Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acb90f80eed66b37d3bd60e5d60a8949412997aff422bc0712f1ae749727d10
+size 27308941

checkpoint-4623/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-beta
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-4623/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-4623/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acb90f80eed66b37d3bd60e5d60a8949412997aff422bc0712f1ae749727d10
+size 27308941

checkpoint-4623/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f751dc07e193744710e977b420e1c08ca7251d6ee62da9aef284491074d0e29a
+size 54633541

checkpoint-4623/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b26094385e073cafbb96e26990c6c7bc8f26e8867d037f0f2242b76947b36d7
+size 15607

checkpoint-4623/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfdf436e52eb2d358acf5092415d4031502e8c9926edff2758046634b8d8e76
+size 15607

checkpoint-4623/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392b80d916941cf8939eb2d6a9e9ef6e501f472c4ca8674e1782d56eebd6df7b
+size 627

checkpoint-4623/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-4623/tokenizer.model

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

checkpoint-4623/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-4623/trainer_state.json

@@ -0,0 +1,1123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2496759559300066,
+  "eval_steps": 500,
+  "global_step": 4623,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.699784017278618e-07,
+      "loss": 1.0969,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.399568034557235e-07,
+      "loss": 1.0905,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.099352051835855e-07,
+      "loss": 1.0853,
+      "step": 75
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.079913606911447e-06,
+      "loss": 1.0712,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.349892008639309e-06,
+      "loss": 1.0577,
+      "step": 125
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.619870410367171e-06,
+      "loss": 1.0345,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8898488120950326e-06,
+      "loss": 1.0094,
+      "step": 175
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.159827213822894e-06,
+      "loss": 0.9685,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.429805615550756e-06,
+      "loss": 0.9441,
+      "step": 225
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.699784017278618e-06,
+      "loss": 0.9111,
+      "step": 250
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.96976241900648e-06,
+      "loss": 0.8798,
+      "step": 275
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.239740820734342e-06,
+      "loss": 0.8499,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.5097192224622035e-06,
+      "loss": 0.8209,
+      "step": 325
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.779697624190065e-06,
+      "loss": 0.7895,
+      "step": 350
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.049676025917927e-06,
+      "loss": 0.7687,
+      "step": 375
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.319654427645788e-06,
+      "loss": 0.7366,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.58963282937365e-06,
+      "loss": 0.717,
+      "step": 425
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.859611231101512e-06,
+      "loss": 0.6993,
+      "step": 450
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.129589632829374e-06,
+      "loss": 0.6828,
+      "step": 475
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.399568034557236e-06,
+      "loss": 0.6755,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.669546436285097e-06,
+      "loss": 0.6622,
+      "step": 525
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.93952483801296e-06,
+      "loss": 0.6537,
+      "step": 550
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.209503239740822e-06,
+      "loss": 0.6405,
+      "step": 575
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.479481641468684e-06,
+      "loss": 0.638,
+      "step": 600
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.749460043196545e-06,
+      "loss": 0.6309,
+      "step": 625
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.019438444924407e-06,
+      "loss": 0.6236,
+      "step": 650
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.289416846652268e-06,
+      "loss": 0.6211,
+      "step": 675
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.55939524838013e-06,
+      "loss": 0.6163,
+      "step": 700
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.829373650107991e-06,
+      "loss": 0.6114,
+      "step": 725
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.099352051835854e-06,
+      "loss": 0.6075,
+      "step": 750
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.369330453563716e-06,
+      "loss": 0.6041,
+      "step": 775
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.639308855291577e-06,
+      "loss": 0.6029,
+      "step": 800
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.90928725701944e-06,
+      "loss": 0.5985,
+      "step": 825
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.1792656587473e-06,
+      "loss": 0.5971,
+      "step": 850
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.449244060475162e-06,
+      "loss": 0.5889,
+      "step": 875
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.719222462203023e-06,
+      "loss": 0.5939,
+      "step": 900
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989200863930886e-06,
+      "loss": 0.5902,
+      "step": 925
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.0259179265658747e-05,
+      "loss": 0.5884,
+      "step": 950
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.0529157667386608e-05,
+      "loss": 0.5854,
+      "step": 975
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.0799136069114471e-05,
+      "loss": 0.5849,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1069114470842333e-05,
+      "loss": 0.5839,
+      "step": 1025
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1339092872570194e-05,
+      "loss": 0.5832,
+      "step": 1050
