Saving weights and logs of step 25

config.json

@@ -0,0 +1,36 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.0,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

events.out.tfevents.1626178471.t1v-n-905ccd3e-w-0.30006.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4b26d39bdf4b0db002f981e15cd81832e2e6eb910517a96dc5229250dc1ef8
+size 367772

events.out.tfevents.1626181176.t1v-n-905ccd3e-w-0.32209.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412077a9c1abb03ab4f057f191545636d56936064cb720214e9a1496b40d800c
+size 40

events.out.tfevents.1626181508.t1v-n-905ccd3e-w-0.34657.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6616379b6dc7b2ce6eb7513365b138630a72bbbbef8e78cdfd020c2becafb59
+size 40

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d317a9c8273d7bffdcd3acac84d73a4e0808140a57ce9b4ae89806e757e2e41
+size 497764120

make_config.py

@@ -0,0 +1,6 @@
+from transformers import GPT2Config
+
+model_dir = "./swe-gpt-wiki" # ${MODEL_DIR}
+
+config = GPT2Config.from_pretrained("gpt2", resid_pdrop=0.0, embd_pdrop=0.0, attn_pdrop=0.0)
+config.save_pretrained(model_dir)