Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+model-index:
+- name: part_2
+  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. -->
+
+# part_2
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the en_train_part_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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_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 sha256:0ed8fab70b70f10e9d905fb30957c87132060ed3e8583bb0fa4b92db313cd706
+size 83945296

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.978540772532189,
+    "num_input_tokens_seen": 924488,
+    "total_flos": 3.957609622319923e+16,
+    "train_loss": 0.10672961984728944,
+    "train_runtime": 329.4461,
+    "train_samples_per_second": 8.46,
+    "train_steps_per_second": 1.056
+}

checkpoint-348/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+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-348/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-348/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed8fab70b70f10e9d905fb30957c87132060ed3e8583bb0fa4b92db313cd706
+size 83945296

checkpoint-348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cf5b6c8c8f6c9a445f196e0ff65733363b71a8037bd52eeda5680e861188ea
+size 168149074

checkpoint-348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-348/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0282d00eed9fe2ab27061734672e5936a63ea9e59fda708608ae904fc55aa57
+size 1064

checkpoint-348/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-348/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-348/trainer_state.json

@@ -0,0 +1,305 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.978540772532189,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08583690987124463,
+      "grad_norm": 5.144778728485107,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.8269,
+      "num_input_tokens_seen": 25888,
+      "step": 10
+    },
+    {
+      "epoch": 0.17167381974248927,
+      "grad_norm": 4.5363545417785645,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.1558,
+      "num_input_tokens_seen": 53280,
+      "step": 20
+    },
+    {
+      "epoch": 0.2575107296137339,
+      "grad_norm": 3.198505401611328,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.1655,
+      "num_input_tokens_seen": 79904,
+      "step": 30
+    },
+    {
+      "epoch": 0.34334763948497854,
+      "grad_norm": 3.3528692722320557,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.1686,
+      "num_input_tokens_seen": 106464,
+      "step": 40
+    },
+    {
+      "epoch": 0.4291845493562232,
+      "grad_norm": 3.4683921337127686,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.128,
+      "num_input_tokens_seen": 132672,
+      "step": 50
+    },
+    {
+      "epoch": 0.5150214592274678,
+      "grad_norm": 6.693175792694092,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.1581,
+      "num_input_tokens_seen": 161312,
+      "step": 60
+    },
+    {
+      "epoch": 0.6008583690987125,
+      "grad_norm": 1.5621659755706787,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.1106,
+      "num_input_tokens_seen": 187680,
+      "step": 70
+    },
+    {
+      "epoch": 0.6866952789699571,
+      "grad_norm": 1.8518391847610474,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.1401,
+      "num_input_tokens_seen": 214400,
+      "step": 80
+    },
+    {
+      "epoch": 0.7725321888412017,
+      "grad_norm": 2.3987910747528076,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.1282,
+      "num_input_tokens_seen": 240480,
+      "step": 90
+    },
+    {
+      "epoch": 0.8583690987124464,
+      "grad_norm": 3.301926612854004,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0936,
+      "num_input_tokens_seen": 267360,
+      "step": 100
+    },
+    {
+      "epoch": 0.944206008583691,
+      "grad_norm": 7.198034286499023,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.1569,
+      "num_input_tokens_seen": 294720,
+      "step": 110
+    },
+    {
+      "epoch": 1.0257510729613735,
+      "grad_norm": 4.04252290725708,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0904,
+      "num_input_tokens_seen": 319184,
+      "step": 120
+    },
+    {
+      "epoch": 1.111587982832618,
+      "grad_norm": 5.508508682250977,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 345680,
+      "step": 130
+    },
+    {
+      "epoch": 1.1974248927038627,
+      "grad_norm": 1.6325355768203735,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.058,
+      "num_input_tokens_seen": 371824,
+      "step": 140
+    },
+    {
+      "epoch": 1.2832618025751072,
+      "grad_norm": 1.3446625471115112,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0818,
+      "num_input_tokens_seen": 398480,
+      "step": 150
+    },
+    {
+      "epoch": 1.3690987124463518,
+      "grad_norm": 2.4645965099334717,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0715,
+      "num_input_tokens_seen": 424656,
+      "step": 160
+    },
+    {
+      "epoch": 1.4549356223175964,
+      "grad_norm": 2.872417688369751,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 451088,
+      "step": 170
+    },
+    {
+      "epoch": 1.5407725321888412,
+      "grad_norm": 2.7769811153411865,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0713,
+      "num_input_tokens_seen": 478320,
+      "step": 180
+    },
+    {
+      "epoch": 1.6266094420600858,
+      "grad_norm": 3.642953634262085,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 505328,
+      "step": 190
+    },
+    {
+      "epoch": 1.7124463519313304,
+      "grad_norm": 4.070372104644775,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0728,
+      "num_input_tokens_seen": 531920,
+      "step": 200
+    },
+    {
+      "epoch": 1.7982832618025753,
+      "grad_norm": 6.3663740158081055,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.1002,
+      "num_input_tokens_seen": 560496,
+      "step": 210
+    },
+    {
+      "epoch": 1.8841201716738198,
+      "grad_norm": 2.0767858028411865,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0976,
