Initial commit

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a68d7a96296315d82ffa37673350ebf8ed7fab517934c70376caf38ec1fa29
+size 655345093

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4eae6d1a9199b8d09636ddea4aacbfb271b56b1b0c09fb587bd3bcf368fed8
+size 327674773

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d753057c95ba4248db37ad243569f0a33445eb8ab2781d3d4be2470e09b6cc25
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c08de7b4d5c9e2749ef223dc382334259c225aad16daee189a12ff56c02c38
+size 627

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.042549796558785206,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-05,
+      "loss": 3.1705,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9777399852193505e-05,
+      "loss": 2.5041,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.955479970438701e-05,
+      "loss": 2.3883,
+      "step": 1500
+    }
+  ],
+  "max_steps": 112809,
+  "num_train_epochs": 3,
+  "total_flos": 1672299203788800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9de51afc8ccea9a7116789d2ff41645c5a8cacdb2cbca8e4fc740875eb5a3a4
+size 3899