End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: gpt2
+base_model: percymamedy/reuters-gpt2-text-gen
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # reuters-gpt2-text-gen
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [percymamedy/reuters-gpt2-text-gen](https://huggingface.co/percymamedy/reuters-gpt2-text-gen) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.9851
+- Loss: 4.7849
 
 ## Model description
 
@@ -42,15 +42,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 5.1471        | 0.9972 | 269  | 5.2732          |
-| 4.7545        | 1.9944 | 538  | 4.9851          |
+| 4.5575        | 0.9972 | 269  | 4.7849          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "percymamedy/reuters-gpt2-text-gen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978655c2ff5f17beffcba95746bc5063ed6d2c2dce62fca4779613ace11b7f7d
+oid sha256:12e67108630bbd18be421b18837a0e14af3ee031eb00afe0939fef46cbc36aa4
 size 503128704

runs/Jun25_06-25-46_65dc034aa3e6/events.out.tfevents.1719296757.65dc034aa3e6.390.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b84b1a0c95446ab4fba60632b602c5b2de3543453ff713b14b1efe0fb31f76
+size 11202

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -13,8 +13,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 512,
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5655016fd1d310be906e0e039b11530d6b1947b9dcf8d4a9d6ca4ffc94a4ee2
+oid sha256:99f904a03b640c6ea0243277e7164f908b9d5f90f6daf6b94b8ac8915e653402
 size 5176