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": "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": 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": [
+    "q_proj",
+    "v_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 sha256:9de164553d9875ff6b058a1c80ac9771a26ab20bbcf138d4490b905849bcd597
+size 27280152

checkpoint-2505/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-2505/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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": 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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2505/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de164553d9875ff6b058a1c80ac9771a26ab20bbcf138d4490b905849bcd597
+size 27280152

checkpoint-2505/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58468843091391e5a39ce46dc514616482488f40644155a5ba9deca22a03086e
+size 54633978

checkpoint-2505/pytorch_model.bin

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

checkpoint-2505/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabecaffa98a0420962e974473eb5688f0bc26aa4827c54a328c507b30c9ccc0
+size 14244

checkpoint-2505/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58df76e46c39eb1aff5e11e85c2d8d3dfbf27f9a9ea14408dfe371256bf0fd4
+size 1064

checkpoint-2505/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2505/tokenizer.model

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

checkpoint-2505/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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": "{{ 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": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2505/trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2505,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.029940119760479042,
+      "grad_norm": 1.6695125102996826,
+      "learning_rate": 2.98804780876494e-06,
+      "loss": 1.1663,
+      "step": 25
+    },
+    {
+      "epoch": 0.059880239520958084,
+      "grad_norm": 1.2466001510620117,
+      "learning_rate": 5.97609561752988e-06,
+      "loss": 1.0872,
+      "step": 50
+    },
+    {
+      "epoch": 0.08982035928143713,
+      "grad_norm": 1.3031201362609863,
+      "learning_rate": 8.964143426294822e-06,
+      "loss": 1.0409,
+      "step": 75
+    },
+    {
+      "epoch": 0.11976047904191617,
+      "grad_norm": 1.2915183305740356,
+      "learning_rate": 1.195219123505976e-05,
+      "loss": 0.9647,
+      "step": 100
+    },
+    {
+      "epoch": 0.1497005988023952,
+      "grad_norm": 1.2883236408233643,
+      "learning_rate": 1.4940239043824702e-05,
+      "loss": 0.8845,
+      "step": 125
+    },
+    {
+      "epoch": 0.17964071856287425,
+      "grad_norm": 1.2346601486206055,
+      "learning_rate": 1.7928286852589643e-05,
+      "loss": 0.7993,
+      "step": 150
+    },
+    {
+      "epoch": 0.20958083832335328,
+      "grad_norm": 1.6535353660583496,
+      "learning_rate": 2.0916334661354585e-05,
+      "loss": 0.7358,
+      "step": 175
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 1.7455912828445435,
+      "learning_rate": 2.390438247011952e-05,
+      "loss": 0.7181,
+      "step": 200
+    },
+    {
+      "epoch": 0.2694610778443114,
+      "grad_norm": 1.9179027080535889,
+      "learning_rate": 2.6892430278884462e-05,
+      "loss": 0.6732,
+      "step": 225
+    },
+    {
+      "epoch": 0.2994011976047904,
+      "grad_norm": 1.792811393737793,
+      "learning_rate": 2.9880478087649403e-05,
+      "loss": 0.6535,
+      "step": 250
+    },
+    {
+      "epoch": 0.32934131736526945,
+      "grad_norm": 1.7675724029541016,
+      "learning_rate": 2.9680567879325643e-05,
+      "loss": 0.6498,
+      "step": 275
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 1.713584303855896,
+      "learning_rate": 2.9347826086956523e-05,
+      "loss": 0.6196,
+      "step": 300
+    },
+    {
+      "epoch": 0.38922155688622756,
+      "grad_norm": 1.8329033851623535,
+      "learning_rate": 2.90150842945874e-05,
+      "loss": 0.6241,
+      "step": 325
+    },
+    {
+      "epoch": 0.41916167664670656,
+      "grad_norm": 1.9062732458114624,
