Training in progress, step 61875

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": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/events.out.tfevents.1724885162.d9703cfffc0c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec49a8bb57039baa1e12d739d11fc4be2ad394cee7846055031c49fa3601c4cd
+size 5629

logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/events.out.tfevents.1724885340.d9703cfffc0c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2eaf8fab08b7627ff90024ee53fd3a7f8a3e16f6972488232bfafcd723e6b54
+size 5629

logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/events.out.tfevents.1724885537.d9703cfffc0c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fe7e2f73f38c29a142d245df3a58c623b20176b5b5befdb9bf60abd6e63ad8
+size 7288916

logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/events.out.tfevents.1724887754.d9703cfffc0c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fcf0b073af16fef68fe99d1b86de1c0e2f820d353086e0c6666046a59c1432
+size 29625351

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cf0df0a59fbf4feec70697b022087bbb7d0006f8855a74e4bc64a8012575fe
+size 248894656

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146fd7de077926ff060437708ca8699049b38a4be7b4e1e7c63e77c3f2079889
+size 5496