End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: gpt2
+base_model: ganeshkamath89/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 [ganeshkamath89/reuters-gpt2-text-gen](https://huggingface.co/ganeshkamath89/reuters-gpt2-text-gen) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.3641
+- Loss: 5.0228
 
 ## Model description
 
@@ -42,15 +42,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.5936        | 0.99  | 134  | 5.6813          |
-| 5.2331        | 1.99  | 268  | 5.3641          |
+| 4.7518        | 1.0   | 269  | 5.0228          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "ganeshkamath89/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 sha256:9331e655688ab56394fd1b9121a99b53c557fdd75e4cbdf58d4661479c84e167
+oid sha256:8eb38021f37d9ce470dcc2d546b06e4b82bfb4c40fb5df8734027d30a240ede1
 size 503128704

runs/Apr06_16-21-28_8093e94b5dd6/events.out.tfevents.1712420495.8093e94b5dd6.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0f28c6efee7f2031abb48e6bea023bc792de8d407278ddcd85b386fe43e655
+size 25447

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "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 sha256:13298c02f058acf2db7eff44286173b59246631b3128df6471a25bdde3ede454
+oid sha256:1c8453de0c945427e73ce3e77187c693c284267d4d54562cfd2744d0e64b375f
 size 4984