+      "num_input_tokens_seen": 586384,
+      "step": 220
+    },
+    {
+      "epoch": 1.9699570815450644,
+      "grad_norm": 4.728202819824219,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0801,
+      "num_input_tokens_seen": 612496,
+      "step": 230
+    },
+    {
+      "epoch": 2.051502145922747,
+      "grad_norm": 0.5934279561042786,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0533,
+      "num_input_tokens_seen": 637448,
+      "step": 240
+    },
+    {
+      "epoch": 2.1373390557939915,
+      "grad_norm": 2.772380828857422,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.059,
+      "num_input_tokens_seen": 663528,
+      "step": 250
+    },
+    {
+      "epoch": 2.223175965665236,
+      "grad_norm": 1.757418155670166,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 689384,
+      "step": 260
+    },
+    {
+      "epoch": 2.3090128755364807,
+      "grad_norm": 2.6222424507141113,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0404,
+      "num_input_tokens_seen": 715560,
+      "step": 270
+    },
+    {
+      "epoch": 2.3948497854077253,
+      "grad_norm": 2.2118000984191895,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.059,
+      "num_input_tokens_seen": 741960,
+      "step": 280
+    },
+    {
+      "epoch": 2.48068669527897,
+      "grad_norm": 4.022334098815918,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0429,
+      "num_input_tokens_seen": 768808,
+      "step": 290
+    },
+    {
+      "epoch": 2.5665236051502145,
+      "grad_norm": 0.4254824221134186,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0341,
+      "num_input_tokens_seen": 795176,
+      "step": 300
+    },
+    {
+      "epoch": 2.652360515021459,
+      "grad_norm": 2.2265915870666504,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0349,
+      "num_input_tokens_seen": 821864,
+      "step": 310
+    },
+    {
+      "epoch": 2.7381974248927037,
+      "grad_norm": 1.5945826768875122,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0375,
+      "num_input_tokens_seen": 849800,
+      "step": 320
+    },
+    {
+      "epoch": 2.8240343347639483,
+      "grad_norm": 3.1935954093933105,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0184,
+      "num_input_tokens_seen": 876616,
+      "step": 330
+    },
+    {
+      "epoch": 2.909871244635193,
+      "grad_norm": 2.1143760681152344,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0583,
+      "num_input_tokens_seen": 903048,
+      "step": 340
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 924488,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.957609622319923e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-348/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3cb86ceab1094d776b1ec437de8d7cd5b248aebd6997bd76c45f08cd0a4571
+size 5688

llamaboard_config.yaml

@@ -0,0 +1,78 @@
+top.booster: unsloth
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-Instruct-v0.3
+top.quantization_bit: '4'
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: alpaca
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+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:
+- en_train_part_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: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 2
+train.learning_rate: 3e-5
+train.logging_steps: 10
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '929'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+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:
+- none
+train.resize_vocab: false
+train.reward_model: []
+train.save_steps: 1000
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+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_apollo: false
+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 +1,503 @@
+[INFO|2025-04-07 18:40:30] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-04-07 18:40:30] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file tokenizer.model from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2025-04-07 18:40:31] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-07 18:40:32] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-04-07 18:40:32] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file tokenizer.model from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2025-04-07 18:40:32] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-07 18:40:32] logging.py:157 >> Add pad token: </s>
+
+[INFO|2025-04-07 18:40:32] logging.py:157 >> Loading dataset en_train_part_1.json...
+
+[INFO|2025-04-07 18:40:34] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-04-07 18:40:34] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:34] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.
+
+[INFO|2025-04-07 18:40:37] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-04-07 18:40:37] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:38] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--aws/snapshots/66e4c14a24a0b445779c922eef992a4af0694a88/config.json
+
+[INFO|2025-04-07 18:40:38] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--repeat/snapshots/7c48478c02f84ed89f149b0815cc0216ee831fb0/config.json
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--vram-48/snapshots/3aea312d98ea327daeb5dbf7374b1d7cf8c65bc0/config.json
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--1/snapshots/7ec782b7604cd9ea0781c23a4270f031650f5617/config.json
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-04-07 18:40:39] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:40:51] modeling_utils.py:3982 >> loading weights file model.safetensors from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/model.safetensors
+
+[INFO|2025-04-07 18:40:51] modeling_utils.py:1633 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-04-07 18:40:51] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 770
+}
+
+
+[INFO|2025-04-07 18:40:52] modeling_utils.py:4970 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2025-04-07 18:40:52] modeling_utils.py:4978 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at unsloth/mistral-7b-instruct-v0.3-bnb-4bit.
