Training in progress, step 40

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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15417bdc83d9e24373177fe858857dbbc2a6bc0f4711d3271c647b933387c4f2
+size 327657928

runs/Dec10_16-56-23_dea6ac3cbb2a/events.out.tfevents.1733849791.dea6ac3cbb2a.764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995ddf698df60da91015cbd7fabec96a569a6d5d4df69f986ca8c98b0bc568e4
+size 5655

runs/Dec10_16-58-36_dea6ac3cbb2a/events.out.tfevents.1733849917.dea6ac3cbb2a.764.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8925a9c8f897417a637edac1dda253065a9f4f1803a82276fcc35b9ec0484ae6
+size 7783

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4570d00ab4685d1e8e26cc24430a4ef6d9bfd91295abe8095a56863220d7338
+size 5304