End of training

README.md

@@ -1,10 +1,12 @@
 ---
-license: mit
-base_model: HuggingFaceH4/mistral-7b-sft-beta
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
 - trl
 - reward-trainer
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: rm_zephyr
   results: []
@@ -15,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # rm_zephyr
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4657
+- Accuracy: 0.7599
 
 ## Model description
 
@@ -39,21 +44,25 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 7
+- num_devices: 8
 - gradient_accumulation_steps: 32
-- total_train_batch_size: 224
-- total_eval_batch_size: 7
+- total_train_batch_size: 256
+- total_eval_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1.0
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.5368        | 0.4290 | 100  | 0.4863          | 0.7537   |
+| 0.4497        | 0.8580 | 200  | 0.4657          | 0.7599   |
 
 
 ### Framework versions
 
-- Transformers 4.40.1
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
   "architectures": [
     "MistralForSequenceClassification"
   ],
@@ -27,7 +27,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.1",
   "use_cache": true,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2d615765cf79772d162d57eb87e1b0b75ea427ae0d93ada943fb98710f23c4
+oid sha256:105d7a303bc53cb2da3f026768889215497153e2c68f91a3b75e91e8c6bf87aa
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0d8a0118b2607f26f912fed55d58f18b5b794fdd329c012c66a40f574e3d7c
+oid sha256:65455db6b99bf0d4bde1ac18b4418894628fbf1255967a42cea7496515d00d65
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2673659c4d1ad4af161ed59550c9629e80ea3fb52924082331f28975b71a0db8
+oid sha256:44c2123f83f42bfe919f26e2f96736696f4e61477e4df00d5156ca834d678848
 size 4278380512

special_tokens_map.json

@@ -1,9 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -19,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -29,6 +29,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -25,24 +25,27 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "left",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e09ea8807e52f329fbf728777352d40c4ec516261d6959d9a9b57307aca9a6
+oid sha256:095a22d234f78ca72ea0d6cc056b9bfcca05d7707da427187fbcf3718fd219f4
 size 6072