End of training

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: NXAIR_M_mistral-7B
+  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. -->
+
+# NXAIR_M_mistral-7B
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8905
+
+## 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: 0.00025
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0223        | 0.39  | 100  | 1.0286          |
+| 0.9037        | 0.78  | 200  | 0.8790          |
+| 0.5836        | 1.16  | 300  | 0.7868          |
+| 0.5867        | 1.55  | 400  | 0.7354          |
+| 0.5663        | 1.94  | 500  | 0.7268          |
+| 0.4228        | 2.33  | 600  | 0.7649          |
+| 0.423         | 2.71  | 700  | 0.7254          |
+| 0.3011        | 3.1   | 800  | 0.7822          |
+| 0.3317        | 3.49  | 900  | 0.7891          |
+| 0.3722        | 3.88  | 1000 | 0.8496          |
+| 0.3005        | 4.26  | 1100 | 0.7813          |
+| 0.3101        | 4.65  | 1200 | 0.7908          |
+| 0.3549        | 5.04  | 1300 | 0.7937          |
+| 0.3198        | 5.43  | 1400 | 0.7881          |
+| 0.2999        | 5.81  | 1500 | 0.7738          |
+| 0.2822        | 6.2   | 1600 | 0.8227          |
+| 0.2977        | 6.59  | 1700 | 0.8299          |
+| 0.3066        | 6.98  | 1800 | 0.8399          |
+| 0.2704        | 7.36  | 1900 | 0.8435          |
+| 0.2703        | 7.75  | 2000 | 0.8527          |
+| 0.2281        | 8.14  | 2100 | 0.8745          |
+| 0.2321        | 8.53  | 2200 | 0.8396          |
+| 0.2528        | 8.91  | 2300 | 0.8342          |
+| 0.2177        | 9.3   | 2400 | 0.8183          |
+| 0.245         | 9.69  | 2500 | 0.8264          |
+| 0.1965        | 10.08 | 2600 | 0.8772          |
+| 0.2107        | 10.47 | 2700 | 0.8543          |
+| 0.2178        | 10.85 | 2800 | 0.8353          |
+| 0.2091        | 11.24 | 2900 | 0.8685          |
+| 0.2253        | 11.63 | 3000 | 0.8220          |
+| 0.2395        | 12.02 | 3100 | 0.8233          |
+| 0.2216        | 12.4  | 3200 | 0.9099          |
+| 0.2392        | 12.79 | 3300 | 0.8779          |
+| 0.237         | 13.18 | 3400 | 0.9224          |
+| 0.227         | 13.57 | 3500 | 0.8935          |
+| 0.231         | 13.95 | 3600 | 0.9021          |
+| 0.1922        | 14.34 | 3700 | 0.9564          |
+| 0.211         | 14.73 | 3800 | 0.8905          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "lm_head",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2612b7044682ec4c6266c8f6ef802169c08abed991d65d27fcb0a4f017fdc822
+size 609389712

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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "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:d28e2976893d061c8b2e630fcf076f901ed1602f7c777dc70a80a84dcc228623
+size 4728