Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+widget:
+ - messages:
+ - role: user
+ content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+ model_path,
+ device_map="auto",
+ torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+ {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,29 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "FelixChao/WestSeverus-7B-DPO-v2",
+ "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": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_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 sha256:10cb162d1174b7eada448dce40914a41cd4397087709d23445073cc312eb30e9
+size 27280152

checkpoint-1730/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: FelixChao/WestSeverus-7B-DPO-v2
+---
+
+# 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-1730/adapter_config.json

@@ -0,0 +1,29 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "FelixChao/WestSeverus-7B-DPO-v2",
+ "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": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v_proj",
+ "q_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}

checkpoint-1730/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cb162d1174b7eada448dce40914a41cd4397087709d23445073cc312eb30e9
+size 27280152

checkpoint-1730/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e5ea926f30dec8f1f7ea4bd3a1262e895be52be50c1038d1ed588c4f35e246
+size 54633978

checkpoint-1730/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-1730/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41b4c69c37bb2ed79fa5d2d52ea3cb72f6d4d261e0a9c3cf68da3def25cdafb
+size 14244

checkpoint-1730/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a45be167dd78c26eb868a87918e04ed24d92531f833212cb351b7fb0aaebd40
+size 1064

checkpoint-1730/special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "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": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-1730/tokenizer.model

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

checkpoint-1730/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+ "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": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "bos_token": "<s>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": true,
+ "model_max_length": 255,
+ "pad_token": "<unk>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": true
+}

