End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: gpt2
+license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # LEDA-v1
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 5.3486
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 
 ## Model description
 
@@ -34,28 +32,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.002
+- train_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 128
+- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 5.3987        | 0.8   | 5000 | 5.3486          |
 
 
 ### Framework versions
 
-- Transformers 4.35.0
+- Transformers 4.35.2
 - Pytorch 2.0.0
 - Datasets 2.1.0
-- Tokenizers 0.14.1
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,14 +9,20 @@
   "bos_token_id": 0,
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 160,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 6,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -33,7 +40,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 3372
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.35.0"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f5a1093f2bf9e2b6dd92a4a01cd190c9d9a12e641045b28238dc9a18db6740
-size 353743488
+oid sha256:a4d9989af044c739f698ffdaa3d129f142cc734a374b233d53b6b1291a7a03de
+size 183627208

runs/Dec10_17-54-16_92ff5bf1e590/events.out.tfevents.1702230867.92ff5bf1e590.42.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cc50bbd82364851fd8d8de047a7a1d423a7f4320451abf2e855e359f5f215c
+size 4882

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60bc919dced4a5b31c726814e3730056573c17ad28afca8e00414d39cd6a6ae2
+oid sha256:5f8d0caf08fbdd7d62143470f60d51e8807ae2c5bf81dcac327bbf51e243a3df
 size 4091