Training in progress, step 22

.gitignore

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

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "hidden_dropout_prob": 0.1,
+  "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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50259
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9f1e42e742a7b6686491fef6378389928d38a91ef847e686030a667e73b662
+size 497813341

runs/Aug02_10-04-48_80bf4485fa1d/events.out.tfevents.1690970699.80bf4485fa1d.356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed36d342a7b888008b3eb559503e95d31331e31c05b6d62038d9367c5bd4ceea
+size 4184

runs/Aug02_10-06-03_80bf4485fa1d/events.out.tfevents.1690970768.80bf4485fa1d.356.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03a173ff49c8ee4f61a359075c6c43e07cb0d73e1604c037cf1299f69882a32
+size 4184

runs/Aug02_10-06-45_80bf4485fa1d/events.out.tfevents.1690970815.80bf4485fa1d.1608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b82c14e86e4b9f944ba8095fcf63e05562f301400c8203c633e90d6804d93e
+size 4184

runs/Aug02_10-08-01_80bf4485fa1d/events.out.tfevents.1690970887.80bf4485fa1d.2019.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1670012486bd49c260ef0576db1772d192e12d122c83ac9b80ac582f8c7cf1
+size 4184

runs/Aug02_10-09-32_80bf4485fa1d/events.out.tfevents.1690970979.80bf4485fa1d.2558.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73e1c170b30fa46296c8b7e9dc4700683e5900b7c8bd51075352c7bf438a398
+size 4316

runs/Aug02_10-14-15_80bf4485fa1d/events.out.tfevents.1690971262.80bf4485fa1d.3818.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8f3cdc1e62ce5569bf9e654fac15d36160ca529691aa5fcba34519346ee3d7
+size 4470

runs/Aug02_10-24-08_80bf4485fa1d/events.out.tfevents.1690971857.80bf4485fa1d.6428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11920ad1f584628bcb89f44defc9942058393d69383393aebe386acba290860b
+size 4736

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddebe2322dc1a0a1812ac79e8fbdbd59902747fd73b72346b75ef56bad8d071
+size 3963