Training in progress, step 200

README.md

@@ -0,0 +1,73 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+license: apache-2.0
+metrics:
+- accuracy
+- precision
+- recall
+tags:
+- generated_from_trainer
+model-index:
+- name: Mistral_Task2_semantic_pred
+  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_Task2_semantic_pred
+
+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: 1.0200
+- Accuracy: 0.7414
+- Precision: 0.6613
+- Recall: 0.9749
+- F1 score: 0.7880
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Accuracy | F1 score | Precision | Recall | Validation Loss |
+|:-------------:|:------:|:----:|:--------:|:--------:|:---------:|:------:|:---------------:|
+| 0.8426        | 0.5208 | 200  | 0.7824   | 0.7958   | 0.7406    | 0.8600 | 0.6397          |
+| 0.6067        | 1.0417 | 400  | 0.6599   | 0.7353   | 0.5967    | 0.9577 | 0.9629          |
+| 0.3511        | 1.5625 | 600  | 0.7922   | 0.8151   | 0.7262    | 0.9287 | 0.5420          |
+| 0.3361        | 2.0833 | 800  | 0.9585   | 0.6769   | 0.6074    | 0.9749 | 0.7485          |
+| 0.2423        | 2.6042 | 1000 | 0.4802   | 0.8339   | 0.7728    | 0.9392 | 0.8479          |
+| 0.2082        | 3.125  | 1200 | 0.6629   | 0.7961   | 0.7181    | 0.9657 | 0.8237          |
+| 0.1397        | 3.6458 | 1400 | 1.0200   | 0.7414   | 0.6613    | 0.9749 | 0.7880          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- 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": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14e493361ac835146c60f495859d5a646647f6d2d9376129c2a24b77b868718
+size 54593240

runs/Sep02_19-13-42_user/events.out.tfevents.1725284623.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638c7c6a513bdf32a03879fe77fced3652b3daf4d39dd4bd20244d9b2a482e09
+size 4227

runs/Sep02_19-15-48_user/events.out.tfevents.1725284749.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5e82502c833367aca1fb212f17b0b26499a32b5325caf7f175d6c49f17bf3a
+size 5500

runs/Sep02_19-28-03_user/events.out.tfevents.1725285484.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146f5f8ab88618fb4690f517828bbac2a286171a18a29a318a0d9df8ad1a911c
+size 5500

runs/Sep02_20-31-49_user/events.out.tfevents.1725289310.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d130b877675aea111267159625aab40f1922167ad3c35cc17744ec7b0635f615
+size 5711

runs/Sep02_22-14-00_user/events.out.tfevents.1725295441.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5c756c232888269d735d091ada8bb66f87fd3b9c2703e6f103ca5ca2688df2
+size 5951

runs/Sep02_22-30-31_user/events.out.tfevents.1725296432.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f0103333fdd46237acb174b18328170a59e3705e5168b083172f18cd5a1cd1
+size 7089

runs/Sep03_03-20-11_user/events.out.tfevents.1725313812.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31036bc364fbeb3b7ad79e6ac2ea2998c312aa3e672a6e226530cd81ce75d406
+size 8610

runs/Sep03_13-23-40_user/events.out.tfevents.1725350022.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77513759dd55700c4848a56f309fa1c889c711610ae8929c5045a482920075b
+size 5500

runs/Sep03_14-51-53_user/events.out.tfevents.1725355314.user

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27558ceda460e382ad2109581136146d2d7d62f85012d7562c5028565f60b73
+size 5711

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": false,
+  "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:f927a7760e08b9a96f4d07976f3009a3067faeac02be8157e8c6c3154e556df2
+size 5240