Upload 14 files

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 100.0,
+    "train_loss": 1.7589535874221183,
+    "train_runtime": 26619.1342,
+    "train_samples": 10272,
+    "train_samples_per_second": 38.589,
+    "train_steps_per_second": 2.412
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/wjn/pre-trained-lm/gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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 sha256:461dba1421370dfc18cd73e022e38e19a1edd141b62a26ff9d408967a6489e1a
+size 14657

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53938d26de96cf471f027a3f58878d7ec056237441d4de099ad7d55ee6c6268
+size 14657

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69bb6c547c777da4ba0044fd99a7e3ea9384a509cd2fe8d5a1e88eb454a7a509
+size 14657

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b109fa88750d60b5058cb28e4b3b86b0db00c9f53b7d21fbd98703a664d1f9a1
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e619762d72bd7f53ba56a902ab1bbd372c78c2bc40daeb5fb35fae02de986c12
+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",
+  "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": 93.45794392523365,
+  "global_step": 60000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "max_steps": 64200,
+  "num_train_epochs": 100,
+  "total_flos": 2.508403579677573e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c672acdc99b9a9f1e0e8aa83dc78ad4677645c87fd67da5cfc4c4cb8b623ee1
+size 3439