+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|2025-04-07 18:40:53] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/generation_config.json
+
+[INFO|2025-04-07 18:40:53] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 770
+}
+
+
+[INFO|2025-04-07 18:40:57] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-04-07 18:40:57] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-04-07 18:40:57] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-04-07 18:40:57] logging.py:157 >> Found linear modules: v_proj,down_proj,k_proj,o_proj,up_proj,q_proj,gate_proj
+
+[WARNING|2025-04-07 18:40:59] logging.py:329 >> Unsloth 2025.3.19 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.
+
+[INFO|2025-04-07 18:41:00] logging.py:157 >> trainable params: 20,971,520 || all params: 7,268,995,072 || trainable%: 0.2885
+
+[INFO|2025-04-07 18:41:00] trainer.py:746 >> Using auto half precision backend
+
+[WARNING|2025-04-07 18:41:01] <string>:168 >> ==((====))==  Unsloth - 2x faster free finetuning | Num GPUs used = 1
+   \\   /|    Num examples = 929 | Num Epochs = 3 | Total steps = 348
+O^O/ \_/ \    Batch size per device = 4 | Gradient accumulation steps = 2
+\        /    Data Parallel GPUs = 1 | Total batch size (4 x 2 x 1) = 8
+ "-____-"     Trainable parameters = 20,971,520/7,000,000,000 (0.30% trained)
+
+[INFO|2025-04-07 18:41:23] logging.py:157 >> {'loss': 0.8269, 'learning_rate': 2.9939e-05, 'epoch': 0.09, 'throughput': 1205.00}
+
+[INFO|2025-04-07 18:41:32] logging.py:157 >> {'loss': 0.1558, 'learning_rate': 2.9756e-05, 'epoch': 0.17, 'throughput': 1741.54}
+
+[INFO|2025-04-07 18:41:41] logging.py:157 >> {'loss': 0.1655, 'learning_rate': 2.9453e-05, 'epoch': 0.26, 'throughput': 2021.00}
+
+[INFO|2025-04-07 18:41:50] logging.py:157 >> {'loss': 0.1686, 'learning_rate': 2.9033e-05, 'epoch': 0.34, 'throughput': 2196.79}
+
+[INFO|2025-04-07 18:41:59] logging.py:157 >> {'loss': 0.1280, 'learning_rate': 2.8498e-05, 'epoch': 0.43, 'throughput': 2312.55}
+
+[INFO|2025-04-07 18:42:08] logging.py:157 >> {'loss': 0.1581, 'learning_rate': 2.7853e-05, 'epoch': 0.52, 'throughput': 2412.29}
+
+[INFO|2025-04-07 18:42:17] logging.py:157 >> {'loss': 0.1106, 'learning_rate': 2.7103e-05, 'epoch': 0.60, 'throughput': 2474.02}
+
+[INFO|2025-04-07 18:42:26] logging.py:157 >> {'loss': 0.1401, 'learning_rate': 2.6255e-05, 'epoch': 0.69, 'throughput': 2522.25}
+
+[INFO|2025-04-07 18:42:35] logging.py:157 >> {'loss': 0.1282, 'learning_rate': 2.5315e-05, 'epoch': 0.77, 'throughput': 2559.46}
+
+[INFO|2025-04-07 18:42:45] logging.py:157 >> {'loss': 0.0936, 'learning_rate': 2.4292e-05, 'epoch': 0.86, 'throughput': 2591.37}
+
+[INFO|2025-04-07 18:42:54] logging.py:157 >> {'loss': 0.1569, 'learning_rate': 2.3192e-05, 'epoch': 0.94, 'throughput': 2617.95}
+
+[INFO|2025-04-07 18:43:03] logging.py:157 >> {'loss': 0.0904, 'learning_rate': 2.2026e-05, 'epoch': 1.03, 'throughput': 2622.68}
+
+[INFO|2025-04-07 18:43:12] logging.py:157 >> {'loss': 0.0730, 'learning_rate': 2.0803e-05, 'epoch': 1.11, 'throughput': 2640.79}
+
+[INFO|2025-04-07 18:43:21] logging.py:157 >> {'loss': 0.0580, 'learning_rate': 1.9532e-05, 'epoch': 1.20, 'throughput': 2656.87}
+
+[INFO|2025-04-07 18:43:30] logging.py:157 >> {'loss': 0.0818, 'learning_rate': 1.8225e-05, 'epoch': 1.28, 'throughput': 2673.66}
+
+[INFO|2025-04-07 18:43:39] logging.py:157 >> {'loss': 0.0715, 'learning_rate': 1.6891e-05, 'epoch': 1.37, 'throughput': 2687.40}
+
+[INFO|2025-04-07 18:43:48] logging.py:157 >> {'loss': 0.0691, 'learning_rate': 1.5542e-05, 'epoch': 1.45, 'throughput': 2700.42}
+
+[INFO|2025-04-07 18:43:58] logging.py:157 >> {'loss': 0.0713, 'learning_rate': 1.4188e-05, 'epoch': 1.54, 'throughput': 2713.99}
+
+[INFO|2025-04-07 18:44:07] logging.py:157 >> {'loss': 0.0985, 'learning_rate': 1.2841e-05, 'epoch': 1.63, 'throughput': 2726.48}
+
+[INFO|2025-04-07 18:44:16] logging.py:157 >> {'loss': 0.0728, 'learning_rate': 1.1511e-05, 'epoch': 1.71, 'throughput': 2736.15}
