Upload folder using huggingface_hub

checkpoint-90/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
+---
+
+# 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

checkpoint-90/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged",
+  "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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-90/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11ddb49df1857036f58ba2d066491952d7bfa321b08da1c922e2f6aacea5ad4
+size 13648432

checkpoint-90/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3093fdbfa72040cee375f6793558600f6d9087c3f8efa7ae6cf32884036a3b3
+size 27370618

checkpoint-90/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543ef05f530d40ee20b8d626b07a69b86597aca643e48897571062f973efe84f
+size 15024

checkpoint-90/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a23f732e43838ce0398d2636885ac16badbb9bcbc04d1406069ba3027bc5ae0
+size 15024

checkpoint-90/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10cce960e7068b051c05e35ed6160656be9091c63f13796ac2ed7e9c84e5a72
+size 15024

checkpoint-90/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f6049e212b1df5cefc5d834afcd8cc052c73f1457449e9fe8a38d514f54078
+size 15024

checkpoint-90/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5e8b12b9c814e867e9bad19493354b25d611955ef1f97df023b67375d67738
+size 1064

checkpoint-90/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-90/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-90/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + message['content'] + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 8192,
+  "max_length": 8192,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-90/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": 0.4368760883808136,
+  "best_model_checkpoint": "./mistral/20-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.6-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-90_batch_16_2024-04-20_ppid_9/checkpoint-90",
+  "epoch": 5.806451612903226,
+  "eval_steps": 30,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.65,
+      "grad_norm": 16.76080894470215,
+      "learning_rate": 4.770114942528735e-06,
+      "logits/chosen": -1.8055893182754517,
+      "logits/rejected": -1.828260064125061,
+      "logps/chosen": -46.100120544433594,
+      "logps/rejected": -82.48685455322266,
+      "loss": 0.6795,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.04209427908062935,
+      "rewards/margins": 0.04848780483007431,
+      "rewards/rejected": -0.006393528077751398,
+      "step": 10
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 11.445436477661133,
+      "learning_rate": 4.1954022988505746e-06,
+      "logits/chosen": -1.8350013494491577,
+      "logits/rejected": -1.8602994680404663,
+      "logps/chosen": -37.913516998291016,
+      "logps/rejected": -67.64692687988281,
+      "loss": 0.6251,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.15703639388084412,
+      "rewards/margins": 0.1911666840314865,
+      "rewards/rejected": -0.0341302864253521,
+      "step": 20
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 11.545478820800781,
+      "learning_rate": 3.620689655172414e-06,
+      "logits/chosen": -1.8373997211456299,
+      "logits/rejected": -1.847825050354004,
+      "logps/chosen": -29.99410057067871,
+      "logps/rejected": -59.1256217956543,
+      "loss": 0.5772,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.27005138993263245,
+      "rewards/margins": 0.30424270033836365,
+      "rewards/rejected": -0.0341913141310215,
+      "step": 30
+    },
+    {
+      "epoch": 1.94,
+      "eval_logits/chosen": -1.81316077709198,
+      "eval_logits/rejected": -1.8455785512924194,
+      "eval_logps/chosen": -36.48888397216797,
+      "eval_logps/rejected": -55.34504699707031,
+      "eval_loss": 0.5171023011207581,
+      "eval_rewards/accuracies": 0.5,
+      "eval_rewards/chosen": 0.5191236138343811,
+      "eval_rewards/margins": 0.5845221877098083,
+      "eval_rewards/rejected": -0.06539855152368546,
+      "eval_runtime": 2.4917,
+      "eval_samples_per_second": 11.237,
+      "eval_steps_per_second": 1.605,
+      "step": 30
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 7.317459583282471,
+      "learning_rate": 3.0459770114942533e-06,
