Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-01-06-18-43-03
+  results: []
+---
+
+<!-- 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. -->
+
+# train_2025-01-06-18-43-03
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the followir_recreate_simple_1 dataset.
+
+## 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: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 6
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 768
+- total_eval_batch_size: 48
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 8.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "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:c3452f38812359447e0d32e15efdb355466977d2cdbc193121c250a243179498
+size 27297032

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.918918918918919,
+    "total_flos": 3.566531758742569e+17,
+    "train_loss": 3.64303145557642,
+    "train_runtime": 8658.9704,
+    "train_samples_per_second": 1.641,
+    "train_steps_per_second": 0.002
+}

checkpoint-16/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-16/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-16/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3452f38812359447e0d32e15efdb355466977d2cdbc193121c250a243179498
+size 27297032

checkpoint-16/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52853ecc782dd7e77e09e4aa79bbdac365278dc76553033c9661d9b808670d6d
+size 54740730

checkpoint-16/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1180467ff90400659d73c4b7b0c6b5065fc1d8edf701c0358a6884bf81f5f3dd
+size 15472

checkpoint-16/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb4e3a848fda1abd4517b949c19a948b12c07d0e87e669de837b8946091d94d
+size 15472

checkpoint-16/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16fa81fbffb188e2d2e3338833393e1416669cd9a2238137e94d67347e69f83
+size 15472

checkpoint-16/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f6f5ca133b91c415db604ea507fb5157ec109d5382fa4dfccf1ba0229aa22a
+size 15472

checkpoint-16/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6fddb505b25b459a0094977038bdf573e2e88076ceb8d0e39d2ebb2afc99ca
+size 15472

checkpoint-16/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ce92e6b41f41e5f8bba6d861a7558ece511e068ca3836a0b8f85e7925f33bf
+size 15472

checkpoint-16/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147983c66b34a4e8e431d3d2209eb0ab4e49a59aeab3ce686b3a1528349ca8bb
+size 1064

checkpoint-16/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-16/tokenizer.model