checkpoint-1730/trainer_state.json

@@ -0,0 +1,504 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 5.0,
+ "eval_steps": 500,
+ "global_step": 1730,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.07,
+ "grad_norm": 4.66322660446167,
+ "learning_rate": 2.8901734104046245e-05,
+ "loss": 2.8724,
+ "step": 25
+ },
+ {
+ "epoch": 0.14,
+ "grad_norm": 4.364796161651611,
+ "learning_rate": 5.780346820809249e-05,
+ "loss": 1.8669,
+ "step": 50
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 7.0544962882995605,
+ "learning_rate": 8.670520231213874e-05,
+ "loss": 1.0394,
+ "step": 75
+ },
+ {
+ "epoch": 0.29,
+ "grad_norm": 2.588165521621704,
+ "learning_rate": 0.00011560693641618498,
+ "loss": 0.8095,
+ "step": 100
+ },
+ {
+ "epoch": 0.36,
+ "grad_norm": 2.311723470687866,
+ "learning_rate": 0.00014450867052023122,
+ "loss": 0.7673,
+ "step": 125
+ },
+ {
+ "epoch": 0.43,
+ "grad_norm": 2.0632615089416504,
+ "learning_rate": 0.00017341040462427748,
+ "loss": 0.7738,
+ "step": 150
+ },
+ {
+ "epoch": 0.51,
+ "grad_norm": 1.7875710725784302,
+ "learning_rate": 0.00019974309569685292,
+ "loss": 0.7151,
+ "step": 175
+ },
+ {
+ "epoch": 0.58,
+ "grad_norm": 1.7314724922180176,
+ "learning_rate": 0.00019653179190751445,
+ "loss": 0.6782,
+ "step": 200
+ },
+ {
+ "epoch": 0.65,
+ "grad_norm": 2.1410841941833496,
+ "learning_rate": 0.00019332048811817598,
+ "loss": 0.6733,
+ "step": 225
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 1.6796475648880005,
+ "learning_rate": 0.0001901091843288375,
+ "loss": 0.711,
+ "step": 250
+ },
+ {
+ "epoch": 0.79,
+ "grad_norm": 1.9651137590408325,
+ "learning_rate": 0.00018689788053949903,
+ "loss": 0.6285,
+ "step": 275
+ },
+ {
+ "epoch": 0.87,
+ "grad_norm": 1.9334725141525269,
+ "learning_rate": 0.00018368657675016056,
+ "loss": 0.6387,
+ "step": 300
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 1.9697507619857788,
+ "learning_rate": 0.00018047527296082209,
+ "loss": 0.6203,
+ "step": 325
+ },
+ {
+ "epoch": 1.01,
+ "grad_norm": 1.5927447080612183,
+ "learning_rate": 0.0001772639691714836,
+ "loss": 0.6036,
+ "step": 350
+ },
+ {
+ "epoch": 1.08,
+ "grad_norm": 1.5775573253631592,
+ "learning_rate": 0.00017405266538214514,
+ "loss": 0.5443,
+ "step": 375
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 2.265123128890991,
+ "learning_rate": 0.0001708413615928067,
+ "loss": 0.5864,
+ "step": 400
+ },
+ {
+ "epoch": 1.23,
+ "grad_norm": 1.9081721305847168,
+ "learning_rate": 0.00016763005780346822,
+ "loss": 0.497,
+ "step": 425
+ },
+ {
+ "epoch": 1.3,
+ "grad_norm": 1.7822768688201904,
+ "learning_rate": 0.00016441875401412975,
+ "loss": 0.5652,
+ "step": 450
+ },
+ {
+ "epoch": 1.37,
+ "grad_norm": 1.585552453994751,
+ "learning_rate": 0.00016120745022479128,
+ "loss": 0.5356,
+ "step": 475
+ },
+ {
+ "epoch": 1.45,
+ "grad_norm": 1.8936752080917358,
+ "learning_rate": 0.0001579961464354528,
+ "loss": 0.4897,
+ "step": 500
+ },
+ {
+ "epoch": 1.52,
+ "grad_norm": 1.7502835988998413,
+ "learning_rate": 0.00015478484264611433,
+ "loss": 0.5051,
+ "step": 525
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 1.6106928586959839,
+ "learning_rate": 0.00015157353885677586,
+ "loss": 0.5034,
+ "step": 550
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 1.6488401889801025,
+ "learning_rate": 0.00014836223506743738,
+ "loss": 0.4692,
+ "step": 575
+ },
+ {
+ "epoch": 1.73,
+ "grad_norm": 1.5491576194763184,
+ "learning_rate": 0.0001451509312780989,
+ "loss": 0.5016,
+ "step": 600
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 1.7753480672836304,
+ "learning_rate": 0.00014193962748876044,
+ "loss": 0.4836,
+ "step": 625
+ },
+ {
+ "epoch": 1.88,
+ "grad_norm": 1.5605947971343994,
+ "learning_rate": 0.00013872832369942197,
+ "loss": 0.5059,
+ "step": 650
+ },
+ {
+ "epoch": 1.95,
+ "grad_norm": 1.4864176511764526,
+ "learning_rate": 0.0001355170199100835,
+ "loss": 0.4667,
+ "step": 675
+ },
+ {
+ "epoch": 2.02,
+ "grad_norm": 1.6282180547714233,
+ "learning_rate": 0.00013230571612074502,
+ "loss": 0.4208,
+ "step": 700
+ },
+ {
+ "epoch": 2.1,
+ "grad_norm": 1.9214680194854736,
+ "learning_rate": 0.00012909441233140655,
+ "loss": 0.3733,
+ "step": 725
+ },
+ {
+ "epoch": 2.17,
+ "grad_norm": 1.9027807712554932,
+ "learning_rate": 0.00012588310854206808,
+ "loss": 0.3831,
+ "step": 750
+ },
+ {
+ "epoch": 2.24,
+ "grad_norm": 1.756855845451355,
+ "learning_rate": 0.0001226718047527296,
+ "loss": 0.3876,
+ "step": 775
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 1.5269505977630615,
+ "learning_rate": 0.00011946050096339114,
+ "loss": 0.3847,
+ "step": 800
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 1.7476940155029297,
+ "learning_rate": 0.00011624919717405267,
+ "loss": 0.3604,
+ "step": 825
+ },
+ {
+ "epoch": 2.46,
+ "grad_norm": 1.8043824434280396,
+ "learning_rate": 0.0001130378933847142,
+ "loss": 0.384,
+ "step": 850
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 1.4151132106781006,
+ "learning_rate": 0.00010982658959537572,
