Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": 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": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0e375273bd791312abdf5466ecd78c7f2fc552b9f9225a619d58b60ff41b25
+size 1444566873

runs/May20_23-52-49_c1f36c566f73/1653090797.2081466/events.out.tfevents.1653090797.c1f36c566f73.80.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72823f36eb34a17c01bc5f41519c841768a6b79a86d38871531c42dc5d8a3cd2
+size 5163

runs/May20_23-52-49_c1f36c566f73/events.out.tfevents.1653090797.c1f36c566f73.80.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c213c4afeaa3e5a7627e238123fff658244e00ce0b3e89d21042879a23a1561
+size 3812

runs/May20_23-54-47_c1f36c566f73/1653090900.9233518/events.out.tfevents.1653090900.c1f36c566f73.305.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d67cd6b03ee3542147e2885c223ac46abb3b13746e6b9c16d1e2d7cf82b527
+size 5163

runs/May20_23-54-47_c1f36c566f73/events.out.tfevents.1653090900.c1f36c566f73.305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04c7de85e57029595a6af84708cd74e51f7e10eb981244a678c39ee3992a4d5
+size 3813

runs/May20_23-59-23_c1f36c566f73/1653091176.6905553/events.out.tfevents.1653091176.c1f36c566f73.509.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37352149c8315c7f1e28fc77e6b2964b55e0a8be0e1e5d9ba681bf2584013a5
+size 5163

runs/May20_23-59-23_c1f36c566f73/events.out.tfevents.1653091176.c1f36c566f73.509.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279bac94dae30d2b5301cff8bf072905d7cd58ff0f7341f276c6ea3bb232edec
+size 3968

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc68ba3fa508c568d4ae351eca153be58cbaa1263535d9470efb09e630fe9e0
+size 3183