KQL/mistral_v2_KQL_generation

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 datasets:
 - generator
-base_model: mistralai/Mistral-7B-Instruct-v0.1
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: mistral_instruct_generation
   results: []
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct_generation
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2659
+- Loss: 0.3490
 
 ## Model description
 
@@ -40,24 +40,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 8
 - 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_steps: 0.03
-- training_steps: 100
+- training_steps: 200
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6875        | 0.95  | 20   | 0.5770          |
-| 0.3974        | 1.9   | 40   | 0.3765          |
-| 0.2749        | 2.86  | 60   | 0.3056          |
-| 0.2231        | 3.81  | 80   | 0.2741          |
-| 0.1768        | 4.76  | 100  | 0.2659          |
+| 0.2485        | 7.14  | 200  | 0.3490          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "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 sha256:59c2cc02abc122e445a1d5ce7b85e2cee2613f35f48f9cfcd60e583260235ce4
-size 109069176
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Mar19_01-11-19_4bc44cfaed06/events.out.tfevents.1710810686.4bc44cfaed06.192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788ccf9c7c2a3596ab4d884f9035609b79883c647550c09b539e86d8c5b5554f
+size 9849

tokenizer_config.json

@@ -29,6 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118bd7e334bd327bc8f9234db3bb4d7537c2e6b7c43245af25481aa4a902fc30
+oid sha256:2b1bb7507cbb097e8e5fc9bf234b70b843643776c54835a937acf0f8e247355b
 size 4920