Upload folder using huggingface_hub (#1)

- 9ee22d80406efdbd6d055aea98f233b70e7cc471168d67c826adf2b306ec22c6 (4f3bfd3c44fed639c35617b9f814ce233aaf281b)

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ai21labs/Jamba-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 0.10.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai21labs/Jamba-v0.1",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "embed_tokens",
+    "x_proj",
+    "out_proj",
+    "in_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 sha256:2100348a9551a417a4d2e9649fe559e0be7d244c7d321b08959fb751816e8823
+size 1112951304

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a91ccc703d775542510497fd7e33d6d81f57c437bf2de289ba43ffd053478b3
+size 78516026

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdd816c1ce4c0b434bf5d4121c664ed520f775cf932fc14981944b58c056894
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,371 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 22.986753463745117,
+      "learning_rate": 0.00198,
+      "loss": 1.7003,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 8.073963165283203,
+      "learning_rate": 0.00196,
+      "loss": 1.9785,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 7.6197099685668945,
+      "learning_rate": 0.0019399999999999999,
+      "loss": 1.9353,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.2731146812438965,
+      "learning_rate": 0.00192,
+      "loss": 1.5962,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.425559043884277,
+      "learning_rate": 0.0019,
+      "loss": 1.389,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.872774600982666,
+      "learning_rate": 0.00188,
+      "loss": 1.4156,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.199490070343018,
+      "learning_rate": 0.00186,
+      "loss": 1.6583,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.413191318511963,
+      "learning_rate": 0.00184,
+      "loss": 1.4334,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.90674352645874,
+      "learning_rate": 0.00182,
+      "loss": 1.6046,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.410930633544922,
+      "learning_rate": 0.0018000000000000002,
+      "loss": 1.5504,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.529223680496216,
+      "learning_rate": 0.0017800000000000001,
+      "loss": 1.6463,
+      "step": 110
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.781284332275391,
+      "learning_rate": 0.00176,
+      "loss": 1.6136,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.6382951736450195,
+      "learning_rate": 0.00174,
+      "loss": 1.5105,
+      "step": 130
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.392839431762695,
+      "learning_rate": 0.00172,
+      "loss": 1.6061,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.9011926651000977,
+      "learning_rate": 0.0017,
+      "loss": 1.6188,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.002920627593994,
+      "learning_rate": 0.00168,
+      "loss": 1.4177,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.34838342666626,
+      "learning_rate": 0.00166,
+      "loss": 1.5689,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.142854690551758,
+      "learning_rate": 0.00164,
+      "loss": 1.5804,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.837989330291748,
+      "learning_rate": 0.0016200000000000001,
+      "loss": 1.5981,
+      "step": 190
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.33852219581604,
+      "learning_rate": 0.0016,
+      "loss": 1.4347,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.069826602935791,
+      "learning_rate": 0.00158,
+      "loss": 1.4809,
+      "step": 210
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.71095609664917,
+      "learning_rate": 0.0015600000000000002,
+      "loss": 1.388,
+      "step": 220
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.450407981872559,
+      "learning_rate": 0.0015400000000000001,
+      "loss": 1.603,
+      "step": 230
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.475738048553467,
+      "learning_rate": 0.00152,
+      "loss": 1.5731,
+      "step": 240
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.051819086074829,
+      "learning_rate": 0.0015,
+      "loss": 1.5133,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.014269828796387,
+      "learning_rate": 0.00148,
+      "loss": 1.5458,
+      "step": 260
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.558957815170288,
+      "learning_rate": 0.00146,
+      "loss": 1.4918,
+      "step": 270
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.6234660148620605,
+      "learning_rate": 0.0014399999999999999,
+      "loss": 1.5247,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.9923095703125,
+      "learning_rate": 0.00142,
+      "loss": 1.6671,
+      "step": 290
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.883978366851807,
+      "learning_rate": 0.0014,
+      "loss": 1.5732,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.3218066692352295,
+      "learning_rate": 0.00138,
+      "loss": 1.6297,
+      "step": 310
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.045559883117676,
+      "learning_rate": 0.00136,
+      "loss": 1.6581,
+      "step": 320
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.832301139831543,
+      "learning_rate": 0.00134,
+      "loss": 1.6966,
+      "step": 330
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.6719107627868652,
+      "learning_rate": 0.00132,
+      "loss": 1.5904,
+      "step": 340
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.4335455894470215,
+      "learning_rate": 0.0013000000000000002,
+      "loss": 1.6643,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.2848339080810547,
+      "learning_rate": 0.00128,
+      "loss": 1.4174,
+      "step": 360
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.8206841945648193,
+      "learning_rate": 0.00126,
+      "loss": 1.7362,
+      "step": 370
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.389599084854126,
+      "learning_rate": 0.00124,
+      "loss": 1.6058,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.887266159057617,
+      "learning_rate": 0.00122,
+      "loss": 1.4604,
+      "step": 390
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.9653384685516357,
+      "learning_rate": 0.0012,
+      "loss": 1.5152,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.5362136363983154,
+      "learning_rate": 0.00118,
+      "loss": 1.469,
+      "step": 410
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.7318670749664307,
+      "learning_rate": 0.00116,
+      "loss": 1.4136,
+      "step": 420
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.6364078521728516,
+      "learning_rate": 0.00114,
+      "loss": 1.6937,
+      "step": 430
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.9428081512451172,
+      "learning_rate": 0.0011200000000000001,
+      "loss": 1.4825,
+      "step": 440
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.1813700199127197,
+      "learning_rate": 0.0011,
+      "loss": 1.4593,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.612652778625488,
+      "learning_rate": 0.00108,
+      "loss": 1.389,
+      "step": 460
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.5145719051361084,
+      "learning_rate": 0.0010600000000000002,
+      "loss": 1.3896,
+      "step": 470
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.4980382919311523,
+      "learning_rate": 0.0010400000000000001,
+      "loss": 1.3725,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.6995227336883545,
+      "learning_rate": 0.00102,
+      "loss": 1.4769,
+      "step": 490
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.1483154296875,
+      "learning_rate": 0.001,
+      "loss": 1.5983,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.0788232684018176e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0781d3934894a85ed10792c9299f0e56b467495a17caf2881d6aaf20b1f3d0b7
+size 4856