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1609071274298057e-05,
+      "loss": 0.5784,
+      "step": 1075
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.187904967602592e-05,
+      "loss": 0.5753,
+      "step": 1100
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.2149028077753782e-05,
+      "loss": 0.5746,
+      "step": 1125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.2419006479481644e-05,
+      "loss": 0.5724,
+      "step": 1150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.2688984881209505e-05,
+      "loss": 0.5659,
+      "step": 1175
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.2958963282937368e-05,
+      "loss": 0.5716,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.3228941684665229e-05,
+      "loss": 0.5691,
+      "step": 1225
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.349892008639309e-05,
+      "loss": 0.5641,
+      "step": 1250
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.3768898488120951e-05,
+      "loss": 0.5669,
+      "step": 1275
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4038876889848814e-05,
+      "loss": 0.5654,
+      "step": 1300
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.4308855291576675e-05,
+      "loss": 0.5651,
+      "step": 1325
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.4578833693304537e-05,
+      "loss": 0.5619,
+      "step": 1350
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.48488120950324e-05,
+      "loss": 0.5621,
+      "step": 1375
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.511879049676026e-05,
+      "loss": 0.5603,
+      "step": 1400
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5388768898488122e-05,
+      "loss": 0.5597,
+      "step": 1425
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5658747300215983e-05,
+      "loss": 0.564,
+      "step": 1450
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.5928725701943844e-05,
+      "loss": 0.5581,
+      "step": 1475
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.619870410367171e-05,
+      "loss": 0.5554,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.646868250539957e-05,
+      "loss": 0.5507,
+      "step": 1525
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.673866090712743e-05,
+      "loss": 0.5533,
+      "step": 1550
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.7008639308855292e-05,
+      "loss": 0.5498,
+      "step": 1575
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.7278617710583154e-05,
+      "loss": 0.5526,
+      "step": 1600
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.7548596112311015e-05,
+      "loss": 0.5503,
+      "step": 1625
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.781857451403888e-05,
+      "loss": 0.5503,
+      "step": 1650
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.808855291576674e-05,
+      "loss": 0.5485,
+      "step": 1675
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.83585313174946e-05,
+      "loss": 0.5502,
+      "step": 1700
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.8628509719222463e-05,
+      "loss": 0.5446,
+      "step": 1725
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.8898488120950324e-05,
+      "loss": 0.5375,
+      "step": 1750
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9168466522678185e-05,
+      "loss": 0.5407,
+      "step": 1775
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9438444924406046e-05,
+      "loss": 0.5453,
+      "step": 1800
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.970842332613391e-05,
+      "loss": 0.5447,
+      "step": 1825
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.9978401727861772e-05,
+      "loss": 0.5421,
+      "step": 1850
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.997239558329333e-05,
+      "loss": 0.5425,
+      "step": 1875
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.9942390782525205e-05,
+      "loss": 0.5418,
+      "step": 1900
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.9912385981757083e-05,
+      "loss": 0.5429,
+      "step": 1925
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.9882381180988958e-05,
+      "loss": 0.5388,
+      "step": 1950
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.9852376380220836e-05,
+      "loss": 0.5402,
+      "step": 1975
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.9822371579452714e-05,
+      "loss": 0.5348,
+      "step": 2000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9792366778684592e-05,
+      "loss": 0.5385,
+      "step": 2025
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.976236197791647e-05,
+      "loss": 0.5415,
+      "step": 2050
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.9732357177148345e-05,
+      "loss": 0.5346,
+      "step": 2075
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.9702352376380223e-05,
+      "loss": 0.5333,
+      "step": 2100
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.9672347575612098e-05,
+      "loss": 0.5339,
+      "step": 2125
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.9642342774843976e-05,
+      "loss": 0.5325,
+      "step": 2150
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.9612337974075854e-05,
+      "loss": 0.5346,
+      "step": 2175
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.958233317330773e-05,
+      "loss": 0.527,
+      "step": 2200
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.9552328372539607e-05,
+      "loss": 0.5343,
+      "step": 2225
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.9522323571771486e-05,
+      "loss": 0.5282,
+      "step": 2250
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.9492318771003364e-05,
+      "loss": 0.527,
+      "step": 2275
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.946231397023524e-05,
+      "loss": 0.5287,
+      "step": 2300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.9432309169467117e-05,
+      "loss": 0.5287,
+      "step": 2325
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.9402304368698995e-05,
+      "loss": 0.5296,
+      "step": 2350
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.937229956793087e-05,
