IbrahimTarek/Boiler_gemma7b

README.md

@@ -3,7 +3,7 @@ license: gemma
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: google/gemma-2b-it
+base_model: google/gemma-7b-it
 model-index:
 - name: your-model
   results: []
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # your-model
 
-This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on an unknown dataset.
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 30
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-2b-it",
+  "base_model_name_or_path": "google/gemma-7b-it",
   "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 sha256:4a597a66a3be8df1f81f0940a6792a1ceb7398095372233f4126f5fb6f0d9b72
-size 3695848
+oid sha256:89fb9766a1291baad715f3917915bb961d2f6d1bbdbd92eb5356c9c8a7813362
+size 12859872

runs/Apr14_09-54-15_88d58899358b/events.out.tfevents.1713088471.88d58899358b.1884.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9d2559e947ab479a1018c55175db69b7c420d9dc4dd5cfac769af53da22cb3
+size 5982

runs/Apr14_09-55-27_88d58899358b/events.out.tfevents.1713088534.88d58899358b.1884.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b457af18413bbb8c0f9a2420ca6b56217e2043e128fab55bab5849f691eeab
+size 266640

tokenizer_config.json

@@ -58,7 +58,6 @@
   "bos_token": "<bos>",
   "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "device": "cuda",
   "eos_token": "<eos>",
   "legacy": null,
   "model_max_length": 1000000000000000019884624838656,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86a6c0829b995d267b5ff9ed8b5f8a3064cd678a2b29861c400374880e37efe
+oid sha256:4c7b8a4d3e62da2cd0ab4f446fdd4b4ecae487ec0082b7f576cb84ccc8dff969
 size 4984