End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: openai-community/gpt2
+base_model: openai-community/gpt2-medium
 tags:
 - trl
 - sft
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/gpt2-medium) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "openai-community/gpt2",
+ "_name_or_path": "openai-community/gpt2-medium",
  "activation_function": "gelu_new",
  "architectures": [
  "GPT2LMHeadModel"
@@ -12,12 +12,13 @@
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 1024,
- "n_embd": 768,
- "n_head": 12,
+ "n_embd": 1024,
+ "n_head": 16,
  "n_inner": null,
- "n_layer": 12,
+ "n_layer": 24,
  "n_positions": 1024,
- "pretraining_tp": 1,
+ "n_special": 0,
+ "predict_special_tokens": true,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d00560d8910fbed77ffad4065dee5011c41ba401b1064e749c498ba9e20373
-size 497774208
+oid sha256:1fe2c3aa64cf154c9c9a9d6349778291668f2bb46751fad3b97857d1fe0e43bc
+size 1419322880

runs/Jul16_10-09-23_8bd9fb9c51a0/events.out.tfevents.1721124568.8bd9fb9c51a0.196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329f1d267375f450074e6ad8a0a4fa2b32ccd0d4101ec7821d1a60d1ebe78d30
+size 5368

runs/Jul16_10-10-57_8bd9fb9c51a0/events.out.tfevents.1721124660.8bd9fb9c51a0.196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8270634614d28aa9041bdc3e242904b4b6472b1ed5b779f60ac37452706758
+size 5716

tokenizer.json

@@ -2,7 +2,7 @@
  "version": "1.0",
  "truncation": {
  "direction": "Right",
- "max_length": 50,
+ "max_length": 256,
  "strategy": "LongestFirst",
  "stride": 0
  },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bb3672810d5315995a88fe121cb5fcecb8e3f7ce52f0f7792bcbdf10f3405e
+oid sha256:75889f3905a21cd8a1ac9524dfc5229f5f543d48e4c1a2076c1c3c83b90585cf
 size 5304