End of training

README.md

@@ -0,0 +1,110 @@
+---
+license: llama2
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: llama_2_7b_Magiccoder_evol_downNupNgateNqNkNvNo_r8_lr0.0001_bg88_alpha8_0_41_normlayergrad
+  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. -->
+
+# llama_2_7b_Magiccoder_evol_downNupNgateNqNkNvNo_r8_lr0.0001_bg88_alpha8_0_41_normlayergrad
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1291
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3048        | 0.0203 | 31   | 1.2412          |
+| 1.1685        | 0.0405 | 62   | 1.2116          |
+| 1.1585        | 0.0608 | 93   | 1.1957          |
+| 1.1653        | 0.0810 | 124  | 1.1848          |
+| 1.1337        | 0.1013 | 155  | 1.1766          |
+| 1.1308        | 0.1215 | 186  | 1.1674          |
+| 1.1602        | 0.1418 | 217  | 1.1661          |
+| 1.1277        | 0.1620 | 248  | 1.1611          |
+| 1.1375        | 0.1823 | 279  | 1.1615          |
+| 1.1095        | 0.2025 | 310  | 1.1582          |
+| 1.1043        | 0.2228 | 341  | 1.1551          |
+| 1.1269        | 0.2431 | 372  | 1.1511          |
+| 1.1175        | 0.2633 | 403  | 1.1533          |
+| 1.1252        | 0.2836 | 434  | 1.1491          |
+| 1.1192        | 0.3038 | 465  | 1.1513          |
+| 1.1074        | 0.3241 | 496  | 1.1437          |
+| 1.117         | 0.3443 | 527  | 1.1459          |
+| 1.1058        | 0.3646 | 558  | 1.1427          |
+| 1.1144        | 0.3848 | 589  | 1.1416          |
+| 1.0913        | 0.4051 | 620  | 1.1435          |
+| 1.111         | 0.4254 | 651  | 1.1388          |
+| 1.1239        | 0.4456 | 682  | 1.1397          |
+| 1.1074        | 0.4659 | 713  | 1.1402          |
+| 1.1076        | 0.4861 | 744  | 1.1396          |
+| 1.0887        | 0.5064 | 775  | 1.1374          |
+| 1.0872        | 0.5266 | 806  | 1.1358          |
+| 1.0802        | 0.5469 | 837  | 1.1351          |
+| 1.0812        | 0.5671 | 868  | 1.1338          |
+| 1.097         | 0.5874 | 899  | 1.1352          |
+| 1.1052        | 0.6076 | 930  | 1.1352          |
+| 1.088         | 0.6279 | 961  | 1.1328          |
+| 1.0977        | 0.6482 | 992  | 1.1315          |
+| 1.0902        | 0.6684 | 1023 | 1.1312          |
+| 1.1085        | 0.6887 | 1054 | 1.1309          |
+| 1.0956        | 0.7089 | 1085 | 1.1294          |
+| 1.0897        | 0.7292 | 1116 | 1.1310          |
+| 1.0816        | 0.7494 | 1147 | 1.1304          |
+| 1.0995        | 0.7697 | 1178 | 1.1296          |
+| 1.1032        | 0.7899 | 1209 | 1.1292          |
+| 1.0878        | 0.8102 | 1240 | 1.1297          |
+| 1.0988        | 0.8304 | 1271 | 1.1294          |
+| 1.0915        | 0.8507 | 1302 | 1.1294          |
+| 1.0823        | 0.8710 | 1333 | 1.1295          |
+| 1.0867        | 0.8912 | 1364 | 1.1289          |
+| 1.098         | 0.9115 | 1395 | 1.1290          |
+| 1.1071        | 0.9317 | 1426 | 1.1292          |
+| 1.061         | 0.9520 | 1457 | 1.1291          |
+| 1.0708        | 0.9722 | 1488 | 1.1292          |
+| 1.0977        | 0.9925 | 1519 | 1.1291          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,73 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fad8cc5aa525f30673e12e6fd993782559e7600cce3ebc596ef82f204958981
+size 80013120

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": "<unk>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6746ecece9c5f207e2a263b71f4a04936b5a35b31cbb45f7fccd2a6ff6ccb9
+size 5304