Add model

config.json

@@ -0,0 +1,40 @@
+{
+  "_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,
+  "max_length": 512,
+  "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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "max_length": 512,
+  "transformers_version": "4.31.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df89e55cf6868d401ad20ca71949411c591660f28f001261bda1b626f5c4790
+size 1384581

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6b013f46b045747861457117714384172b61092c169466468f8561fe7778bc
+size 497807197

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb0108a1e50c6b0d24ddba383250004950c4cb216d5e80491253222ae96da37
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227b6fc98e72e825fc7cb2707e3d2e4916c6a423fe8d00e2abd407f878fb8fe6
+size 627

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": 0.8317058086395264,
+  "best_model_checkpoint": "output/gpt2-multiquestions/checkpoint-1636",
+  "epoch": 2.0,
+  "global_step": 1636,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.777506112469438e-05,
+      "loss": 0.4879,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8343050479888916,
+      "eval_runtime": 2.343,
+      "eval_samples_per_second": 213.404,
+      "eval_steps_per_second": 26.889,
+      "step": 818
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.555012224938876e-05,
+      "loss": 0.4298,
+      "step": 1000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.332518337408312e-05,
+      "loss": 0.3909,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8317058086395264,
+      "eval_runtime": 2.381,
+      "eval_samples_per_second": 209.994,
+      "eval_steps_per_second": 26.459,
+      "step": 1636
+    }
+  ],
+  "max_steps": 4090,
+  "num_train_epochs": 5,
+  "total_flos": 2562490957824000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ea54f10bee7c263a9c6c25683e2e9b93c8db8e8ee08e0adba91e1bafe0b2ab
+size 3963