+
+[INFO|2025-04-07 18:44:25] logging.py:157 >> {'loss': 0.1002, 'learning_rate': 1.0210e-05, 'epoch': 1.80, 'throughput': 2748.97}
+
+[INFO|2025-04-07 18:44:34] logging.py:157 >> {'loss': 0.0976, 'learning_rate': 8.9485e-06, 'epoch': 1.88, 'throughput': 2756.85}
+
+[INFO|2025-04-07 18:44:43] logging.py:157 >> {'loss': 0.0801, 'learning_rate': 7.7358e-06, 'epoch': 1.97, 'throughput': 2764.62}
+
+[INFO|2025-04-07 18:44:52] logging.py:157 >> {'loss': 0.0533, 'learning_rate': 6.5822e-06, 'epoch': 2.05, 'throughput': 2769.81}
+
+[INFO|2025-04-07 18:45:00] logging.py:157 >> {'loss': 0.0590, 'learning_rate': 5.4972e-06, 'epoch': 2.14, 'throughput': 2775.77}
+
+[INFO|2025-04-07 18:45:09] logging.py:157 >> {'loss': 0.0505, 'learning_rate': 4.4896e-06, 'epoch': 2.22, 'throughput': 2781.09}
+
+[INFO|2025-04-07 18:45:18] logging.py:157 >> {'loss': 0.0404, 'learning_rate': 3.5676e-06, 'epoch': 2.31, 'throughput': 2786.55}
+
+[INFO|2025-04-07 18:45:27] logging.py:157 >> {'loss': 0.0590, 'learning_rate': 2.7387e-06, 'epoch': 2.39, 'throughput': 2792.12}
+
+[INFO|2025-04-07 18:45:36] logging.py:157 >> {'loss': 0.0429, 'learning_rate': 2.0096e-06, 'epoch': 2.48, 'throughput': 2797.48}
+
+[INFO|2025-04-07 18:45:45] logging.py:157 >> {'loss': 0.0341, 'learning_rate': 1.3864e-06, 'epoch': 2.57, 'throughput': 2802.16}
+
+[INFO|2025-04-07 18:45:54] logging.py:157 >> {'loss': 0.0349, 'learning_rate': 8.7399e-07, 'epoch': 2.65, 'throughput': 2806.55}
+
+[INFO|2025-04-07 18:46:04] logging.py:157 >> {'loss': 0.0375, 'learning_rate': 4.7666e-07, 'epoch': 2.74, 'throughput': 2812.12}
+
+[INFO|2025-04-07 18:46:13] logging.py:157 >> {'loss': 0.0184, 'learning_rate': 1.9760e-07, 'epoch': 2.82, 'throughput': 2816.04}
+
+[INFO|2025-04-07 18:46:22] logging.py:157 >> {'loss': 0.0583, 'learning_rate': 3.9102e-08, 'epoch': 2.91, 'throughput': 2819.51}
+
+[INFO|2025-04-07 18:46:29] trainer.py:3942 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/part_2/checkpoint-348
+
+[INFO|2025-04-07 18:46:30] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-04-07 18:46:30] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-04-07 18:46:31] <string>:415 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-04-07 18:46:31] trainer.py:3942 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/part_2
+
+[INFO|2025-04-07 18:46:31] configuration_utils.py:699 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-04-07 18:46:31] configuration_utils.py:771 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[WARNING|2025-04-07 18:46:31] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-04-07 18:46:31] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-04-07 18:46:31] 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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.978540772532189,
+    "num_input_tokens_seen": 924488,
+    "total_flos": 3.957609622319923e+16,
+    "train_loss": 0.10672961984728944,
+    "train_runtime": 329.4461,
+    "train_samples_per_second": 8.46,
+    "train_steps_per_second": 1.056
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 10, "total_steps": 348, "loss": 0.8269, "lr": 2.9938918800982563e-05, "epoch": 0.08583690987124463, "percentage": 2.87, "elapsed_time": "0:00:21", "remaining_time": "0:12:06", "throughput": 1205.0, "total_tokens": 25888}
+{"current_steps": 20, "total_steps": 348, "loss": 0.1558, "lr": 2.975617265898004e-05, "epoch": 0.17167381974248927, "percentage": 5.75, "elapsed_time": "0:00:30", "remaining_time": "0:08:21", "throughput": 1741.54, "total_tokens": 53280}
+{"current_steps": 30, "total_steps": 348, "loss": 0.1655, "lr": 2.9453249887788343e-05, "epoch": 0.2575107296137339, "percentage": 8.62, "elapsed_time": "0:00:39", "remaining_time": "0:06:59", "throughput": 2021.0, "total_tokens": 79904}
+{"current_steps": 40, "total_steps": 348, "loss": 0.1686, "lr": 2.9032617538884018e-05, "epoch": 0.34334763948497854, "percentage": 11.49, "elapsed_time": "0:00:48", "remaining_time": "0:06:13", "throughput": 2196.79, "total_tokens": 106464}
