Training in progress, epoch 1

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 128,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d2a8e5326622bec8f0ae742cff761b312f466046b39cd79d73628a9efb579f
+size 324905416

runs/Feb18_21-24-52_nlp-gpu-02.be.ucsc.edu/events.out.tfevents.1708320293.nlp-gpu-02.be.ucsc.edu.29444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693714bfdb0bcad6817e9ec767f2bba5345179c6f8ce265f0a16453b130c799c
+size 6856

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4927e364b3fe02e0ab04555c2b443d90c2512771e2794b8229e9fcced91a4558
+size 4728