End of training

README.md

@@ -0,0 +1,100 @@
+---
+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_Magiccoder_evol_10k_ortho
+  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_Magiccoder_evol_10k_ortho
+
+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: 1.1371
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1548        | 0.0262 | 4    | 1.1975          |
+| 1.1117        | 0.0523 | 8    | 1.1750          |
+| 1.1638        | 0.0785 | 12   | 1.1670          |
+| 1.0902        | 0.1047 | 16   | 1.1675          |
+| 1.1292        | 0.1308 | 20   | 1.1671          |
+| 1.0469        | 0.1570 | 24   | 1.1621          |
+| 1.2005        | 0.1832 | 28   | 1.1638          |
+| 1.1491        | 0.2093 | 32   | 1.1638          |
+| 1.0749        | 0.2355 | 36   | 1.1475          |
+| 1.1758        | 0.2617 | 40   | 1.1525          |
+| 1.1511        | 0.2878 | 44   | 1.1410          |
+| 1.1229        | 0.3140 | 48   | 1.1532          |
+| 1.1349        | 0.3401 | 52   | 1.1592          |
+| 1.1116        | 0.3663 | 56   | 1.1465          |
+| 1.1127        | 0.3925 | 60   | 1.1517          |
+| 1.1709        | 0.4186 | 64   | 1.1460          |
+| 1.0574        | 0.4448 | 68   | 1.1504          |
+| 1.0794        | 0.4710 | 72   | 1.1414          |
+| 1.0711        | 0.4971 | 76   | 1.1485          |
+| 1.1984        | 0.5233 | 80   | 1.1544          |
+| 1.0625        | 0.5495 | 84   | 1.1346          |
+| 1.151         | 0.5756 | 88   | 1.1728          |
+| 1.1977        | 0.6018 | 92   | 1.1364          |
+| 1.1757        | 0.6280 | 96   | 1.1418          |
+| 1.1191        | 0.6541 | 100  | 1.1487          |
+| 1.1415        | 0.6803 | 104  | 1.1431          |
+| 1.1272        | 0.7065 | 108  | 1.1399          |
+| 1.0134        | 0.7326 | 112  | 1.1431          |
+| 1.09          | 0.7588 | 116  | 1.1261          |
+| 1.0848        | 0.7850 | 120  | 1.1346          |
+| 1.1346        | 0.8111 | 124  | 1.1401          |
+| 1.1336        | 0.8373 | 128  | 1.1371          |
+| 1.1458        | 0.8635 | 132  | 1.1338          |
+| 1.0835        | 0.8896 | 136  | 1.1334          |
+| 1.1795        | 0.9158 | 140  | 1.1345          |
+| 1.0422        | 0.9419 | 144  | 1.1359          |
+| 1.0608        | 0.9681 | 148  | 1.1367          |
+| 1.2045        | 0.9943 | 152  | 1.1371          |
+
+
+### 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",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdeb961475868c1973b03b3e8b17456bda247927413e45725c6bd9f470749a2
+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 sha256:0d33a4ef2bbc9ec7635f7f53470603d89aa1b3036909d2bca8bcaaa5dc675c12
+size 5112