Mithul27/GPT2-fine-tuned

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: gpt2-medium
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 
 ## Model description
 
@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,13 +12,11 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 1024,
-  "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 sha256:4ae31103acbf5c328fe56e8a0ae2e5ef0bd1f02f5db63e67c76e2e549c7b08a1
-size 1419322880
+oid sha256:deff919f287121430f52d41b86b6c7ffb005302f312c9c301b557b60dd6816cf
+size 497774208

runs/Jul09_13-09-39_e1c3468dab8e/events.out.tfevents.1720530579.e1c3468dab8e.14400.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161571cf4ab3e52b83fcb2815fc696a8ebbfdb037b7cbc3f4c52acc71e10c076
+size 5014

runs/Jul09_13-09-56_e1c3468dab8e/events.out.tfevents.1720530597.e1c3468dab8e.14400.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc8873b14553dc812906f9878c38cf9d543614d81a3f936a54357f3c6c7e6d5
+size 5368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec3fb53b5583bfb949cbe203a0e4ae37d0ba5047061dee4395b08cd5ffc9e66
+oid sha256:7179f5f511f084f8d5821256ef5e3f8f9cd6bf9bb893ee8b38d6c6b7dcf55465
 size 5048