Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ec2d0997943cef57b55bf320136e23f05d7f79c6225d4c93fbb4ddd76bca19
+size 510398013

runs/Apr23_23-26-18_03a91521804f/1682292407.9841154/events.out.tfevents.1682292407.03a91521804f.227.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2792df79954b6eb12478ca07a583da56b54fb4c478b081d056f7e6fdb67924
+size 5864

runs/Apr23_23-26-18_03a91521804f/events.out.tfevents.1682292407.03a91521804f.227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f18504aff7fb160d91e0ba8e810691f37fbf4ca85e8eb60f6e0d5ca9bf07c2
+size 4223

runs/Apr23_23-28-30_03a91521804f/1682292525.0177407/events.out.tfevents.1682292525.03a91521804f.227.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb140b15272eb542f17c1dd0bb860cb3bb8ebcd711a127310ef0a8c82e30e4f
+size 5864

runs/Apr23_23-28-30_03a91521804f/events.out.tfevents.1682292525.03a91521804f.227.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144908420deec66f9242dba3f48109e4eb0bf2bc441a398911b5c013f937be81
+size 4378

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a69ad133e2c194f570ba9a7797a1a4b7a4f6e5d2bef29acca3563c5d997cc6a
+size 3579