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": "4.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757ff479349d1098edcf12d42d895641f212e84fef8265bf87784e2595b4fa90
+size 510403817

runs/Jan10_23-25-21_amax/1641828359.8199317/events.out.tfevents.1641828359.amax.278216.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa8bbe5d3d8266a891db535fd5ef2cab6318db1543d1d580d9feea0941430ac
+size 4711

runs/Jan10_23-25-21_amax/1641828801.5425813/events.out.tfevents.1641828801.amax.278216.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f45b7d58edcf0c5ce6d9bb9dfd088f0634fe2903d1354c0a69bacf34de3970
+size 4711

runs/Jan10_23-25-21_amax/events.out.tfevents.1641828359.amax.278216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b76abf440eeac611aabe89e66029ff2ec4bf74a65ff3e0bfe0c4f47d8d217b
+size 3503

runs/Jan10_23-25-21_amax/events.out.tfevents.1641828801.amax.278216.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323643a050e913a4d485923a25603590296453c6bacebe8c9ae3a37d93f622ab
+size 3503

runs/Jan10_23-44-17_amax/1641829504.8882298/events.out.tfevents.1641829504.amax.305350.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3963e41b79cf96da5dd8e5cf07cb5e4f578552863157db8a375e9fa2c2f412ad
+size 4711

runs/Jan10_23-44-17_amax/events.out.tfevents.1641829504.amax.305350.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb084a8be03fe74aa7b24bf88dc98e08cb707987d5143bad164bbd778e3e90a
+size 4202

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98460a12e9ad8af9037cf3f5f2fed615e55cd14220c07125564fc81f83bbe581
+size 2927