End of training

README.md

@@ -1,10 +1,11 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: meta-llama/Llama-2-7b-chat-hf
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: results
   results: []
@@ -13,9 +14,15 @@ 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/agam_/huggingface/runs/9nsrefgc)
+[<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/agam_/huggingface/runs/9nsrefgc)
+[<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/agam_/huggingface/runs/9nsrefgc)
+[<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/agam_/huggingface/runs/9nsrefgc)
+[<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/agam_/huggingface/runs/9nsrefgc)
+[<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/agam_/huggingface/runs/9nsrefgc)
 # results
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown 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 an unknown dataset.
 
 ## Model description
 
@@ -36,24 +43,20 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 4
-- eval_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 500
+- training_steps: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- PEFT 0.7.1
-- Transformers 4.37.1
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- PEFT 0.10.1.dev0
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "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": {},
@@ -22,5 +23,7 @@
     "v_proj",
     "q_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05662b71751a419792065b0f7249afa22896e4868c2eca8d87a2b41c2f59c61
-size 134235048
+oid sha256:dcb7f102f69ee992b3c25a5242755478457a8e195561ae06cab9a5b9f185f5d2
+size 109069176

runs/May11_11-01-13_8d69fa7a2964/events.out.tfevents.1715425434.8d69fa7a2964.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380e36bdd45c5f0b74e560b8b8acc33fb66a5bf20dee4e3006151c6dd6d53812
+size 5298

runs/May11_11-10-54_8d69fa7a2964/events.out.tfevents.1715425872.8d69fa7a2964.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a86e7cdbbad690da25f98b97a4fecdee6430d388ba59077b8abbf0501ca9758
+size 10508

runs/May11_11-10-54_8d69fa7a2964/events.out.tfevents.1715426041.8d69fa7a2964.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb093edd1b002681571ec4d8aebefd7ccdd7e496d0cbdd5162f93fa3220eaef5
+size 5298

runs/May11_11-10-54_8d69fa7a2964/events.out.tfevents.1715427563.8d69fa7a2964.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce4d3d97ae0ff682d7d16ee17a533e32121c3050d329e81cced93f06776e6a5
+size 10508

runs/May11_11-46-51_8d69fa7a2964/events.out.tfevents.1715428484.8d69fa7a2964.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cdd92b0ad98e8ff3851e1ed49697d3e2a2d54026032474b924a707e8516a115
+size 5502

special_tokens_map.json

@@ -2,14 +2,14 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -17,7 +17,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "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

@@ -5,7 +5,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,27 +21,21 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
+  "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": 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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492c76516965067a057043bc9d938b5eee43ff70e469a09aca6ddd62c1874e73
-size 4664
+oid sha256:5f85484e7286d0f101924d3f181cf9f86b12c8253ae87b989a8c26995d14a090
+size 5112