+{"current_steps": 50, "total_steps": 348, "loss": 0.128, "lr": 2.84977013093626e-05, "epoch": 0.4291845493562232, "percentage": 14.37, "elapsed_time": "0:00:57", "remaining_time": "0:05:41", "throughput": 2312.55, "total_tokens": 132672}
+{"current_steps": 60, "total_steps": 348, "loss": 0.1581, "lr": 2.7852857642513838e-05, "epoch": 0.5150214592274678, "percentage": 17.24, "elapsed_time": "0:01:06", "remaining_time": "0:05:20", "throughput": 2412.29, "total_tokens": 161312}
+{"current_steps": 70, "total_steps": 348, "loss": 0.1106, "lr": 2.7103338248251055e-05, "epoch": 0.6008583690987125, "percentage": 20.11, "elapsed_time": "0:01:15", "remaining_time": "0:05:01", "throughput": 2474.02, "total_tokens": 187680}
+{"current_steps": 80, "total_steps": 348, "loss": 0.1401, "lr": 2.6255247332346036e-05, "epoch": 0.6866952789699571, "percentage": 22.99, "elapsed_time": "0:01:25", "remaining_time": "0:04:44", "throughput": 2522.25, "total_tokens": 214400}
+{"current_steps": 90, "total_steps": 348, "loss": 0.1282, "lr": 2.531549188280135e-05, "epoch": 0.7725321888412017, "percentage": 25.86, "elapsed_time": "0:01:33", "remaining_time": "0:04:29", "throughput": 2559.46, "total_tokens": 240480}
+{"current_steps": 100, "total_steps": 348, "loss": 0.0936, "lr": 2.4291725418235848e-05, "epoch": 0.8583690987124464, "percentage": 28.74, "elapsed_time": "0:01:43", "remaining_time": "0:04:15", "throughput": 2591.37, "total_tokens": 267360}
+{"current_steps": 110, "total_steps": 348, "loss": 0.1569, "lr": 2.3192285656405456e-05, "epoch": 0.944206008583691, "percentage": 31.61, "elapsed_time": "0:01:52", "remaining_time": "0:04:03", "throughput": 2617.95, "total_tokens": 294720}
+{"current_steps": 120, "total_steps": 348, "loss": 0.0904, "lr": 2.2026126610496852e-05, "epoch": 1.0257510729613735, "percentage": 34.48, "elapsed_time": "0:02:01", "remaining_time": "0:03:51", "throughput": 2622.68, "total_tokens": 319184}
+{"current_steps": 130, "total_steps": 348, "loss": 0.073, "lr": 2.0802745666212592e-05, "epoch": 1.111587982832618, "percentage": 37.36, "elapsed_time": "0:02:10", "remaining_time": "0:03:39", "throughput": 2640.79, "total_tokens": 345680}
+{"current_steps": 140, "total_steps": 348, "loss": 0.058, "lr": 1.953210623354359e-05, "epoch": 1.1974248927038627, "percentage": 40.23, "elapsed_time": "0:02:19", "remaining_time": "0:03:27", "throughput": 2656.87, "total_tokens": 371824}
+{"current_steps": 150, "total_steps": 348, "loss": 0.0818, "lr": 1.8224556603165363e-05, "epoch": 1.2832618025751072, "percentage": 43.1, "elapsed_time": "0:02:29", "remaining_time": "0:03:16", "throughput": 2673.66, "total_tokens": 398480}
+{"current_steps": 160, "total_steps": 348, "loss": 0.0715, "lr": 1.689074566830434e-05, "epoch": 1.3690987124463518, "percentage": 45.98, "elapsed_time": "0:02:38", "remaining_time": "0:03:05", "throughput": 2687.4, "total_tokens": 424656}
+{"current_steps": 170, "total_steps": 348, "loss": 0.0691, "lr": 1.5541536198449044e-05, "epoch": 1.4549356223175964, "percentage": 48.85, "elapsed_time": "0:02:47", "remaining_time": "0:02:54", "throughput": 2700.42, "total_tokens": 451088}
+{"current_steps": 180, "total_steps": 348, "loss": 0.0713, "lr": 1.4187916371218739e-05, "epoch": 1.5407725321888412, "percentage": 51.72, "elapsed_time": "0:02:56", "remaining_time": "0:02:44", "throughput": 2713.99, "total_tokens": 478320}
+{"current_steps": 190, "total_steps": 348, "loss": 0.0985, "lr": 1.2840910282888211e-05, "epoch": 1.6266094420600858, "percentage": 54.6, "elapsed_time": "0:03:05", "remaining_time": "0:02:34", "throughput": 2726.48, "total_tokens": 505328}
+{"current_steps": 200, "total_steps": 348, "loss": 0.0728, "lr": 1.1511488166385349e-05, "epoch": 1.7124463519313304, "percentage": 57.47, "elapsed_time": "0:03:14", "remaining_time": "0:02:23", "throughput": 2736.15, "total_tokens": 531920}
