Training in progress, step 500

config.json

@@ -1,30 +1,21 @@
 {
-  "_name_or_path": "distilbert/distilgpt2",
-  "_num_labels": 1,
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "do_sample": true,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
-  "max_length": 50,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
+  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d223556906b98f28cdd2295c15255c62d86fb94b8b949588c135f116f31555
-size 327657928
+oid sha256:f49575472d18824b10eddb72c1abeb23409f275e144bcec177bcc26209d569bc
+size 497774208

runs/Jun15_08-40-22_3981491d00a1/events.out.tfevents.1718440823.3981491d00a1.941.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f4f92b8f146bb2efef8d1854103bf7ac854d330875393ce655cc8fedf38b86
-size 6263
+oid sha256:ed7ea4757eb9194caa4e063ac9335557b68268a76adca9127764b23f58b657da
+size 6888

runs/Jun15_08-40-22_3981491d00a1/events.out.tfevents.1718441203.3981491d00a1.941.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8874de3f678b1ab75a08ecfd6f24d5d557be54a82d0136b00b2a21dc4b1994
+size 359

runs/Jun15_09-20-48_3981491d00a1/events.out.tfevents.1718443249.3981491d00a1.941.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9550f63b55e4202e1965fb56b504b83c1e65456cefac363ea3e63045d741fce
+size 5598

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb20a334e63fcedd4e934ce03976286990a9087a15b98001cf943e72a8df26f5
+oid sha256:51e9e940e2056f53df545b821f8946ce63f4ded8bafc5a28b604f2c3fa46333e
 size 5176