Training in progress, step 500

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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55078f6f03e5909b09d94ded3a277f93d89413019af94ec562accc1bf133d7c0
+size 497774208

runs/Feb02_06-53-03_4be8609535f5/events.out.tfevents.1706856804.4be8609535f5.680.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad6a893329e058d3341e55a6ada3aad0603918167eab2ff1c68ecdca0a57e54
+size 4406

runs/Feb02_07-17-21_4be8609535f5/events.out.tfevents.1706858247.4be8609535f5.680.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ca9110c5014664f199a18fa9241f5c5fa6bd9969e9fc1f53299729effa345c
+size 4406

runs/Feb02_07-21-53_4be8609535f5/events.out.tfevents.1706858518.4be8609535f5.680.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bd38c86308ba5601bb66a7bb65a85e9c33342bf9b0a7bb04fdaebf5a1fb456
+size 4563

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d215ad59f54612f23b7fa21bda7061b0607514f18b241585f09522707e1cb1d
+size 4536