embed-finetuned-llama-3.2

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,20 +1,20 @@
----
-library_name: peft
-license: apache-2.0
-base_model: SmallDoge/Doge-60M-Instruct
-tags:
-- generated_from_trainer
-model-index:
-- name: finetuned_model
-  results: []
----
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+library_name: peft
+license: llama3.2
+tags:
+- generated_from_trainer
+model-index:
+- name: finetuned_model
+  results: []
+---
 
 <!-- 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. -->
 
 # finetuned_model
 
-This model is a fine-tuned version of [SmallDoge/Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -33,12 +33,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 4
+- learning_rate: 0.0002
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
@@ -49,7 +52,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.15.2
-- Transformers 4.52.4
-- Pytorch 2.6.0+cu124
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
 - Datasets 3.6.0
-- Tokenizers 0.21.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -1,36 +1,39 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "SmallDoge/Doge-60M-Instruct",
-  "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "v_proj",
-    "q_proj",
-    "k_proj",
-    "o_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_rslora": false
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7b0b746d440974dd241205809bb7fad60789e1baa11e4ae703884309f00d3a
-size 1851584
+oid sha256:a6f50aae4d1de3230cb201cfdd098cc519507fb10dc86f2050951d6ca98bcf1b
+size 22573704

special_tokens_map.json

@@ -1,17 +1,17 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|end_of_text|>"
-}
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0344d2feb3682d99df6c52b54ea89e60faf72246b983d910cb4c86c3f2de52a9
-size 5240
+oid sha256:c9b70088318b9ee2378e6944884ceede5ea4eb1603fd93cad94afe6a8b5e48c7
+size 5176