Training in progress, step 94

README.md

@@ -1,178 +1,202 @@
 ---
-library_name: peft
-license: mit
 base_model: microsoft/Phi-3.5-mini-instruct
-tags:
-- axolotl
-- generated_from_trainer
-datasets:
-- collinear-ai/R1-Distill-SFT-numina-math-ensemble_8_train
-model-index:
-- name: sn_math_curator_on_ensemble_8
-  results: []
+library_name: peft
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Model Card for Model ID
 
-[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
-<details><summary>See axolotl config</summary>
+<!-- Provide a quick summary of what the model is/does. -->
 
-axolotl version: `0.7.0`
-```yaml
-strict: false
-base_model: microsoft/Phi-3.5-mini-instruct
-tokenizer_config: microsoft/Phi-3.5-mini-instruct
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-# Output configuration
-hub_model_id: collinear-ai/sn_math_curator_on_ensemble_8
-dataset_prepared_path: data/sn_math_curator_on_ensemble_8
-output_dir: model/sn_math_curator_on_ensemble_8
-
-# Format the dataset into the right instruction format.
-chat_template: phi_3
-datasets:
-  - path: collinear-ai/R1-Distill-SFT-numina-math-ensemble_8_train
-    split: train
-    type: chat_template
-    chat_template: phi_3
-    field_messages: train_conv
-    message_field_role: role
-    message_field_content: content
-train_on_inputs: false #FALSE
-
-val_set_size: 0.05
-# Data packing
-sequence_len: 8192
-eval_sample_packing: false
-sample_packing: false
-pad_to_sequence_len: true
-group_by_length: false
-
-# Lora config
-adapter: qlora
-lora_model_dir:
-load_in_8bit: false
-load_in_4bit: true
-lora_r: 128
-lora_alpha: 64
-lora_dropout: 0.2
-lora_target_linear: true
-lora_fan_in_fan_out:
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-lora_modules_to_save: 
-  - embed_tokens
-  - lm_head
-
-
-# Logging config
-wandb_project: sn-curators-downstream
-wandb_entity: nazneen
-wandb_name: curator_math_sn_ensemble_8_phi
-
-# Trainer config
-gradient_accumulation_steps: 2
-micro_batch_size: 10
-num_epochs: 1
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 5e-6
-
-
-bfloat16: true
-bf16: true
-fp16:
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 10
-xformers_attention:
-flash_attention: true
-save_safetensors: true
-
-
-
-warmup_steps: 50
-evals_per_epoch: 3
-eval_table_size: 3
-eval_max_new_tokens: 2048
-saves_per_epoch: 40
-debug:
-deepspeed:
-weight_decay: 0.02
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "<|endoftext|>"
-  unk_token: "<unk>"
-  pad_token: "<|endoftext|>"
-```
-
-</details><br>
-
-# sn_math_curator_on_ensemble_8
-
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the collinear-ai/R1-Distill-SFT-numina-math-ensemble_8_train dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3350
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 10
-- eval_batch_size: 10
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 160
-- total_eval_batch_size: 80
-- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 50
-- num_epochs: 1.0
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.0003 | 1    | 0.7150          |
-| 0.3405        | 0.3333 | 1301 | 0.3525          |
-| 0.323         | 0.6667 | 2602 | 0.3369          |
-| 0.3195        | 1.0    | 3903 | 0.3350          |
 
 
+## 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 0.14.0
-- Transformers 4.48.3
-- Pytorch 2.5.1
-- Datasets 3.2.0
-- Tokenizers 0.21.0
+- PEFT 0.13.2

adapter_config.json

@@ -3,8 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
   "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -13,7 +11,6 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
-  "lora_bias": false,
   "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -27,14 +24,14 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
-    "gate_up_proj",
-    "q_proj",
     "k_proj",
+    "q_proj",
+    "up_proj",
     "gate_proj",
+    "gate_up_proj",
+    "down_proj",
     "qkv_proj",
-    "up_proj",
-    "down_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448cbd6f2f17e919f2db329e1057735f45b1a940f43d6ef1f1612ff404b87f6d
+oid sha256:de8aa442a99b0055b4df079a8b63f00106d6b41ea53899a9ff33f521cbe8c740
 size 1199344216

config.json

@@ -148,7 +148,7 @@
   "sliding_window": 262144,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.46.1",
   "use_cache": false,
   "vocab_size": 32064
 }

tokenizer_config.json

@@ -120,7 +120,6 @@
   "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32dff8fdfeab5bc1699c7053ff5e994f81e14f638113c69dfd7bbb21ac554a22
-size 6968
+oid sha256:c673fd12296a7622b7a46d1a7aab69688b4fcb6f2a03cf9f35d55593ca9a04aa
+size 6712