Training in progress, step 500

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "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": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308ee411af9ff5116ac3ca1fae089f5c30d7fc30b047287132dbe0554c59a30d
+size 327657928

runs/Feb19_08-23-50_7fcf0257d693/events.out.tfevents.1739953433.7fcf0257d693.819.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126a65216e59875e1b0201b52c062c0a80273891786236f788089dd24a0c204b
+size 9122

runs/Feb19_08-23-50_7fcf0257d693/events.out.tfevents.1739955060.7fcf0257d693.819.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9715df81fcaa45efc864eea44b237c33f643a1454c9a1a93ce5a89ddb87d9e3
+size 359

runs/Feb19_08-55-18_7fcf0257d693/events.out.tfevents.1739955319.7fcf0257d693.819.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4521d52d44ec1f868b52ca2dc8e9c43fc8b3655b51804460ad4a53c1d9caf1
+size 5892

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab9f49e1306a1aa8ba27c711ee5c260ea0f6de9aeb96b06b16c181512c3b0fa
+size 5368