+      "learning_rate": 2.868234250221828e-05,
+      "loss": 0.6262,
+      "step": 350
+    },
+    {
+      "epoch": 0.4491017964071856,
+      "grad_norm": 2.1072585582733154,
+      "learning_rate": 2.834960070984916e-05,
+      "loss": 0.6337,
+      "step": 375
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 1.9632734060287476,
+      "learning_rate": 2.8016858917480035e-05,
+      "loss": 0.6225,
+      "step": 400
+    },
+    {
+      "epoch": 0.5089820359281437,
+      "grad_norm": 1.9905979633331299,
+      "learning_rate": 2.7684117125110915e-05,
+      "loss": 0.6079,
+      "step": 425
+    },
+    {
+      "epoch": 0.5389221556886228,
+      "grad_norm": 1.9922906160354614,
+      "learning_rate": 2.735137533274179e-05,
+      "loss": 0.615,
+      "step": 450
+    },
+    {
+      "epoch": 0.5688622754491018,
+      "grad_norm": 1.898781418800354,
+      "learning_rate": 2.701863354037267e-05,
+      "loss": 0.612,
+      "step": 475
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 2.038163423538208,
+      "learning_rate": 2.668589174800355e-05,
+      "loss": 0.6307,
+      "step": 500
+    },
+    {
+      "epoch": 0.6287425149700598,
+      "grad_norm": 1.7456048727035522,
+      "learning_rate": 2.635314995563443e-05,
+      "loss": 0.6021,
+      "step": 525
+    },
+    {
+      "epoch": 0.6586826347305389,
+      "grad_norm": 1.9026494026184082,
+      "learning_rate": 2.6020408163265307e-05,
+      "loss": 0.6123,
+      "step": 550
+    },
+    {
+      "epoch": 0.688622754491018,
+      "grad_norm": 1.8563848733901978,
+      "learning_rate": 2.5687666370896187e-05,
+      "loss": 0.6272,
+      "step": 575
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 1.7864805459976196,
+      "learning_rate": 2.5354924578527063e-05,
+      "loss": 0.6147,
+      "step": 600
+    },
+    {
+      "epoch": 0.7485029940119761,
+      "grad_norm": 1.581784963607788,
+      "learning_rate": 2.5022182786157943e-05,
+      "loss": 0.6003,
+      "step": 625
+    },
+    {
+      "epoch": 0.7784431137724551,
+      "grad_norm": 1.7364259958267212,
+      "learning_rate": 2.4689440993788823e-05,
+      "loss": 0.5972,
+      "step": 650
+    },
+    {
+      "epoch": 0.8083832335329342,
+      "grad_norm": 1.889833927154541,
+      "learning_rate": 2.43566992014197e-05,
+      "loss": 0.6206,
+      "step": 675
+    },
+    {
+      "epoch": 0.8383233532934131,
+      "grad_norm": 1.6451694965362549,
+      "learning_rate": 2.402395740905058e-05,
+      "loss": 0.6084,
+      "step": 700
+    },
+    {
+      "epoch": 0.8682634730538922,
+      "grad_norm": 1.9670981168746948,
+      "learning_rate": 2.3691215616681455e-05,
+      "loss": 0.58,
+      "step": 725
+    },
+    {
+      "epoch": 0.8982035928143712,
+      "grad_norm": 1.8126428127288818,
+      "learning_rate": 2.3358473824312335e-05,
+      "loss": 0.6039,
+      "step": 750
+    },
+    {
+      "epoch": 0.9281437125748503,
+      "grad_norm": 1.6846369504928589,
+      "learning_rate": 2.302573203194321e-05,
+      "loss": 0.6032,
+      "step": 775
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 1.777023434638977,
+      "learning_rate": 2.269299023957409e-05,
+      "loss": 0.5884,
+      "step": 800
+    },
+    {
+      "epoch": 0.9880239520958084,
+      "grad_norm": 1.7603051662445068,
+      "learning_rate": 2.2360248447204967e-05,
+      "loss": 0.6098,
+      "step": 825
+    },
+    {
+      "epoch": 1.0179640718562875,
+      "grad_norm": 1.8388431072235107,
+      "learning_rate": 2.2027506654835847e-05,
+      "loss": 0.5802,
+      "step": 850
+    },
+    {
+      "epoch": 1.0479041916167664,
+      "grad_norm": 1.9411472082138062,
+      "learning_rate": 2.1694764862466724e-05,
+      "loss": 0.596,
+      "step": 875
+    },
+    {
+      "epoch": 1.0778443113772456,
+      "grad_norm": 1.8858859539031982,
+      "learning_rate": 2.1362023070097603e-05,
+      "loss": 0.5776,
+      "step": 900
+    },
+    {
+      "epoch": 1.1077844311377245,
+      "grad_norm": 1.9276236295700073,
+      "learning_rate": 2.1029281277728483e-05,
+      "loss": 0.5673,
