End of training

README.md

@@ -0,0 +1,109 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- unsloth
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.3
+model-index:
+- name: mistral_7b_v_MetaMathQA_40K_reverse
+  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. -->
+
+# mistral_7b_v_MetaMathQA_40K_reverse
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4421
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.02
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7252        | 0.0211 | 13   | 0.6225          |
+| 0.5814        | 0.0421 | 26   | 0.5900          |
+| 0.5599        | 0.0632 | 39   | 0.5751          |
+| 0.548         | 0.0842 | 52   | 0.5708          |
+| 0.5371        | 0.1053 | 65   | 0.5625          |
+| 0.5347        | 0.1264 | 78   | 0.5600          |
+| 0.5232        | 0.1474 | 91   | 0.5529          |
+| 0.5382        | 0.1685 | 104  | 0.5478          |
+| 0.5178        | 0.1896 | 117  | 0.5482          |
+| 0.5272        | 0.2106 | 130  | 0.5423          |
+| 0.5135        | 0.2317 | 143  | 0.5397          |
+| 0.4943        | 0.2527 | 156  | 0.5321          |
+| 0.5012        | 0.2738 | 169  | 0.5323          |
+| 0.5077        | 0.2949 | 182  | 0.5300          |
+| 0.5031        | 0.3159 | 195  | 0.5233          |
+| 0.506         | 0.3370 | 208  | 0.5238          |
+| 0.4851        | 0.3580 | 221  | 0.5180          |
+| 0.4915        | 0.3791 | 234  | 0.5146          |
+| 0.4826        | 0.4002 | 247  | 0.5150          |
+| 0.4964        | 0.4212 | 260  | 0.5096          |
+| 0.4989        | 0.4423 | 273  | 0.5050          |
+| 0.4846        | 0.4633 | 286  | 0.5021          |
+| 0.4776        | 0.4844 | 299  | 0.5006          |
+| 0.4725        | 0.5055 | 312  | 0.4927          |
+| 0.4752        | 0.5265 | 325  | 0.4898          |
+| 0.4719        | 0.5476 | 338  | 0.4862          |
+| 0.4689        | 0.5687 | 351  | 0.4817          |
+| 0.4573        | 0.5897 | 364  | 0.4772          |
+| 0.4536        | 0.6108 | 377  | 0.4754          |
+| 0.4536        | 0.6318 | 390  | 0.4700          |
+| 0.4519        | 0.6529 | 403  | 0.4664          |
+| 0.4448        | 0.6740 | 416  | 0.4633          |
+| 0.4327        | 0.6950 | 429  | 0.4618          |
+| 0.4528        | 0.7161 | 442  | 0.4586          |
+| 0.4379        | 0.7371 | 455  | 0.4557          |
+| 0.4504        | 0.7582 | 468  | 0.4537          |
+| 0.4436        | 0.7793 | 481  | 0.4525          |
+| 0.4451        | 0.8003 | 494  | 0.4497          |
+| 0.435         | 0.8214 | 507  | 0.4482          |
+| 0.4247        | 0.8424 | 520  | 0.4466          |
+| 0.4295        | 0.8635 | 533  | 0.4455          |
+| 0.4204        | 0.8846 | 546  | 0.4444          |
+| 0.4381        | 0.9056 | 559  | 0.4433          |
+| 0.4355        | 0.9267 | 572  | 0.4430          |
+| 0.4234        | 0.9478 | 585  | 0.4424          |
+| 0.4261        | 0.9688 | 598  | 0.4421          |
+| 0.4266        | 0.9899 | 611  | 0.4421          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,73 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40
+  ],
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a374c2b88be072d9716e65bf9e02d9b39b0174f96dbce8c010a7c734696c5123
+size 83945296

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": "[control_768]",
+  "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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3540d0fa1d706c9497b7cfe9a65225c70d741238896c851334610d66d61e2d5a
+size 5112