Training in progress, step 500

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert/distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "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,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0545be3d74ca349ac10e96b964971bee0c7d7036d4d529f647ff430d73211c1
+size 327657928

runs/May05_20-27-27_DESKTOP-TG6V4R3/events.out.tfevents.1714921047.DESKTOP-TG6V4R3.201880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a6cbaffc2ea99bb06ebbf29cf70912eb9be9671773bbee00d17c3480a8da74
+size 4907

runs/May05_20-34-05_DESKTOP-TG6V4R3/events.out.tfevents.1714921446.DESKTOP-TG6V4R3.201880.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866a093cd8c4283c1f3b4fc49857dd65be814141b61f1849de06bb6b0ab733dc
+size 5118

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508902e8f8fc6c08c98f341a8e4eda2b532621449abff233847f30bc3f71b261
+size 4920