+      "step": 925
+    },
+    {
+      "epoch": 1.1377245508982037,
+      "grad_norm": 2.1130690574645996,
+      "learning_rate": 2.0696539485359363e-05,
+      "loss": 0.5859,
+      "step": 950
+    },
+    {
+      "epoch": 1.1676646706586826,
+      "grad_norm": 2.248739004135132,
+      "learning_rate": 2.0363797692990243e-05,
+      "loss": 0.5856,
+      "step": 975
+    },
+    {
+      "epoch": 1.1976047904191618,
+      "grad_norm": 2.193042516708374,
+      "learning_rate": 2.003105590062112e-05,
+      "loss": 0.5803,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2275449101796407,
+      "grad_norm": 1.9028452634811401,
+      "learning_rate": 1.9698314108252e-05,
+      "loss": 0.5721,
+      "step": 1025
+    },
+    {
+      "epoch": 1.2574850299401197,
+      "grad_norm": 2.1685469150543213,
+      "learning_rate": 1.9365572315882875e-05,
+      "loss": 0.5854,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2874251497005988,
+      "grad_norm": 1.913358449935913,
+      "learning_rate": 1.9032830523513755e-05,
+      "loss": 0.5739,
+      "step": 1075
+    },
+    {
+      "epoch": 1.3173652694610778,
+      "grad_norm": 2.101280450820923,
+      "learning_rate": 1.870008873114463e-05,
+      "loss": 0.5757,
+      "step": 1100
+    },
+    {
+      "epoch": 1.347305389221557,
+      "grad_norm": 1.8946870565414429,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 0.5652,
+      "step": 1125
+    },
+    {
+      "epoch": 1.377245508982036,
+      "grad_norm": 1.9929522275924683,
+      "learning_rate": 1.8034605146406388e-05,
+      "loss": 0.5717,
+      "step": 1150
+    },
+    {
+      "epoch": 1.407185628742515,
+      "grad_norm": 1.9487309455871582,
+      "learning_rate": 1.7701863354037267e-05,
+      "loss": 0.5633,
+      "step": 1175
+    },
+    {
+      "epoch": 1.437125748502994,
+      "grad_norm": 2.029733896255493,
+      "learning_rate": 1.7369121561668147e-05,
+      "loss": 0.566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.467065868263473,
+      "grad_norm": 2.0024046897888184,
+      "learning_rate": 1.7036379769299024e-05,
+      "loss": 0.5707,
+      "step": 1225
+    },
+    {
+      "epoch": 1.4970059880239521,
+      "grad_norm": 2.075111150741577,
+      "learning_rate": 1.6703637976929903e-05,
+      "loss": 0.5707,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5269461077844313,
+      "grad_norm": 2.050729751586914,
+      "learning_rate": 1.637089618456078e-05,
+      "loss": 0.5769,
+      "step": 1275
+    },
+    {
+      "epoch": 1.55688622754491,
+      "grad_norm": 1.8547407388687134,
+      "learning_rate": 1.603815439219166e-05,
+      "loss": 0.5821,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5868263473053892,
+      "grad_norm": 1.965280294418335,
+      "learning_rate": 1.5705412599822536e-05,
+      "loss": 0.5611,
+      "step": 1325
+    },
+    {
+      "epoch": 1.6167664670658684,
+      "grad_norm": 2.0741708278656006,
+      "learning_rate": 1.5372670807453416e-05,
+      "loss": 0.5786,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6467065868263473,
+      "grad_norm": 1.8129183053970337,
+      "learning_rate": 1.5039929015084294e-05,
+      "loss": 0.5716,
+      "step": 1375
+    },
+    {
+      "epoch": 1.6766467065868262,
+      "grad_norm": 1.8226035833358765,
+      "learning_rate": 1.4707187222715174e-05,
+      "loss": 0.5739,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7065868263473054,
+      "grad_norm": 2.042602062225342,
+      "learning_rate": 1.4374445430346052e-05,
+      "loss": 0.5664,
+      "step": 1425
+    },
+    {
+      "epoch": 1.7365269461077846,
+      "grad_norm": 1.8656301498413086,
+      "learning_rate": 1.404170363797693e-05,
+      "loss": 0.5656,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7664670658682635,
+      "grad_norm": 1.8996257781982422,
+      "learning_rate": 1.3708961845607808e-05,
+      "loss": 0.5791,
+      "step": 1475
+    },
+    {
+      "epoch": 1.7964071856287425,
+      "grad_norm": 1.7967721223831177,
+      "learning_rate": 1.3376220053238688e-05,
