Upload 17 files

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/wjn/pre-trained-lm/gpt2-large",
+  "activation_function": "gelu_new",
+  "adapter_choice": "LiST",
+  "adapter_dim": 128,
+  "architectures": [
+    "GPT2ForCausalLM"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "finetuning_task": "causal_instruction",
+  "hidden_dropout_prob": 0.1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "pre_seq_len": 4,
+  "prefix_hidden_size": 512,
+  "prefix_projection": false,
+  "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": "4.21.2",
+  "use_cache": true,
+  "use_freezing": false,
+  "use_prompt_for_cls": false,
+  "vocab_size": 50257
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ceae5cd0dc91d6ae8517fccc5b869670d97adb43d2f17b37143a6d4900eb41b
+size 14657

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd279fc8a9c72e7dfa07120198eebbd16ea2a210fd8f9bfd4cd6aca5c9f111d1
+size 14657

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897cf33adda90d279b7b937123d1419fd7a00a09f42402e7145974707faec98c
+size 14657

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256688de9dbcb9558c4704b68a3f7e33cf07967dc4a33847fe43d603628b6cd6
+size 14657

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01e1d3413f163cd46879bffdd3e0529c1c9f9c99e701a5d443b839c3987c55a
+size 14657

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7c753c6351ca2dc91f1c270f4a68a2dd5a946cf9e6e5eb9fb3903f36c633bb
+size 14657

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cd7bfb82b731f8ba147c89a79c4db79359dbb4eeaf52c1e3bc12229197d778
+size 14657

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7f2ca3293b403b284278c07e37c8358789fe235f2c2b9f582e384d8dca6574
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2e40d1c9788e37be1a2cadba28c2a7a531bda63665f568e994a6dc08c589b3
+size 623

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 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "/wjn/pre-trained-lm/gpt2-large",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,15 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.674298613350532,
+  "global_step": 60000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "max_steps": 62020,
+  "num_train_epochs": 10,
+  "total_flos": 4.17809975840709e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b30b40d28a2980472995459bc0dabb231d4824b7b68d902f8f0e3c34055bad5
+size 3439