+{"current_steps": 210, "total_steps": 348, "loss": 0.1002, "lr": 1.0210477047960303e-05, "epoch": 1.7982832618025753, "percentage": 60.34, "elapsed_time": "0:03:23", "remaining_time": "0:02:13", "throughput": 2748.97, "total_tokens": 560496}
+{"current_steps": 220, "total_steps": 348, "loss": 0.0976, "lr": 8.948472570152874e-06, "epoch": 1.8841201716738198, "percentage": 63.22, "elapsed_time": "0:03:32", "remaining_time": "0:02:03", "throughput": 2756.85, "total_tokens": 586384}
+{"current_steps": 230, "total_steps": 348, "loss": 0.0801, "lr": 7.735752699185711e-06, "epoch": 1.9699570815450644, "percentage": 66.09, "elapsed_time": "0:03:41", "remaining_time": "0:01:53", "throughput": 2764.62, "total_tokens": 612496}
+{"current_steps": 240, "total_steps": 348, "loss": 0.0533, "lr": 6.582194019564266e-06, "epoch": 2.051502145922747, "percentage": 68.97, "elapsed_time": "0:03:50", "remaining_time": "0:01:43", "throughput": 2769.81, "total_tokens": 637448}
+{"current_steps": 250, "total_steps": 348, "loss": 0.059, "lr": 5.497191297593647e-06, "epoch": 2.1373390557939915, "percentage": 71.84, "elapsed_time": "0:03:59", "remaining_time": "0:01:33", "throughput": 2775.77, "total_tokens": 663528}
+{"current_steps": 260, "total_steps": 348, "loss": 0.0505, "lr": 4.4895809688998655e-06, "epoch": 2.223175965665236, "percentage": 74.71, "elapsed_time": "0:04:07", "remaining_time": "0:01:23", "throughput": 2781.09, "total_tokens": 689384}
+{"current_steps": 270, "total_steps": 348, "loss": 0.0404, "lr": 3.567569173085455e-06, "epoch": 2.3090128755364807, "percentage": 77.59, "elapsed_time": "0:04:16", "remaining_time": "0:01:14", "throughput": 2786.55, "total_tokens": 715560}
+{"current_steps": 280, "total_steps": 348, "loss": 0.059, "lr": 2.7386649216166233e-06, "epoch": 2.3948497854077253, "percentage": 80.46, "elapsed_time": "0:04:25", "remaining_time": "0:01:04", "throughput": 2792.12, "total_tokens": 741960}
+{"current_steps": 290, "total_steps": 348, "loss": 0.0429, "lr": 2.0096189432334194e-06, "epoch": 2.48068669527897, "percentage": 83.33, "elapsed_time": "0:04:34", "remaining_time": "0:00:54", "throughput": 2797.48, "total_tokens": 768808}
+{"current_steps": 300, "total_steps": 348, "loss": 0.0341, "lr": 1.3863687049356465e-06, "epoch": 2.5665236051502145, "percentage": 86.21, "elapsed_time": "0:04:43", "remaining_time": "0:00:45", "throughput": 2802.16, "total_tokens": 795176}
+{"current_steps": 310, "total_steps": 348, "loss": 0.0349, "lr": 8.7399005630238e-07, "epoch": 2.652360515021459, "percentage": 89.08, "elapsed_time": "0:04:52", "remaining_time": "0:00:35", "throughput": 2806.55, "total_tokens": 821864}
+{"current_steps": 320, "total_steps": 348, "loss": 0.0375, "lr": 4.766558909615504e-07, "epoch": 2.7381974248927037, "percentage": 91.95, "elapsed_time": "0:05:02", "remaining_time": "0:00:26", "throughput": 2812.12, "total_tokens": 849800}
+{"current_steps": 330, "total_steps": 348, "loss": 0.0184, "lr": 1.9760216187710788e-07, "epoch": 2.8240343347639483, "percentage": 94.83, "elapsed_time": "0:05:11", "remaining_time": "0:00:16", "throughput": 2816.04, "total_tokens": 876616}
+{"current_steps": 340, "total_steps": 348, "loss": 0.0583, "lr": 3.910152723075322e-08, "epoch": 2.909871244635193, "percentage": 97.7, "elapsed_time": "0:05:20", "remaining_time": "0:00:07", "throughput": 2819.51, "total_tokens": 903048}
+{"current_steps": 348, "total_steps": 348, "epoch": 2.978540772532189, "percentage": 100.0, "elapsed_time": "0:05:29", "remaining_time": "0:00:00", "throughput": 2806.23, "total_tokens": 924488}

trainer_state.json

@@ -0,0 +1,315 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.978540772532189,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08583690987124463,
+      "grad_norm": 5.144778728485107,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.8269,
+      "num_input_tokens_seen": 25888,
+      "step": 10
+    },
+    {
+      "epoch": 0.17167381974248927,
+      "grad_norm": 4.5363545417785645,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.1558,