+      "loss": 0.5551,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8263473053892216,
+      "grad_norm": 1.7963491678237915,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.5686,
+      "step": 1525
+    },
+    {
+      "epoch": 1.8562874251497006,
+      "grad_norm": 2.0248234272003174,
+      "learning_rate": 1.2710736468500444e-05,
+      "loss": 0.5518,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8862275449101795,
+      "grad_norm": 1.84022855758667,
+      "learning_rate": 1.2377994676131322e-05,
+      "loss": 0.5521,
+      "step": 1575
+    },
+    {
+      "epoch": 1.9161676646706587,
+      "grad_norm": 2.160158157348633,
+      "learning_rate": 1.20452528837622e-05,
+      "loss": 0.5525,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9461077844311379,
+      "grad_norm": 1.9900472164154053,
+      "learning_rate": 1.171251109139308e-05,
+      "loss": 0.5574,
+      "step": 1625
+    },
+    {
+      "epoch": 1.9760479041916168,
+      "grad_norm": 1.9723472595214844,
+      "learning_rate": 1.1379769299023958e-05,
+      "loss": 0.5785,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0059880239520957,
+      "grad_norm": 2.0681216716766357,
+      "learning_rate": 1.1047027506654836e-05,
+      "loss": 0.5553,
+      "step": 1675
+    },
+    {
+      "epoch": 2.035928143712575,
+      "grad_norm": 2.1955301761627197,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.5657,
+      "step": 1700
+    },
+    {
+      "epoch": 2.065868263473054,
+      "grad_norm": 2.136237859725952,
+      "learning_rate": 1.0381543921916594e-05,
+      "loss": 0.5415,
+      "step": 1725
+    },
+    {
+      "epoch": 2.095808383233533,
+      "grad_norm": 2.073801279067993,
+      "learning_rate": 1.0048802129547472e-05,
+      "loss": 0.5335,
+      "step": 1750
+    },
+    {
+      "epoch": 2.125748502994012,
+      "grad_norm": 2.140120506286621,
+      "learning_rate": 9.71606033717835e-06,
+      "loss": 0.5623,
+      "step": 1775
+    },
+    {
+      "epoch": 2.155688622754491,
+      "grad_norm": 2.025439977645874,
+      "learning_rate": 9.383318544809228e-06,
+      "loss": 0.5427,
+      "step": 1800
+    },
+    {
+      "epoch": 2.18562874251497,
+      "grad_norm": 2.0939273834228516,
+      "learning_rate": 9.050576752440106e-06,
+      "loss": 0.5542,
+      "step": 1825
+    },
+    {
+      "epoch": 2.215568862275449,
+      "grad_norm": 2.1501097679138184,
+      "learning_rate": 8.717834960070984e-06,
+      "loss": 0.5559,
+      "step": 1850
+    },
+    {
+      "epoch": 2.245508982035928,
+      "grad_norm": 2.0543227195739746,
+      "learning_rate": 8.385093167701862e-06,
+      "loss": 0.542,
+      "step": 1875
+    },
+    {
+      "epoch": 2.2754491017964074,
+      "grad_norm": 1.9872088432312012,
+      "learning_rate": 8.052351375332742e-06,
+      "loss": 0.5421,
+      "step": 1900
+    },
+    {
+      "epoch": 2.305389221556886,
+      "grad_norm": 2.2318456172943115,
+      "learning_rate": 7.71960958296362e-06,
+      "loss": 0.5575,
+      "step": 1925
+    },
+    {
+      "epoch": 2.3353293413173652,
+      "grad_norm": 2.1007492542266846,
+      "learning_rate": 7.386867790594499e-06,
+      "loss": 0.5585,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3652694610778444,
+      "grad_norm": 2.1291024684906006,
+      "learning_rate": 7.054125998225377e-06,
+      "loss": 0.5606,
+      "step": 1975
+    },
+    {
+      "epoch": 2.3952095808383236,
+      "grad_norm": 2.263563394546509,
+      "learning_rate": 6.721384205856256e-06,
+      "loss": 0.5585,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4251497005988023,
+      "grad_norm": 2.1472697257995605,
+      "learning_rate": 6.388642413487134e-06,
+      "loss": 0.5377,
+      "step": 2025
+    },
+    {
+      "epoch": 2.4550898203592815,
+      "grad_norm": 2.075249195098877,
+      "learning_rate": 6.055900621118012e-06,
+      "loss": 0.5413,
+      "step": 2050
+    },
+    {
+      "epoch": 2.4850299401197606,
+      "grad_norm": 2.2139124870300293,
+      "learning_rate": 5.7231588287488905e-06,
+      "loss": 0.5468,
+      "step": 2075
+    },
+    {
