End of training

README.md

@@ -0,0 +1,92 @@
+---
+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: 0.6929
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1435        | 0.0702 | 100  | 1.1971          |
+| 1.0993        | 0.1404 | 200  | 1.0390          |
+| 1.0643        | 0.2107 | 300  | 0.9309          |
+| 0.956         | 0.2809 | 400  | 0.9125          |
+| 0.9906        | 0.3511 | 500  | 0.8591          |
+| 0.9083        | 0.4213 | 600  | 0.8703          |
+| 0.8951        | 0.4916 | 700  | 0.8179          |
+| 0.8352        | 0.5618 | 800  | 0.7852          |
+| 0.8472        | 0.6320 | 900  | 0.7772          |
+| 0.8733        | 0.7022 | 1000 | 0.7447          |
+| 0.7958        | 0.7725 | 1100 | 0.7082          |
+| 0.8726        | 0.8427 | 1200 | 0.7125          |
+| 0.804         | 0.9129 | 1300 | 0.6909          |
+| 0.8467        | 0.9831 | 1400 | 0.7287          |
+| 0.4705        | 1.0534 | 1500 | 0.6921          |
+| 0.4864        | 1.1236 | 1600 | 0.6648          |
+| 0.4535        | 1.1938 | 1700 | 0.6765          |
+| 0.4542        | 1.2640 | 1800 | 0.6620          |
+| 0.4789        | 1.3343 | 1900 | 0.6584          |
+| 0.5154        | 1.4045 | 2000 | 0.6492          |
+| 0.459         | 1.4747 | 2100 | 0.6647          |
+| 0.5168        | 1.5449 | 2200 | 0.6484          |
+| 0.483         | 1.6152 | 2300 | 0.6795          |
+| 0.4768        | 1.6854 | 2400 | 0.6730          |
+| 0.4821        | 1.7556 | 2500 | 0.6404          |
+| 0.4929        | 1.8258 | 2600 | 0.6409          |
+| 0.5438        | 1.8961 | 2700 | 0.6551          |
+| 0.4598        | 1.9663 | 2800 | 0.6740          |
+| 0.4902        | 2.0365 | 2900 | 0.7287          |
+| 0.5058        | 2.1067 | 3000 | 0.7142          |
+| 0.4615        | 2.1770 | 3100 | 0.6929          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "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,
+  "layer_replication": null,
+  "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": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "lm_head",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5894b8f370384519acfc7170b5d71f71d17a5bcb20455ddd07b20b06d0540b77
+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:e00103715f22d6650f40d9330ccae5b42950550043ff9448d654f17670311f99
+size 4984