+      "num_input_tokens_seen": 53280,
+      "step": 20
+    },
+    {
+      "epoch": 0.2575107296137339,
+      "grad_norm": 3.198505401611328,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.1655,
+      "num_input_tokens_seen": 79904,
+      "step": 30
+    },
+    {
+      "epoch": 0.34334763948497854,
+      "grad_norm": 3.3528692722320557,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.1686,
+      "num_input_tokens_seen": 106464,
+      "step": 40
+    },
+    {
+      "epoch": 0.4291845493562232,
+      "grad_norm": 3.4683921337127686,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.128,
+      "num_input_tokens_seen": 132672,
+      "step": 50
+    },
+    {
+      "epoch": 0.5150214592274678,
+      "grad_norm": 6.693175792694092,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.1581,
+      "num_input_tokens_seen": 161312,
+      "step": 60
+    },
+    {
+      "epoch": 0.6008583690987125,
+      "grad_norm": 1.5621659755706787,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.1106,
+      "num_input_tokens_seen": 187680,
+      "step": 70
+    },
+    {
+      "epoch": 0.6866952789699571,
+      "grad_norm": 1.8518391847610474,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.1401,
+      "num_input_tokens_seen": 214400,
+      "step": 80
+    },
+    {
+      "epoch": 0.7725321888412017,
+      "grad_norm": 2.3987910747528076,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.1282,
+      "num_input_tokens_seen": 240480,
+      "step": 90
+    },
+    {
+      "epoch": 0.8583690987124464,
+      "grad_norm": 3.301926612854004,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0936,
+      "num_input_tokens_seen": 267360,
+      "step": 100
+    },
+    {
+      "epoch": 0.944206008583691,
+      "grad_norm": 7.198034286499023,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.1569,
+      "num_input_tokens_seen": 294720,
+      "step": 110
+    },
+    {
+      "epoch": 1.0257510729613735,
+      "grad_norm": 4.04252290725708,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0904,
+      "num_input_tokens_seen": 319184,
+      "step": 120
+    },
+    {
+      "epoch": 1.111587982832618,
+      "grad_norm": 5.508508682250977,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 345680,
+      "step": 130
+    },
+    {
+      "epoch": 1.1974248927038627,
+      "grad_norm": 1.6325355768203735,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.058,
+      "num_input_tokens_seen": 371824,
+      "step": 140
+    },
+    {
+      "epoch": 1.2832618025751072,
+      "grad_norm": 1.3446625471115112,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0818,
+      "num_input_tokens_seen": 398480,
+      "step": 150
+    },
+    {
+      "epoch": 1.3690987124463518,
+      "grad_norm": 2.4645965099334717,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0715,
+      "num_input_tokens_seen": 424656,
+      "step": 160
+    },
+    {
+      "epoch": 1.4549356223175964,
+      "grad_norm": 2.872417688369751,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 451088,
+      "step": 170
+    },
+    {
+      "epoch": 1.5407725321888412,
+      "grad_norm": 2.7769811153411865,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0713,
+      "num_input_tokens_seen": 478320,
+      "step": 180
+    },
+    {
+      "epoch": 1.6266094420600858,
+      "grad_norm": 3.642953634262085,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 505328,
+      "step": 190
+    },
+    {
+      "epoch": 1.7124463519313304,
+      "grad_norm": 4.070372104644775,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0728,
+      "num_input_tokens_seen": 531920,
+      "step": 200
+    },
+    {
+      "epoch": 1.7982832618025753,
+      "grad_norm": 6.3663740158081055,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.1002,
+      "num_input_tokens_seen": 560496,
+      "step": 210
+    },
+    {
+      "epoch": 1.8841201716738198,
