End of training

README.md

@@ -7,14 +7,14 @@ tags:
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
-- name: mistral-7b-it-ua-gec
+- name: mistral-7b-ua-gec
   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-it-ua-gec
+# mistral-7b-ua-gec
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
 
@@ -36,14 +36,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 5
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1
 
 ### Training results
 
@@ -51,8 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.9.1.dev0
-- Transformers 4.39.0.dev0
+- PEFT 0.10.1.dev0
+- Transformers 4.40.0.dev0
 - Pytorch 2.1.2
 - Datasets 2.16.0
 - Tokenizers 0.15.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/kaggle/input/mistral/pytorch/7b-instruct-v0.1-hf/1",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee7a79115e4fdf1a35765bc1744b1adf5f787484866d9d50378d3db9a7951eb
+oid sha256:4c1737928126f90d8d42507dee56bfa0df9d6a672314c94308398fab39c0e509
 size 23111032

tokenizer_config.json

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -36,7 +35,7 @@
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a3d64117e197a8c1c9cd77fea4f22973966c91427e868cc435ef925c99f659
+oid sha256:ab118c0a55bb33d5f1ab9aed5bbc01cbd2e7d141d301cdb9e5a3b002800c92c1
 size 4920