+    {
+      "epoch": 0.47679863771817793,
+      "grad_norm": 6.200751781463623,
+      "learning_rate": 9.003215434083602e-06,
+      "loss": 1.5909,
+      "step": 5600
+    },
+    {
+      "epoch": 0.47679863771817793,
+      "eval_loss": 1.5394023656845093,
+      "eval_runtime": 2068.134,
+      "eval_samples_per_second": 1.42,
+      "eval_steps_per_second": 0.178,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7151979565772669,
+      "grad_norm": 8.85448169708252,
+      "learning_rate": 6.002143622722401e-06,
+      "loss": 1.4945,
+      "step": 8400
+    },
+    {
+      "epoch": 0.7151979565772669,
+      "eval_loss": 1.4963045120239258,
+      "eval_runtime": 2077.7916,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.177,
+      "step": 8400
+    },
+    {
+      "epoch": 0.9535972754363559,
+      "grad_norm": 9.303555488586426,
+      "learning_rate": 3.0010718113612005e-06,
+      "loss": 1.4832,
+      "step": 11200
+    },
+    {
+      "epoch": 0.9535972754363559,
+      "eval_loss": 1.4696238040924072,
+      "eval_runtime": 2075.1801,
+      "eval_samples_per_second": 1.415,
+      "eval_steps_per_second": 0.177,
+      "step": 11200
+    },
+    {
+      "epoch": 1.191996594295445,
+      "grad_norm": 9.281532287597656,
+      "learning_rate": 0.0,
+      "loss": 1.4425,
+      "step": 14000
+    },
+    {
+      "epoch": 1.191996594295445,
+      "eval_loss": 1.4569294452667236,
+      "eval_runtime": 2302.3378,
+      "eval_samples_per_second": 1.276,
+      "eval_steps_per_second": 0.16,
+      "step": 14000
+    }
+  ],
+  "logging_steps": 2800,
+  "max_steps": 14000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2800,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.69679748808704e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8041073235c0f95eb25cb751e560cc8a8be23939e1db9d53a0db343bc786fb43
+size 5112