+      "logits/chosen": -1.7586491107940674,
+      "logits/rejected": -1.7903881072998047,
+      "logps/chosen": -52.9969367980957,
+      "logps/rejected": -87.54074096679688,
+      "loss": 0.5181,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.6470302939414978,
+      "rewards/margins": 0.7092825174331665,
+      "rewards/rejected": -0.06225220113992691,
+      "step": 40
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 5.132155418395996,
+      "learning_rate": 2.471264367816092e-06,
+      "logits/chosen": -1.8951135873794556,
+      "logits/rejected": -1.9210799932479858,
+      "logps/chosen": -34.33287811279297,
+      "logps/rejected": -68.03052520751953,
+      "loss": 0.5415,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 0.5781847238540649,
+      "rewards/margins": 0.6501666903495789,
+      "rewards/rejected": -0.07198190689086914,
+      "step": 50
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 7.053220748901367,
+      "learning_rate": 1.896551724137931e-06,
+      "logits/chosen": -1.9114513397216797,
+      "logits/rejected": -1.9271589517593384,
+      "logps/chosen": -25.962200164794922,
+      "logps/rejected": -48.20077133178711,
+      "loss": 0.5125,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.47203439474105835,
+      "rewards/margins": 0.5603113174438477,
+      "rewards/rejected": -0.08827687054872513,
+      "step": 60
+    },
+    {
+      "epoch": 3.87,
+      "eval_logits/chosen": -1.817034363746643,
+      "eval_logits/rejected": -1.8500827550888062,
+      "eval_logps/chosen": -35.225791931152344,
+      "eval_logps/rejected": -55.629276275634766,
+      "eval_loss": 0.4517291486263275,
+      "eval_rewards/accuracies": 0.5,
+      "eval_rewards/chosen": 0.8980507254600525,
+      "eval_rewards/margins": 1.048719048500061,
+      "eval_rewards/rejected": -0.15066833794116974,
+      "eval_runtime": 2.4913,
+      "eval_samples_per_second": 11.239,
+      "eval_steps_per_second": 1.606,
+      "step": 60
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 3.6152443885803223,
+      "learning_rate": 1.3218390804597702e-06,
+      "logits/chosen": -1.8332040309906006,
+      "logits/rejected": -1.8538074493408203,
+      "logps/chosen": -34.457115173339844,
+      "logps/rejected": -72.48670959472656,
+      "loss": 0.4838,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.6265449523925781,
+      "rewards/margins": 0.7487497329711914,
+      "rewards/rejected": -0.12220476567745209,
+      "step": 70
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 3.271343231201172,
+      "learning_rate": 7.471264367816093e-07,
+      "logits/chosen": -1.7745481729507446,
+      "logits/rejected": -1.784841537475586,
+      "logps/chosen": -52.409339904785156,
+      "logps/rejected": -76.24700164794922,
+      "loss": 0.4665,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.939862847328186,
+      "rewards/margins": 1.0275475978851318,
+      "rewards/rejected": -0.08768495172262192,
+      "step": 80
+    },
+    {
+      "epoch": 5.81,
+      "grad_norm": 2.297419786453247,
+      "learning_rate": 1.7241379310344828e-07,
+      "logits/chosen": -1.8448705673217773,
+      "logits/rejected": -1.8637123107910156,
+      "logps/chosen": -33.81181335449219,
+      "logps/rejected": -63.00860595703125,
+      "loss": 0.491,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.6832905411720276,
+      "rewards/margins": 0.8434805870056152,
+      "rewards/rejected": -0.1601901352405548,
+      "step": 90
+    },
+    {
+      "epoch": 5.81,
+      "eval_logits/chosen": -1.8184903860092163,
+      "eval_logits/rejected": -1.8517436981201172,
+      "eval_logps/chosen": -34.81117630004883,
+      "eval_logps/rejected": -55.731048583984375,
+      "eval_loss": 0.4368760883808136,
+      "eval_rewards/accuracies": 0.5,
+      "eval_rewards/chosen": 1.0224344730377197,
+      "eval_rewards/margins": 1.2036339044570923,
+      "eval_rewards/rejected": -0.18119940161705017,
+      "eval_runtime": 2.4928,
+      "eval_samples_per_second": 11.232,
+      "eval_steps_per_second": 1.605,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-90/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c20933681c819e3eca9593cd0c21a0b47ebbfa7455cec09dcd232391e6516e9
+size 5304