+      "grad_norm": 2.0767858028411865,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0976,
+      "num_input_tokens_seen": 586384,
+      "step": 220
+    },
+    {
+      "epoch": 1.9699570815450644,
+      "grad_norm": 4.728202819824219,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0801,
+      "num_input_tokens_seen": 612496,
+      "step": 230
+    },
+    {
+      "epoch": 2.051502145922747,
+      "grad_norm": 0.5934279561042786,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0533,
+      "num_input_tokens_seen": 637448,
+      "step": 240
+    },
+    {
+      "epoch": 2.1373390557939915,
+      "grad_norm": 2.772380828857422,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.059,
+      "num_input_tokens_seen": 663528,
+      "step": 250
+    },
+    {
+      "epoch": 2.223175965665236,
+      "grad_norm": 1.757418155670166,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 689384,
+      "step": 260
+    },
+    {
+      "epoch": 2.3090128755364807,
+      "grad_norm": 2.6222424507141113,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0404,
+      "num_input_tokens_seen": 715560,
+      "step": 270
+    },
+    {
+      "epoch": 2.3948497854077253,
+      "grad_norm": 2.2118000984191895,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.059,
+      "num_input_tokens_seen": 741960,
+      "step": 280
+    },
+    {
+      "epoch": 2.48068669527897,
+      "grad_norm": 4.022334098815918,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0429,
+      "num_input_tokens_seen": 768808,
+      "step": 290
+    },
+    {
+      "epoch": 2.5665236051502145,
+      "grad_norm": 0.4254824221134186,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0341,
+      "num_input_tokens_seen": 795176,
+      "step": 300
+    },
+    {
+      "epoch": 2.652360515021459,
+      "grad_norm": 2.2265915870666504,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0349,
+      "num_input_tokens_seen": 821864,
+      "step": 310
+    },
+    {
+      "epoch": 2.7381974248927037,
+      "grad_norm": 1.5945826768875122,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0375,
+      "num_input_tokens_seen": 849800,
+      "step": 320
+    },
+    {
+      "epoch": 2.8240343347639483,
+      "grad_norm": 3.1935954093933105,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0184,
+      "num_input_tokens_seen": 876616,
+      "step": 330
+    },
+    {
+      "epoch": 2.909871244635193,
+      "grad_norm": 2.1143760681152344,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0583,
+      "num_input_tokens_seen": 903048,
+      "step": 340
+    },
+    {
+      "epoch": 2.978540772532189,
+      "num_input_tokens_seen": 924488,
+      "step": 348,
+      "total_flos": 3.957609622319923e+16,
+      "train_loss": 0.10672961984728944,
+      "train_runtime": 329.4461,
+      "train_samples_per_second": 8.46,
+      "train_steps_per_second": 1.056
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 924488,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.957609622319923e+16,
+  "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 sha256:0b3cb86ceab1094d776b1ec437de8d7cd5b248aebd6997bd76c45f08cd0a4571
+size 5688

training_args.yaml

@@ -0,0 +1,37 @@
+bf16: true
+cutoff_len: 2048
+dataset: en_train_part_1
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+double_quantization: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 2
+include_num_input_tokens_seen: true
+learning_rate: 3.0e-05
+logging_steps: 10
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 929
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.3
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-Instruct-v0.3/lora/part_2
+packing: false
+per_device_train_batch_size: 4
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+quantization_method: bitsandbytes
+report_to: none
+save_steps: 1000
+stage: sft
+template: alpaca
+trust_remote_code: true
+use_unsloth: true
+warmup_steps: 0