Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-7b-it
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b-it",
+  "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": "kajol-008k-d10",
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077beb24bc616dcd30bcf67566c12d237106baf6d58605ebe7170859364e196b
+size 100059752

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcc5c458f52abddc8f9c025b6f427a688080bb9b0c15985154ebc50b56bbbe9
+size 200249850

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e8a3420e711d29f066d5414ee1c88f79ce73164d8eac918d3048a0f70243d2
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7b358298aa83a40c1b56e5c320426fa83976856684a928a0b4adb7fc547539
+size 1064

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "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
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": 7.237969398498535,
+  "best_model_checkpoint": "out/checkpoint-9",
+  "epoch": 0.03769633507853403,
+  "eval_steps": 1,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 17.85124397277832,
+      "learning_rate": 0.0002,
+      "loss": 10.6824,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 9.331878662109375,
+      "eval_runtime": 735.4997,
+      "eval_samples_per_second": 0.305,
+      "eval_steps_per_second": 0.305,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.460932731628418,
+      "learning_rate": 0.0002,
+      "loss": 9.4215,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 8.825074195861816,
+      "eval_runtime": 735.7631,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.690059661865234,
+      "learning_rate": 0.0002,
+      "loss": 7.7604,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 8.533729553222656,
+      "eval_runtime": 735.7831,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.018722057342529,
+      "learning_rate": 0.0002,
+      "loss": 7.94,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 8.247579574584961,
+      "eval_runtime": 735.7455,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.668647289276123,
+      "learning_rate": 0.0002,
+      "loss": 7.3386,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 8.042969703674316,
+      "eval_runtime": 735.6593,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 9.495285034179688,
+      "learning_rate": 0.0002,
+      "loss": 8.5567,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 7.848848819732666,
+      "eval_runtime": 735.6542,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 10.991780281066895,
+      "learning_rate": 0.0002,
+      "loss": 7.1324,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 7.553219795227051,
+      "eval_runtime": 735.6545,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0002,
+      "loss": 6.999,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 7.553219795227051,
+      "eval_runtime": 735.6924,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 15.588254928588867,
+      "learning_rate": 0.0002,
+      "loss": 8.0144,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 7.237969398498535,
+      "eval_runtime": 735.7337,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.304,
+      "step": 9
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "total_flos": 1719982274641920.0,
+  "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 sha256:8919c1c1e60677b180f6fd3323b6f7355a6ad3f11f2b3708c33f8c931b705f62
+size 4856