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_ortho_eye
+  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_ortho_eye
+
+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: 0.4403
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7124        | 0.0211 | 13   | 0.5905          |
+| 0.5476        | 0.0421 | 26   | 0.5631          |
+| 0.5329        | 0.0632 | 39   | 0.5495          |
+| 0.523         | 0.0842 | 52   | 0.5404          |
+| 0.5078        | 0.1053 | 65   | 0.5362          |
+| 0.5097        | 0.1264 | 78   | 0.5276          |
+| 0.494         | 0.1474 | 91   | 0.5230          |
+| 0.5066        | 0.1685 | 104  | 0.5173          |
+| 0.4881        | 0.1896 | 117  | 0.5167          |
+| 0.4963        | 0.2106 | 130  | 0.5138          |
+| 0.4841        | 0.2317 | 143  | 0.5092          |
+| 0.4676        | 0.2527 | 156  | 0.5046          |
+| 0.4722        | 0.2738 | 169  | 0.5045          |
+| 0.4791        | 0.2949 | 182  | 0.4997          |
+| 0.477         | 0.3159 | 195  | 0.4962          |
+| 0.4791        | 0.3370 | 208  | 0.4947          |
+| 0.4621        | 0.3580 | 221  | 0.4909          |
+| 0.4647        | 0.3791 | 234  | 0.4885          |
+| 0.4584        | 0.4002 | 247  | 0.4858          |
+| 0.4651        | 0.4212 | 260  | 0.4814          |
+| 0.4761        | 0.4423 | 273  | 0.4792          |
+| 0.4621        | 0.4633 | 286  | 0.4783          |
+| 0.4556        | 0.4844 | 299  | 0.4758          |
+| 0.4556        | 0.5055 | 312  | 0.4726          |
+| 0.4551        | 0.5265 | 325  | 0.4674          |
+| 0.4554        | 0.5476 | 338  | 0.4637          |
+| 0.4486        | 0.5687 | 351  | 0.4620          |
+| 0.4413        | 0.5897 | 364  | 0.4619          |
+| 0.4416        | 0.6108 | 377  | 0.4611          |
+| 0.4358        | 0.6318 | 390  | 0.4559          |
+| 0.4399        | 0.6529 | 403  | 0.4538          |
+| 0.4324        | 0.6740 | 416  | 0.4535          |
+| 0.4217        | 0.6950 | 429  | 0.4506          |
+| 0.4423        | 0.7161 | 442  | 0.4488          |
+| 0.4281        | 0.7371 | 455  | 0.4469          |
+| 0.4402        | 0.7582 | 468  | 0.4456          |
+| 0.4363        | 0.7793 | 481  | 0.4447          |
+| 0.4385        | 0.8003 | 494  | 0.4433          |
+| 0.429         | 0.8214 | 507  | 0.4435          |
+| 0.4199        | 0.8424 | 520  | 0.4421          |
+| 0.4223        | 0.8635 | 533  | 0.4415          |
+| 0.4158        | 0.8846 | 546  | 0.4412          |
+| 0.4369        | 0.9056 | 559  | 0.4408          |
+| 0.432         | 0.9267 | 572  | 0.4407          |
+| 0.4202        | 0.9478 | 585  | 0.4403          |
+| 0.4239        | 0.9688 | 598  | 0.4403          |
+| 0.4228        | 0.9899 | 611  | 0.4403          |
+
+
+### 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": [
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542e97e986e2e9c835fc080b4099f835b6b925a3880d26fc43471788e9e0334c
+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 sha256:67b5db49c7859f048cd2802b36a0f87482ea918732bb4dd384c099c25583fc35
+size 5112