+ "loss": 0.3745,
+ "step": 875
+ },
+ {
+ "epoch": 2.6,
+ "grad_norm": 1.907926082611084,
+ "learning_rate": 0.00010661528580603725,
+ "loss": 0.372,
+ "step": 900
+ },
+ {
+ "epoch": 2.67,
+ "grad_norm": 1.8263049125671387,
+ "learning_rate": 0.00010340398201669879,
+ "loss": 0.3972,
+ "step": 925
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 1.8957775831222534,
+ "learning_rate": 0.00010019267822736032,
+ "loss": 0.3967,
+ "step": 950
+ },
+ {
+ "epoch": 2.82,
+ "grad_norm": 1.772609829902649,
+ "learning_rate": 9.698137443802185e-05,
+ "loss": 0.3775,
+ "step": 975
+ },
+ {
+ "epoch": 2.89,
+ "grad_norm": 1.976365566253662,
+ "learning_rate": 9.377007064868337e-05,
+ "loss": 0.4043,
+ "step": 1000
+ },
+ {
+ "epoch": 2.96,
+ "grad_norm": 1.689432978630066,
+ "learning_rate": 9.05587668593449e-05,
+ "loss": 0.3226,
+ "step": 1025
+ },
+ {
+ "epoch": 3.03,
+ "grad_norm": 1.9092849493026733,
+ "learning_rate": 8.734746307000643e-05,
+ "loss": 0.3758,
+ "step": 1050
+ },
+ {
+ "epoch": 3.11,
+ "grad_norm": 1.7606756687164307,
+ "learning_rate": 8.413615928066796e-05,
+ "loss": 0.3095,
+ "step": 1075
+ },
+ {
+ "epoch": 3.18,
+ "grad_norm": 1.8509767055511475,
+ "learning_rate": 8.092485549132948e-05,
+ "loss": 0.2712,
+ "step": 1100
+ },
+ {
+ "epoch": 3.25,
+ "grad_norm": 1.5414364337921143,
+ "learning_rate": 7.771355170199101e-05,
+ "loss": 0.2695,
+ "step": 1125
+ },
+ {
+ "epoch": 3.32,
+ "grad_norm": 1.8055434226989746,
+ "learning_rate": 7.450224791265255e-05,
+ "loss": 0.2828,
+ "step": 1150
+ },
+ {
+ "epoch": 3.4,
+ "grad_norm": 2.0254344940185547,
+ "learning_rate": 7.129094412331408e-05,
+ "loss": 0.2729,
+ "step": 1175
+ },
+ {
+ "epoch": 3.47,
+ "grad_norm": 2.2866463661193848,
+ "learning_rate": 6.80796403339756e-05,
+ "loss": 0.3022,
+ "step": 1200
+ },
+ {
+ "epoch": 3.54,
+ "grad_norm": 1.5647475719451904,
+ "learning_rate": 6.486833654463712e-05,
+ "loss": 0.2893,
+ "step": 1225
+ },
+ {
+ "epoch": 3.61,
+ "grad_norm": 1.9078121185302734,
+ "learning_rate": 6.165703275529865e-05,
+ "loss": 0.2751,
+ "step": 1250
+ },
+ {
+ "epoch": 3.68,
+ "grad_norm": 1.9310845136642456,
+ "learning_rate": 5.844572896596018e-05,
+ "loss": 0.2614,
+ "step": 1275
+ },
+ {
+ "epoch": 3.76,
+ "grad_norm": 1.5173165798187256,
+ "learning_rate": 5.523442517662171e-05,
+ "loss": 0.2781,
+ "step": 1300
+ },
+ {
+ "epoch": 3.83,
+ "grad_norm": 2.2908642292022705,
+ "learning_rate": 5.2023121387283234e-05,
+ "loss": 0.2889,
+ "step": 1325
+ },
+ {
+ "epoch": 3.9,
+ "grad_norm": 2.0346012115478516,
+ "learning_rate": 4.881181759794477e-05,
+ "loss": 0.2997,
+ "step": 1350
+ },
+ {
+ "epoch": 3.97,
+ "grad_norm": 1.6963484287261963,
+ "learning_rate": 4.56005138086063e-05,
+ "loss": 0.2415,
+ "step": 1375
+ },
+ {
+ "epoch": 4.05,
+ "grad_norm": 1.552463173866272,
+ "learning_rate": 4.238921001926782e-05,
+ "loss": 0.229,
+ "step": 1400
+ },
+ {
+ "epoch": 4.12,
+ "grad_norm": 2.3235974311828613,
+ "learning_rate": 3.917790622992935e-05,
+ "loss": 0.1927,
+ "step": 1425
+ },
+ {
+ "epoch": 4.19,
+ "grad_norm": 1.6171674728393555,
+ "learning_rate": 3.596660244059088e-05,
+ "loss": 0.2116,
+ "step": 1450
+ },
+ {
+ "epoch": 4.26,
+ "grad_norm": 1.9670432806015015,
+ "learning_rate": 3.275529865125241e-05,
+ "loss": 0.207,
+ "step": 1475
+ },
+ {
+ "epoch": 4.34,
+ "grad_norm": 2.1716980934143066,
+ "learning_rate": 2.9543994861913938e-05,
+ "loss": 0.2023,
+ "step": 1500
+ },
+ {
+ "epoch": 4.41,
+ "grad_norm": 2.0103349685668945,
+ "learning_rate": 2.6332691072575465e-05,
+ "loss": 0.2081,
+ "step": 1525
+ },
+ {
+ "epoch": 4.48,
+ "grad_norm": 2.488182544708252,
+ "learning_rate": 2.3121387283236996e-05,
+ "loss": 0.2206,
+ "step": 1550
+ },
+ {
+ "epoch": 4.55,
+ "grad_norm": 2.150543451309204,
+ "learning_rate": 1.9910083493898523e-05,
+ "loss": 0.1989,
+ "step": 1575
+ },
+ {
+ "epoch": 4.62,
+ "grad_norm": 1.952592134475708,
+ "learning_rate": 1.6698779704560053e-05,
+ "loss": 0.2074,
+ "step": 1600
+ },
+ {
+ "epoch": 4.7,
+ "grad_norm": 1.8111902475357056,
+ "learning_rate": 1.348747591522158e-05,
+ "loss": 0.2122,
+ "step": 1625
+ },
+ {
+ "epoch": 4.77,
+ "grad_norm": 2.595923662185669,
+ "learning_rate": 1.027617212588311e-05,
+ "loss": 0.191,
+ "step": 1650
+ },
+ {
+ "epoch": 4.84,
+ "grad_norm": 2.17901611328125,
+ "learning_rate": 7.064868336544637e-06,
+ "loss": 0.2205,
+ "step": 1675
+ },
+ {
+ "epoch": 4.91,
+ "grad_norm": 2.284546136856079,
+ "learning_rate": 3.853564547206165e-06,
+ "loss": 0.2239,
+ "step": 1700
+ },
+ {
+ "epoch": 4.99,
+ "grad_norm": 2.4415647983551025,
+ "learning_rate": 6.422607578676943e-07,
+ "loss": 0.1967,
+ "step": 1725
+ }
+ ],
+ "logging_steps": 25,
+ "max_steps": 1730,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 500,
+ "total_flos": 7.5248089823232e+16,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-1730/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5651da0f60fb42e708a71f4df3418443474660dadaf10118fea5af3c40373954
+size 4984

