Training in progress, step 500

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355e8ea474d0728b2d4116e1e1679980a9a36bd9251961831750972e1c2eba84
+size 497774208

runs/Apr30_01-40-51_f824684a92d7/events.out.tfevents.1714441273.f824684a92d7.292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3102589c45e6cdf1390a85f2552a3474f9c40be07f2bd9ad4d0c068106f1bc
+size 4912

runs/Apr30_01-42-27_f824684a92d7/events.out.tfevents.1714441353.f824684a92d7.292.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1a6c06e660bd5c973744817f366ad8d8a38d33c72a70b837294f44c7c9a393
+size 4911

runs/Apr30_01-42-56_f824684a92d7/events.out.tfevents.1714441380.f824684a92d7.292.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06278f9a3ebb1599cbb027c855c45aded7560fb29d0a1dc0aa5c960e18d1bd5
+size 5121

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c9b6b13dffa88f1a594738ca6cbd74c6b614661a4a62e9c411481798032c37
+size 4984