Training in progress, epoch 1

config.json

@@ -0,0 +1,41 @@
+{
+ "_name_or_path": "gpt2",
+ "activation_function": "gelu_new",
+ "architectures": [
+ "GPT2LMHeadModel"
+ ],
+ "attn_pdrop": 0.1,
+ "bos_token_id": 50256,
+ "embd_pdrop": 0.1,
+ "end_token_id": 50256,
+ "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,
+ "pad_token_id": 50256,
+ "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": "4.36.2",
+ "use_cache": false,
+ "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2516a952d42c128c4e32199f7e3c23ba3ae78c4169256f11e7c9f7bfd3e7ebbc
+size 497807706

runs/Dec30_23-45-36_instance-2/events.out.tfevents.1703979981.instance-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875bdcc99a75c07cf577be3e2eae2f777584ac80ac3c0cc17ae13b279fb0dcca
+size 5039

runs/Dec30_23-51-49_instance-2/events.out.tfevents.1703980323.instance-2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b055639bda807e682b0abdc0238f638c6fed2565d271e6fbb5583c210161ecde
+size 7905

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171c14d31c8b047af99e6dbee673d92bc5f4394b131847fdeb229248a454c8b4
+size 4792