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_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_Magiccoder_evol_10k_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: 1.1146
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1799        | 0.0262 | 4    | 1.1888          |
+| 1.1193        | 0.0523 | 8    | 1.1757          |
+| 1.1603        | 0.0785 | 12   | 1.1751          |
+| 1.0847        | 0.1047 | 16   | 1.1702          |
+| 1.1304        | 0.1308 | 20   | 1.1674          |
+| 1.042         | 0.1570 | 24   | 1.1582          |
+| 1.1863        | 0.1832 | 28   | 1.1633          |
+| 1.14          | 0.2093 | 32   | 1.1597          |
+| 1.0763        | 0.2355 | 36   | 1.1503          |
+| 1.135         | 0.2617 | 40   | 1.1458          |
+| 1.1623        | 0.2878 | 44   | 1.1393          |
+| 1.1173        | 0.3140 | 48   | 1.1423          |
+| 1.1283        | 0.3401 | 52   | 1.1482          |
+| 1.0967        | 0.3663 | 56   | 1.1356          |
+| 1.1131        | 0.3925 | 60   | 1.1338          |
+| 1.1613        | 0.4186 | 64   | 1.1419          |
+| 1.0548        | 0.4448 | 68   | 1.1454          |
+| 1.0629        | 0.4710 | 72   | 1.1320          |
+| 1.0679        | 0.4971 | 76   | 1.1355          |
+| 1.16          | 0.5233 | 80   | 1.1287          |
+| 1.0579        | 0.5495 | 84   | 1.1295          |
+| 1.1214        | 0.5756 | 88   | 1.1392          |
+| 1.1681        | 0.6018 | 92   | 1.1242          |
+| 1.1667        | 0.6280 | 96   | 1.1223          |
+| 1.0871        | 0.6541 | 100  | 1.1221          |
+| 1.1147        | 0.6803 | 104  | 1.1243          |
+| 1.1075        | 0.7065 | 108  | 1.1254          |
+| 0.9958        | 0.7326 | 112  | 1.1186          |
+| 1.0718        | 0.7588 | 116  | 1.1085          |
+| 1.0748        | 0.7850 | 120  | 1.1193          |
+| 1.1082        | 0.8111 | 124  | 1.1138          |
+| 1.0981        | 0.8373 | 128  | 1.1102          |
+| 1.1231        | 0.8635 | 132  | 1.1133          |
+| 1.0687        | 0.8896 | 136  | 1.1143          |
+| 1.1568        | 0.9158 | 140  | 1.1139          |
+| 1.0177        | 0.9419 | 144  | 1.1140          |
+| 1.0401        | 0.9681 | 148  | 1.1145          |
+| 1.1827        | 0.9943 | 152  | 1.1146          |
+
+
+### 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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8fa4cf1e3337261329f42ee7529f439580414f17d6c4f6e40873ed714cfd4d
+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 sha256:75cc822c1b8eba07721f2c20b3e222a978cdd320b4a0c7af1e0f7f625cea73f5
+size 5112