Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-218/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-218/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-218/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-218/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# 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 0.12.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_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 sha256:018dd4c075f785ccbd463824bdae6489309d082a93f9b3040ba00fbc4c631e1b
+size 645956704

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32768
+}

checkpoint-218/optimizer_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451de5d9daa6c389b8d8d53bee0db1c12a1d2b0e2587618cf1ba81b5d5110078
+size 109355164

checkpoint-218/optimizer_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb6aeab0ffa33e9a2f904352a057a0249d0c2a93de3b5ba80c6d218e2864983
+size 109534500

checkpoint-218/pytorch_model_fsdp_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9caebcdf981ec9a37e2842558f61c69c9e98d43cbbdb52eebda39097fb6b41cb
+size 54676992

checkpoint-218/pytorch_model_fsdp_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a13152e49c705e468a84c5614586f43ff90302f88551aa69cac72364a0eebff
+size 54676992

checkpoint-218/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3cad9aaf820e6aa894ab78ce74424d232a8fc619967c61fa9998cfe66bbc4b
+size 14512

checkpoint-218/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076a492e4d991d8c0cf3bdc61847428261c0eec1a4b9e77afddf352b4cc989dc
+size 14512

checkpoint-218/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b1fb572c315e51df9a7ebbd5fa057db8946c1e24126a0a756a286716245ede
+size 1064

checkpoint-218/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9965714285714286,
+  "eval_steps": 500,
+  "global_step": 218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.41318315267562866,
+      "learning_rate": 0.0001908256880733945,
+      "loss": 0.2471,
+      "step": 10
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 0.2800535261631012,
+      "learning_rate": 0.000181651376146789,
+      "loss": 0.2546,
+      "step": 20
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 0.37750667333602905,
+      "learning_rate": 0.00017247706422018351,
+      "loss": 0.2334,
+      "step": 30
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.3601243197917938,
+      "learning_rate": 0.00016330275229357798,
+      "loss": 0.2265,
+      "step": 40
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.2832874059677124,
+      "learning_rate": 0.0001541284403669725,
+      "loss": 0.2302,
+      "step": 50
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.2666235864162445,
+      "learning_rate": 0.00014495412844036697,
+      "loss": 0.2349,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.24652349948883057,
+      "learning_rate": 0.00013577981651376149,
+      "loss": 0.2256,
+      "step": 70
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.4081045389175415,
+      "learning_rate": 0.00012660550458715598,
+      "loss": 0.2224,
+      "step": 80
+    },
+    {
+      "epoch": 0.4114285714285714,
+      "grad_norm": 0.24895720183849335,
+      "learning_rate": 0.00011743119266055047,
+      "loss": 0.2375,
+      "step": 90
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.39015132188796997,
+      "learning_rate": 0.00010825688073394495,
+      "loss": 0.2211,
+      "step": 100
+    },
+    {
+      "epoch": 0.5028571428571429,
+      "grad_norm": 0.292385071516037,
+      "learning_rate": 9.908256880733946e-05,
+      "loss": 0.2192,
+      "step": 110
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.22755630314350128,
+      "learning_rate": 8.990825688073395e-05,
+      "loss": 0.2153,
+      "step": 120
+    },
+    {
+      "epoch": 0.5942857142857143,
+      "grad_norm": 0.24241922795772552,
+      "learning_rate": 8.073394495412844e-05,
+      "loss": 0.2233,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2538710832595825,
+      "learning_rate": 7.155963302752295e-05,
+      "loss": 0.2211,
+      "step": 140
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.26939839124679565,
+      "learning_rate": 6.238532110091744e-05,
+      "loss": 0.2187,
+      "step": 150
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.23713251948356628,
+      "learning_rate": 5.3211009174311934e-05,
+      "loss": 0.214,
+      "step": 160
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 0.2701284885406494,
+      "learning_rate": 4.403669724770643e-05,
+      "loss": 0.2219,
+      "step": 170
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.24489356577396393,
+      "learning_rate": 3.486238532110092e-05,
+      "loss": 0.2177,
+      "step": 180
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 0.21330754458904266,
+      "learning_rate": 2.5688073394495416e-05,
+      "loss": 0.2222,
+      "step": 190
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.23901572823524475,
+      "learning_rate": 1.651376146788991e-05,
+      "loss": 0.2228,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.21248246729373932,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.2091,
+      "step": 210
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.700904762612122e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc7eca6c21906158b76202a6125f2a7339d0aadf7dc9c11ae71a40ac307f4d2
+size 5560