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

checkpoint-16/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-16/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.918918918918919,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 66.02604675292969,
+      "learning_rate": 2.3333553495294033e-05,
+      "loss": 9.0853,
+      "step": 5
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 22.67275619506836,
+      "learning_rate": 9.259748514523654e-06,
+      "loss": 2.016,
+      "step": 10
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 9.565340995788574,
+      "learning_rate": 2.8822079395154357e-07,
+      "loss": 0.5055,
+      "step": 15
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 16,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.566531758742569e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8768f7b05bd5b5c3b878446fc395e0602be5cc33e44a070e937be401bdc364
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,72 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-Instruct-v0.2
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: mistral
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 4
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- followir_recreate_simple_1
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 32
+train.learning_rate: 3e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: q_proj,v_proj,o_proj,k_proj
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '8.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.swanlab_api_key: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,274 @@
+[WARNING|2025-01-06 18:44:37] logging.py:162 >> `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json
+
+[INFO|2025-01-06 18:44:37] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.model
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.json
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/special_tokens_map.json
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer_config.json
+
+[INFO|2025-01-06 18:44:37] parser.py:359 >> Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|2025-01-06 18:44:37] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json
+
+[INFO|2025-01-06 18:44:37] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.model
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.json
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/special_tokens_map.json
+
+[INFO|2025-01-06 18:44:37] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer_config.json
+
+[INFO|2025-01-06 18:44:37] logging.py:157 >> Add pad token: </s>
+
+[INFO|2025-01-06 18:44:37] logging.py:157 >> Loading dataset followir_recreate_simple_1.json...
+
+[INFO|2025-01-06 18:44:39] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json
+
+[INFO|2025-01-06 18:44:39] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|2025-01-06 18:44:39] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/model.safetensors.index.json
+
+[INFO|2025-01-06 18:44:39] modeling_utils.py:1670 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-01-06 18:44:39] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|2025-01-06 18:44:45] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2025-01-06 18:44:45] modeling_utils.py:4808 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-Instruct-v0.2.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
+
+[INFO|2025-01-06 18:44:45] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/generation_config.json
+
+[INFO|2025-01-06 18:44:45] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|2025-01-06 18:44:45] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-01-06 18:44:45] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-01-06 18:44:45] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-01-06 18:44:45] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-01-06 18:44:45] logging.py:157 >> trainable params: 6,815,744 || all params: 7,248,547,840 || trainable%: 0.0940
+
+[INFO|2025-01-06 18:44:45] trainer.py:698 >> Using auto half precision backend
+
+[INFO|2025-01-06 18:44:47] trainer.py:2313 >> ***** Running training *****
+
+[INFO|2025-01-06 18:44:47] trainer.py:2314 >>   Num examples = 1,776
+
+[INFO|2025-01-06 18:44:47] trainer.py:2315 >>   Num Epochs = 8
+
+[INFO|2025-01-06 18:44:47] trainer.py:2316 >>   Instantaneous batch size per device = 4
+
+[INFO|2025-01-06 18:44:47] trainer.py:2319 >>   Total train batch size (w. parallel, distributed & accumulation) = 768
+
+[INFO|2025-01-06 18:44:47] trainer.py:2320 >>   Gradient Accumulation steps = 32
+
+[INFO|2025-01-06 18:44:47] trainer.py:2321 >>   Total optimization steps = 16
+
+[INFO|2025-01-06 18:44:47] trainer.py:2322 >>   Number of trainable parameters = 6,815,744
+
+[INFO|2025-01-06 19:29:53] logging.py:157 >> {'loss': 9.0853, 'learning_rate': 2.3334e-05, 'epoch': 2.16}
+
+[INFO|2025-01-06 20:14:35] logging.py:157 >> {'loss': 2.0160, 'learning_rate': 9.2597e-06, 'epoch': 4.32}
+
+[INFO|2025-01-06 20:59:53] logging.py:157 >> {'loss': 0.5055, 'learning_rate': 2.8822e-07, 'epoch': 6.49}
+
+[INFO|2025-01-06 21:09:05] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03/checkpoint-16
+
+[INFO|2025-01-06 21:09:05] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json
+
+[INFO|2025-01-06 21:09:05] configuration_utils.py:746 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|2025-01-06 21:09:05] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03/checkpoint-16/tokenizer_config.json
+
+[INFO|2025-01-06 21:09:05] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03/checkpoint-16/special_tokens_map.json
+
+[INFO|2025-01-06 21:09:06] trainer.py:2584 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-01-06 21:09:06] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03
+
+[INFO|2025-01-06 21:09:06] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json
+
+[INFO|2025-01-06 21:09:06] configuration_utils.py:746 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|2025-01-06 21:09:06] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03/tokenizer_config.json
+
+[INFO|2025-01-06 21:09:06] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03/special_tokens_map.json
+
+[WARNING|2025-01-06 21:09:06] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-01-06 21:09:06] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-01-06 21:09:06] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.918918918918919,
+    "total_flos": 3.566531758742569e+17,
+    "train_loss": 3.64303145557642,
+    "train_runtime": 8658.9704,
+    "train_samples_per_second": 1.641,
+    "train_steps_per_second": 0.002
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 5, "total_steps": 16, "loss": 9.0853, "lr": 2.3333553495294033e-05, "epoch": 2.1621621621621623, "percentage": 31.25, "elapsed_time": "0:45:05", "remaining_time": "1:39:13"}
+{"current_steps": 10, "total_steps": 16, "loss": 2.016, "lr": 9.259748514523654e-06, "epoch": 4.324324324324325, "percentage": 62.5, "elapsed_time": "1:29:47", "remaining_time": "0:53:52"}
+{"current_steps": 15, "total_steps": 16, "loss": 0.5055, "lr": 2.8822079395154357e-07, "epoch": 6.486486486486487, "percentage": 93.75, "elapsed_time": "2:15:06", "remaining_time": "0:09:00"}
+{"current_steps": 16, "total_steps": 16, "epoch": 6.918918918918919, "percentage": 100.0, "elapsed_time": "2:24:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.918918918918919,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 66.02604675292969,
+      "learning_rate": 2.3333553495294033e-05,
+      "loss": 9.0853,
+      "step": 5
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 22.67275619506836,
+      "learning_rate": 9.259748514523654e-06,
+      "loss": 2.016,
+      "step": 10
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 9.565340995788574,
+      "learning_rate": 2.8822079395154357e-07,
+      "loss": 0.5055,
+      "step": 15
+    },
+    {
+      "epoch": 6.918918918918919,
+      "step": 16,
+      "total_flos": 3.566531758742569e+17,
+      "train_loss": 3.64303145557642,
+      "train_runtime": 8658.9704,
+      "train_samples_per_second": 1.641,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 16,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.566531758742569e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8768f7b05bd5b5c3b878446fc395e0602be5cc33e44a070e937be401bdc364
+size 5432

training_args.yaml

@@ -0,0 +1,32 @@
+bf16: true
+cutoff_len: 2048
+dataset: followir_recreate_simple_1
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 32
+learning_rate: 3.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: q_proj,v_proj,o_proj,k_proj
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.2
+num_train_epochs: 8.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-06-18-43-03
+packing: false
+per_device_train_batch_size: 4
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: mistral
+trust_remote_code: true
+warmup_steps: 0