+      "loss": 0.5265,
+      "step": 2375
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9342294767162748e-05,
+      "loss": 0.5225,
+      "step": 2400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9312289966394622e-05,
+      "loss": 0.5254,
+      "step": 2425
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.92822851656265e-05,
+      "loss": 0.5273,
+      "step": 2450
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.925228036485838e-05,
+      "loss": 0.5248,
+      "step": 2475
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.9222275564090257e-05,
+      "loss": 0.5255,
+      "step": 2500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.9192270763322135e-05,
+      "loss": 0.5252,
+      "step": 2525
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.916226596255401e-05,
+      "loss": 0.5255,
+      "step": 2550
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9132261161785888e-05,
+      "loss": 0.5273,
+      "step": 2575
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9102256361017763e-05,
+      "loss": 0.522,
+      "step": 2600
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.907225156024964e-05,
+      "loss": 0.5244,
+      "step": 2625
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.904224675948152e-05,
+      "loss": 0.5195,
+      "step": 2650
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9012241958713397e-05,
+      "loss": 0.5204,
+      "step": 2675
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.8982237157945272e-05,
+      "loss": 0.5153,
+      "step": 2700
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.895223235717715e-05,
+      "loss": 0.5173,
+      "step": 2725
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8922227556409028e-05,
+      "loss": 0.5196,
+      "step": 2750
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8892222755640903e-05,
+      "loss": 0.5153,
+      "step": 2775
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.886221795487278e-05,
+      "loss": 0.518,
+      "step": 2800
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.883221315410466e-05,
+      "loss": 0.5162,
+      "step": 2825
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.8802208353336534e-05,
+      "loss": 0.5177,
+      "step": 2850
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.8772203552568412e-05,
+      "loss": 0.5187,
+      "step": 2875
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.874219875180029e-05,
+      "loss": 0.5164,
+      "step": 2900
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.871219395103217e-05,
+      "loss": 0.5142,
+      "step": 2925
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.8682189150264043e-05,
+      "loss": 0.5183,
+      "step": 2950
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.865218434949592e-05,
+      "loss": 0.5146,
+      "step": 2975
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.86221795487278e-05,
+      "loss": 0.5187,
+      "step": 3000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8592174747959674e-05,
+      "loss": 0.5147,
+      "step": 3025
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8562169947191553e-05,
+      "loss": 0.5127,
+      "step": 3050
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.8532165146423427e-05,
+      "loss": 0.5089,
+      "step": 3075
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8502160345655305e-05,
+      "loss": 0.5117,
+      "step": 3100
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.8472155544887184e-05,
+      "loss": 0.5101,
+      "step": 3125
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.8442150744119062e-05,
+      "loss": 0.5113,
+      "step": 3150
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.841214594335094e-05,
+      "loss": 0.5109,
+      "step": 3175
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.8382141142582815e-05,
+      "loss": 0.5108,
+      "step": 3200
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.8352136341814693e-05,
+      "loss": 0.5094,
+      "step": 3225
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.8322131541046568e-05,
+      "loss": 0.5118,
+      "step": 3250
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.8292126740278446e-05,
+      "loss": 0.5035,
+      "step": 3275
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.826212193951032e-05,
+      "loss": 0.5029,
+      "step": 3300
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.82321171387422e-05,
+      "loss": 0.5042,
+      "step": 3325
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.8202112337974077e-05,
+      "loss": 0.5079,
+      "step": 3350
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.8172107537205955e-05,
+      "loss": 0.506,
+      "step": 3375
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.8142102736437833e-05,
+      "loss": 0.5114,
+      "step": 3400
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.8112097935669708e-05,
+      "loss": 0.5023,
+      "step": 3425
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.8082093134901586e-05,
+      "loss": 0.5104,
+      "step": 3450
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.805208833413346e-05,
+      "loss": 0.5091,
+      "step": 3475
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.802208353336534e-05,
+      "loss": 0.504,
+      "step": 3500
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.7992078732597217e-05,
+      "loss": 0.5054,
+      "step": 3525
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.7962073931829095e-05,
+      "loss": 0.5013,
+      "step": 3550
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.7932069131060973e-05,
+      "loss": 0.5077,
+      "step": 3575
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.7902064330292848e-05,
+      "loss": 0.509,
+      "step": 3600
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.7872059529524726e-05,
+      "loss": 0.5014,
+      "step": 3625
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.78420547287566e-05,
+      "loss": 0.5001,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.7813250120019206e-05,
+      "loss": 0.5027,