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+ "additional_special_tokens": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "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": "<unk>",
+ "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+ "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": [
+ "<unk>",
+ "<s>",
+ "</s>"
+ ],
+ "bos_token": "<s>",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": true,
+ "model_max_length": 255,
+ "pad_token": "<unk>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5651da0f60fb42e708a71f4df3418443474660dadaf10118fea5af3c40373954
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+ "model": "FelixChao/WestSeverus-7B-DPO-v2",
+ "project_name": "westseverus-finetune2",
+ "data_path": "westseverus-finetune2/autotrain-data",
+ "train_split": "train",
+ "valid_split": null,
+ "add_eos_token": false,
+ "block_size": -1,
+ "model_max_length": 1024,
+ "padding": null,
+ "trainer": "sft",
+ "use_flash_attention_2": false,
+ "log": "none",
+ "disable_gradient_checkpointing": false,
+ "logging_steps": -1,
+ "evaluation_strategy": "epoch",
+ "save_total_limit": 1,
+ "save_strategy": "epoch",
+ "auto_find_batch_size": false,
+ "mixed_precision": null,
+ "lr": 0.0002,
+ "epochs": 5,
+ "batch_size": 4,
+ "warmup_ratio": 0.1,
+ "gradient_accumulation": 1,
+ "optimizer": "adamw_torch",
+ "scheduler": "linear",
+ "weight_decay": 0.0,
+ "max_grad_norm": 1.0,
+ "seed": 42,
+ "chat_template": null,
+ "quantization": "int4",
+ "target_modules": "q_proj,v_proj",
+ "merge_adapter": false,
+ "peft": true,
+ "lora_r": 16,
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "model_ref": null,
+ "dpo_beta": 0.1,
+ "prompt_text_column": "autotrain_prompt",
+ "text_column": "autotrain_text",
+ "rejected_text_column": "autotrain_rejected_text",
+ "push_to_hub": true,
+ "repo_id": "shaswatamitra/westseverus-finetuned2",
+ "username": null
+}