Upload 8 files

README.md

@@ -1,3 +1,204 @@
 ---
-license: mit
+library_name: peft
+base_model: mistralai/Mixtral-8x7B-v0.1
 ---
+
+# 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 0.7.2.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "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": 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": [
+    "o_proj",
+    "w1",
+    "lm_head",
+    "w2",
+    "v_proj",
+    "k_proj",
+    "w3",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4b50260d884e5824dc4f01b1c2a59ba319ad72a43e643945534ba18dac38bb
+size 1005955192

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee46d4d316b0890ca638eb52a984d1dab1d82c65f16e908584d8f324431d878e
+size 243269534

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f80ba0fe503ee7e7489af638645bdea7abd82a0d5e159ccf24167ad46239a01
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc861a47ce68de3c1f8fdb7433ac8edc96a66ee89e12bee48feced973c63ecc
+size 1064

trainer_state.json

@@ -0,0 +1,277 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47619047619047616,
+  "eval_steps": 20,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.0689338445663452,
+      "eval_runtime": 9.952,
+      "eval_samples_per_second": 3.818,
+      "eval_steps_per_second": 0.502,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.3734177215189873e-05,
+      "loss": 1.5255,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.8571718335151672,
+      "eval_runtime": 9.9124,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.504,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.2151898734177217e-05,
+      "loss": 0.9309,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.7807316780090332,
+      "eval_runtime": 9.9144,
+      "eval_samples_per_second": 3.833,
+      "eval_steps_per_second": 0.504,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.056962025316456e-05,
+      "loss": 0.7794,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.7378336191177368,
+      "eval_runtime": 9.9203,
+      "eval_samples_per_second": 3.831,
+      "eval_steps_per_second": 0.504,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.89873417721519e-05,
+      "loss": 0.7628,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.7243497371673584,
+      "eval_runtime": 9.9102,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.505,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.7043508291244507,
+      "eval_runtime": 9.9123,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.504,
+      "step": 120
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.7405063291139243e-05,
+      "loss": 0.7323,
+      "step": 125
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.6957876086235046,
+      "eval_runtime": 9.9105,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.505,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.5822784810126583e-05,
+      "loss": 0.706,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.6854685544967651,
+      "eval_runtime": 9.9176,
+      "eval_samples_per_second": 3.832,
+      "eval_steps_per_second": 0.504,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4240506329113925e-05,
+      "loss": 0.6974,
+      "step": 175
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.6812862753868103,
+      "eval_runtime": 9.918,
+      "eval_samples_per_second": 3.831,
+      "eval_steps_per_second": 0.504,
+      "step": 180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.2658227848101267e-05,
+      "loss": 0.6823,
+      "step": 200
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.6784127950668335,
+      "eval_runtime": 9.9087,
+      "eval_samples_per_second": 3.835,
+      "eval_steps_per_second": 0.505,
+      "step": 200
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.6723252534866333,
+      "eval_runtime": 9.9104,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.505,
+      "step": 220
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.1075949367088608e-05,
+      "loss": 0.6856,
+      "step": 225
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.669580340385437,
+      "eval_runtime": 9.9088,
+      "eval_samples_per_second": 3.835,
+      "eval_steps_per_second": 0.505,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.49367088607595e-06,
+      "loss": 0.6857,
+      "step": 250
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.6672892570495605,
+      "eval_runtime": 9.8865,
+      "eval_samples_per_second": 3.844,
+      "eval_steps_per_second": 0.506,
+      "step": 260
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.911392405063292e-06,
+      "loss": 0.6915,
+      "step": 275
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 0.6666972637176514,
+      "eval_runtime": 9.9103,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.505,
+      "step": 280
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.329113924050633e-06,
+      "loss": 0.6685,
+      "step": 300
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.6638540029525757,
+      "eval_runtime": 9.9153,
+      "eval_samples_per_second": 3.832,
+      "eval_steps_per_second": 0.504,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.6611661911010742,
+      "eval_runtime": 9.9319,
+      "eval_samples_per_second": 3.826,
+      "eval_steps_per_second": 0.503,
+      "step": 320
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.746835443037975e-06,
+      "loss": 0.6759,
+      "step": 325
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.658918559551239,
+      "eval_runtime": 9.9278,
+      "eval_samples_per_second": 3.828,
+      "eval_steps_per_second": 0.504,
+      "step": 340
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1645569620253167e-06,
+      "loss": 0.6682,
+      "step": 350
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.6601454615592957,
+      "eval_runtime": 9.9146,
+      "eval_samples_per_second": 3.833,
+      "eval_steps_per_second": 0.504,
+      "step": 360
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5822784810126583e-06,
+      "loss": 0.6876,
+      "step": 375
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.6586702466011047,
+      "eval_runtime": 9.9,
+      "eval_samples_per_second": 3.838,
+      "eval_steps_per_second": 0.505,
+      "step": 380
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0,
+      "loss": 0.6721,
+      "step": 400
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.6582174897193909,
+      "eval_runtime": 9.916,
+      "eval_samples_per_second": 3.832,
+      "eval_steps_per_second": 0.504,
+      "step": 400
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "total_flos": 2.51016575975424e+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 sha256:151e5ea63fa245c12043d539494804f19b850ffc011d1283b07d441306cd6494
+size 4664