+      "step": 3675
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.778324531925108e-05,
+      "loss": 0.501,
+      "step": 3700
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.7754440710513683e-05,
+      "loss": 0.4997,
+      "step": 3725
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.772443590974556e-05,
+      "loss": 0.5,
+      "step": 3750
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.7694431108977435e-05,
+      "loss": 0.5038,
+      "step": 3775
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.7664426308209314e-05,
+      "loss": 0.4962,
+      "step": 3800
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.7634421507441192e-05,
+      "loss": 0.4995,
+      "step": 3825
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.760441670667307e-05,
+      "loss": 0.5,
+      "step": 3850
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.7574411905904948e-05,
+      "loss": 0.4991,
+      "step": 3875
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.7544407105136823e-05,
+      "loss": 0.4985,
+      "step": 3900
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.75144023043687e-05,
+      "loss": 0.4981,
+      "step": 3925
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.7484397503600576e-05,
+      "loss": 0.4935,
+      "step": 3950
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.7454392702832454e-05,
+      "loss": 0.4998,
+      "step": 3975
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.7424387902064332e-05,
+      "loss": 0.4972,
+      "step": 4000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.7394383101296207e-05,
+      "loss": 0.4972,
+      "step": 4025
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.7364378300528085e-05,
+      "loss": 0.4981,
+      "step": 4050
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.7334373499759963e-05,
+      "loss": 0.4989,
+      "step": 4075
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.730436869899184e-05,
+      "loss": 0.4961,
+      "step": 4100
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.727436389822372e-05,
+      "loss": 0.5008,
+      "step": 4125
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.7244359097455594e-05,
+      "loss": 0.4949,
+      "step": 4150
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.7214354296687472e-05,
+      "loss": 0.4978,
+      "step": 4175
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.7184349495919347e-05,
+      "loss": 0.4931,
+      "step": 4200
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.7154344695151225e-05,
+      "loss": 0.491,
+      "step": 4225
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.7124339894383103e-05,
+      "loss": 0.4905,
+      "step": 4250
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.7094335093614978e-05,
+      "loss": 0.4935,
+      "step": 4275
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.7064330292846856e-05,
+      "loss": 0.494,
+      "step": 4300
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.7034325492078735e-05,
+      "loss": 0.4882,
+      "step": 4325
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.7004320691310613e-05,
+      "loss": 0.4906,
+      "step": 4350
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.6974315890542487e-05,
+      "loss": 0.4927,
+      "step": 4375
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.6944311089774366e-05,
+      "loss": 0.4929,
+      "step": 4400
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.691430628900624e-05,
+      "loss": 0.4928,
+      "step": 4425
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.688430148823812e-05,
+      "loss": 0.4907,
+      "step": 4450
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6854296687469997e-05,
+      "loss": 0.4909,
+      "step": 4475
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6824291886701875e-05,
+      "loss": 0.492,
+      "step": 4500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.6794287085933753e-05,
+      "loss": 0.4925,
+      "step": 4525
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.6764282285165628e-05,
+      "loss": 0.4917,
+      "step": 4550
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.6734277484397506e-05,
+      "loss": 0.4899,
+      "step": 4575
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.670427268362938e-05,
+      "loss": 0.4876,
+      "step": 4600
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 18516,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.2933954243483664e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4623/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1151021f0e8518636c69e7c7248693889a52566dadb9dd3d8b447dd682d10126
+size 4027

runs/Oct26_14-53-04_hf-dgx-01/events.out.tfevents.1698324784.hf-dgx-01.1235962.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4dcbd061c38b9fbfb99e40f97447a61fb300c014f42567e56b92cb3a540283
+size 4491

runs/Oct26_14-56-01_hf-dgx-01/events.out.tfevents.1698324962.hf-dgx-01.1237057.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301c5d8dfff60c67fe49a49eb4562c4ed682014d4a8be7cae15fe04696297536
+size 4491

runs/Oct26_14-57-23_hf-dgx-01/events.out.tfevents.1698325043.hf-dgx-01.1240095.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874635f20341d124b05859849cbf7397008603ac0b3caabdc329183bd543c242
+size 33718

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": "</s>",
+    "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 +1,46 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1151021f0e8518636c69e7c7248693889a52566dadb9dd3d8b447dd682d10126
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "HuggingFaceH4/zephyr-7b-beta", "data_path": "rishiraj/guanaco-style-metamath", "project_name": "zephyr-beta-math", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 2e-05, "epochs": 3, "batch_size": 32, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": 25, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": null, "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "merge_adapter": false, "username": "abhishek", "use_flash_attention_2": false, "log": "tensorboard", "disable_gradient_checkpointing": false}