Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "gpt2-xl",
+  "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": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43b27d6dbea8d9bafa0fa3a3e69152f72e1f150c5866c976f3e74d4ab4772c8
+size 6281011243

runs/Jan16_12-31-33_tiger4.stanford.edu/1673901102.5699794/events.out.tfevents.1673901102.tiger4.stanford.edu.3075041.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a584398dd2db3ab023eeefee59d742efc82738ae7a2ab26c1007d4ebf95ffc10
+size 5636

runs/Jan16_12-31-33_tiger4.stanford.edu/events.out.tfevents.1673901102.tiger4.stanford.edu.3075041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786f5193a70ee2c695c001f21babbdfd2c511bff3cce95462105a9163af6cfe4
+size 4274

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fd8472f5131a20543bbbbf13de95c559f2ae92ac06fb28a2dec6f6b0afa678
+size 3503