+      "epoch": 2.5149700598802394,
+      "grad_norm": 2.2758278846740723,
+      "learning_rate": 5.390417036379769e-06,
+      "loss": 0.5619,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5449101796407185,
+      "grad_norm": 2.212797164916992,
+      "learning_rate": 5.057675244010648e-06,
+      "loss": 0.544,
+      "step": 2125
+    },
+    {
+      "epoch": 2.5748502994011977,
+      "grad_norm": 2.078122615814209,
+      "learning_rate": 4.724933451641526e-06,
+      "loss": 0.5263,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6047904191616764,
+      "grad_norm": 3.65337872505188,
+      "learning_rate": 4.3921916592724045e-06,
+      "loss": 0.551,
+      "step": 2175
+    },
+    {
+      "epoch": 2.6347305389221556,
+      "grad_norm": 2.2584967613220215,
+      "learning_rate": 4.059449866903283e-06,
+      "loss": 0.5445,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6646706586826348,
+      "grad_norm": 2.1008565425872803,
+      "learning_rate": 3.7267080745341615e-06,
+      "loss": 0.5451,
+      "step": 2225
+    },
+    {
+      "epoch": 2.694610778443114,
+      "grad_norm": 2.453005790710449,
+      "learning_rate": 3.3939662821650396e-06,
+      "loss": 0.5573,
+      "step": 2250
+    },
+    {
+      "epoch": 2.724550898203593,
+      "grad_norm": 2.185372829437256,
+      "learning_rate": 3.0612244897959185e-06,
+      "loss": 0.5399,
+      "step": 2275
+    },
+    {
+      "epoch": 2.754491017964072,
+      "grad_norm": 2.158651351928711,
+      "learning_rate": 2.7284826974267966e-06,
+      "loss": 0.5482,
+      "step": 2300
+    },
+    {
+      "epoch": 2.784431137724551,
+      "grad_norm": 2.1352522373199463,
+      "learning_rate": 2.3957409050576756e-06,
+      "loss": 0.5453,
+      "step": 2325
+    },
+    {
+      "epoch": 2.81437125748503,
+      "grad_norm": 2.063870906829834,
+      "learning_rate": 2.0629991126885537e-06,
+      "loss": 0.5452,
+      "step": 2350
+    },
+    {
+      "epoch": 2.844311377245509,
+      "grad_norm": 2.159843921661377,
+      "learning_rate": 1.7302573203194322e-06,
+      "loss": 0.5374,
+      "step": 2375
+    },
+    {
+      "epoch": 2.874251497005988,
+      "grad_norm": 2.268249273300171,
+      "learning_rate": 1.3975155279503105e-06,
+      "loss": 0.5608,
+      "step": 2400
+    },
+    {
+      "epoch": 2.904191616766467,
+      "grad_norm": 1.9996740818023682,
+      "learning_rate": 1.078083407275954e-06,
+      "loss": 0.5355,
+      "step": 2425
+    },
+    {
+      "epoch": 2.934131736526946,
+      "grad_norm": 2.2193121910095215,
+      "learning_rate": 7.453416149068323e-07,
+      "loss": 0.5425,
+      "step": 2450
+    },
+    {
+      "epoch": 2.964071856287425,
+      "grad_norm": 2.098750591278076,
+      "learning_rate": 4.125998225377108e-07,
+      "loss": 0.5527,
+      "step": 2475
+    },
+    {
+      "epoch": 2.9940119760479043,
+      "grad_norm": 2.186506986618042,
+      "learning_rate": 7.985803016858918e-08,
+      "loss": 0.5567,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.1895496620572672e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2505/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c995bfd8427f21941734d17bbad8e059d4181f57f2c383263cca07c48f5d28be
+size 4984

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": "</s>",
+  "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 +1,43 @@
+{
+  "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": "{{ 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": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c995bfd8427f21941734d17bbad8e059d4181f57f2c383263cca07c48f5d28be
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "mistralai/Mistral-7B-Instruct-v0.2",
+    "project_name": "autotrain-abc",
+    "data_path": "autotrain-abc/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "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": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "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": null,
+    "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": "hkufyp2024/finetuned-model",
+    "username": null
+}