Training in progress, step 500

README.md

@@ -6,14 +6,6 @@ tags:
 model-index:
 - name: GPT2-arithmetic-3digits
   results: []
-datasets:
-- Nbeau/additiondataset_3digits_10000examples
-widget:
-- text: "Input:\n561+372\nTarget:"
-inference:
-  parameters:
-    add_special_tokens: True
-    do_sample: False
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -69,4 +61,4 @@ The following hyperparameters were used during training:
 - Transformers 4.40.2
 - Pytorch 2.3.0
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

config.json

@@ -17,7 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 2,
+  "pad_token_id": 32000,
   "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 sha256:2cb8cb936fe8224bcc38b887023cc71a454545c82c238652c1fac6e4088583b7
+oid sha256:559704e9da8d819c84387e547a1e42ee323924e58074bb0600c77ae442cec227
 size 441691776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f5cb4d558e9ea973b249dfda6c2f28100bdb0853103fe41bc350cf518db912
+oid sha256:1267483ff059ea879b3a0ea0f4a5afb8cff43a998d3030d4f8be0527a68d0f01
 size 5048