End of training

README.md

@@ -1,8 +1,12 @@
 ---
 base_model: mistralai/Mistral-7B-Instruct-v0.3
+datasets:
+- generator
 library_name: peft
 license: apache-2.0
 tags:
+- trl
+- sft
 - generated_from_trainer
 model-index:
 - name: mistral-mistralinstruct_climate_finetune
@@ -12,12 +16,12 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fayetitchenal-university-of-california-berkeley/mistralinstruct_climate_finetune/runs/gmsc32zy)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fayetitchenal-university-of-california-berkeley/mistralinstruct_climate_finetune/runs/9qdupr57)
 # mistral-mistralinstruct_climate_finetune
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3746
+- Loss: 0.6394
 
 ## Model description
 
@@ -36,26 +40,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.4405        | 1.0   | 225  | 1.3746          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.632         | 0.9811 | 26   | 1.3186          |
+| 1.0175        | 2.0    | 53   | 0.8842          |
+| 0.555         | 2.9434 | 78   | 0.6394          |
 
 
 ### Framework versions
 
 - PEFT 0.11.1
 - Transformers 4.42.4
-- Pytorch 2.3.0+cu121
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -10,24 +10,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
+    "gate_proj",
     "up_proj",
     "k_proj",
-    "q_proj",
+    "o_proj",
     "v_proj",
-    "lm_head",
-    "gate_proj",
-    "o_proj"
+    "q_proj",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9010fa0e14478022d1a3b9669ffdedf21b6c7d4574101497c97a5889a94b600
-size 877194832
+oid sha256:15c5f87436c262db9d8832cb20053866733212d51d14af88d265cedc21c4ab07
+size 707063376

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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d911a0b3b264d51226df6906204160801ffea4e80236a6560d65071546b737d9
-size 5304
+oid sha256:fac0d1b77b547b8ccf7ea91b8614e1e1551b75edbfe0b7ae34f6578a7bc080f3
+size 5496