Upload folder using huggingface_hub

checkpoint-8/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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-8/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 64,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-8/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69017f73c4a48d2c19578829eeebafe31f094bdc9baf78851563faec7b8bf23
+size 167832240

checkpoint-8/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-8/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4cc81aba190782279f650153c8908381bf07d53f9942cebeacd819aab610e0
+size 84575956

checkpoint-8/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f1ad5db3cf1a4420d5a566f296f11888efa93c608a58160aa55b8f2ba4b626
+size 14244

checkpoint-8/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6864207a1837047f5ab1d864e4374754ccba404d60841effd791d29982764b93
+size 1064

checkpoint-8/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
+  }
+}

checkpoint-8/tokenizer.model

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

checkpoint-8/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-8/trainer_state.json

@@ -0,0 +1,165 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.002535004852157725,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0003168756065197156,
+      "grad_norm": 6.832624876551563e-06,
+      "learning_rate": 2.9996830427892237e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 2.0139850676059723e-08,
+      "objective/entropy": 56.029441833496094,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.5591201782226562,
+      "objective/scores": -0.559173583984375,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.46982458233833313,
+      "step": 1,
+      "timer/training_step": 4.71628999710083,
+      "val/num_eos_tokens": 0.75,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.0006337512130394313,
+      "grad_norm": 7.318521966226399e-06,
+      "learning_rate": 2.999366085578447e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 1.0943040251731873e-08,
+      "objective/entropy": 49.566184997558594,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.7360076904296875,
+      "objective/scores": -0.73590087890625,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.47101089358329773,
+      "step": 2,
+      "timer/training_step": 5.188745975494385,
+      "val/num_eos_tokens": 1.21875,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.0009506268195591468,
+      "grad_norm": 6.249741545616416e-06,
+      "learning_rate": 2.9990491283676707e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 8.149072527885437e-09,
+      "objective/entropy": 57.22004699707031,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.70709228515625,
+      "objective/scores": -0.70703125,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4886399507522583,
+      "step": 3,
+      "timer/training_step": 4.847959518432617,
+      "val/num_eos_tokens": 0.53125,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.0012675024260788625,
+      "grad_norm": 7.052934051898774e-06,
+      "learning_rate": 2.998732171156894e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 1.0710209608078003e-08,
+      "objective/entropy": 59.56321716308594,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.716552734375,
+      "objective/scores": -0.71685791015625,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4839285612106323,
+      "step": 4,
+      "timer/training_step": 5.577988624572754,
+      "val/num_eos_tokens": 0.4375,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.001584378032598578,
+      "grad_norm": 8.835036169330124e-06,
+      "learning_rate": 2.9984152139461176e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 2.3748725652694702e-08,
+      "objective/entropy": 45.10405731201172,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.444000244140625,
+      "objective/scores": -0.44439697265625,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4351224899291992,
+      "step": 5,
+      "timer/training_step": 5.305084705352783,
+      "val/num_eos_tokens": 1.0,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.0019012536391182935,
+      "grad_norm": 6.025600214343285e-06,
+      "learning_rate": 2.998098256735341e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 7.450580596923828e-09,
+      "objective/entropy": 60.55895233154297,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.746917724609375,
+      "objective/scores": -0.7470703125,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4965381920337677,
+      "step": 6,
+      "timer/training_step": 4.756265640258789,
+      "val/num_eos_tokens": 0.53125,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.002218129245638009,
+      "grad_norm": 9.883336133498233e-06,
+      "learning_rate": 2.997781299524564e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 1.6298145055770874e-08,
+      "objective/entropy": 56.12989807128906,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.58819580078125,
+      "objective/scores": -0.58782958984375,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4676559567451477,
+      "step": 7,
+      "timer/training_step": 5.001364707946777,
+      "val/num_eos_tokens": 0.65625,
+      "val/ratio": 1.0
+    },
+    {
+      "epoch": 0.002535004852157725,
+      "grad_norm": 3.0753049031773116e-06,
+      "learning_rate": 2.9974643423137877e-06,
+      "loss": 0.0,
+      "loss/policy_avg": 3.259629011154175e-09,
+      "objective/entropy": 52.772064208984375,
+      "objective/kl": 0.0,
+      "objective/rlhf_reward": -0.8326416015625,
+      "objective/scores": -0.83258056640625,
+      "policy/approxkl_avg": 0.0,
+      "policy/clipfrac_avg": 0.0,
+      "policy/entropy_avg": 0.4242881238460541,
+      "step": 8,
+      "timer/training_step": 5.542971134185791,
+      "val/num_eos_tokens": 0.40625,
+      "val/ratio": 1.0
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 9465,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "total_flos": 5677993863069696.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4790157c5fbd0cb6249bce3f856574e5353406ee2bfdde3cf3f2571e6337a71c
+size 5240

runs/May06_21-16-51_2efa04e46d11/events.out.tfevents.1715030211.2efa04e46d11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a419c80c25f1cae692076dc240bfd8fbd21ad442805fad2eab7a89cfe66d12
-size 12233
+oid sha256:f8b475c5c6cf4308cfac265ea2845c327e2b164789d1379f2bf02b8b481edde8
+size 16840