End of training

README.md

@@ -1,11 +1,11 @@
 ---
-library_name: transformers
 license: mit
-base_model: gpt2-large
+base_model: openai-community/gpt2-large
 tags:
 - trl
 - dpo
 - generated_from_trainer
+library_name: peft
 model-index:
 - name: Jon_GPT2L_DPO_epi_inf
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Jon_GPT2L_DPO_epi_inf
 
-This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on the None dataset.
+This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the None dataset.
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.005
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
@@ -44,7 +44,7 @@ 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_steps: 10
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
@@ -52,7 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.45.1
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+- PEFT 0.8.2
+- Transformers 4.38.2
+- Pytorch 2.5.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2-large",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc6f5b47e30c0a559a2f0027e6258329571dea4c58f6654ff1e999aaee1ea38
+size 11805792

runs/Nov14_00-55-45_cbda12b040f0/events.out.tfevents.1731545757.cbda12b040f0.3705.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f633d6e6a127e374c3f27488111114ef4dd6639a000818c2253f02727c35c736
+size 31690

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -11,7 +11,10 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
+  "device_map": {
+    "": 0
+  },
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67313b3a7340e59f9932a4d86519d9b8e480c6069fd1bd55e602473b5a0682a5
-size 6008
+oid sha256:07302ad44de364a95c028f65f7cda1cc1b00c7c2646eb77db24ee0656fa1787a
+size 4920