Upload 8 files

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": "4.27.4",
+  "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": "4.27.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fa2a05605aab2e11f861ef17640d2c023a965819a786a5ee7d325c728124e5
+size 655342981

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6bd5575107c868751997c3181c6ab275ee441597b01f1f91588034e0296b22
+size 333968953

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f57bcfbae4c99682d8c5c02dbb6af4a34190d48a4b4b8965716867c8f57131
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597f102a1876ce7b5eccff45979cd35c5efbd5f7c3c6378c74b924f7632225e0
+size 627

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1532816104005033,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.930104144824212e-05,
+      "loss": 2.0398,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.860208289648424e-05,
+      "loss": 1.7138,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.790312434472636e-05,
+      "loss": 1.6022,
+      "step": 1500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.720416579296848e-05,
+      "loss": 1.5263,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6505207241210597e-05,
+      "loss": 1.4804,
+      "step": 2500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5806248689452716e-05,
+      "loss": 1.434,
+      "step": 3000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5107290137694836e-05,
+      "loss": 1.4131,
+      "step": 3500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4408331585936954e-05,
+      "loss": 1.3862,
+      "step": 4000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3709373034179074e-05,
+      "loss": 1.3675,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4010822772979736,
+      "eval_runtime": 3146.6255,
+      "eval_samples_per_second": 11.181,
+      "eval_steps_per_second": 1.398,
+      "step": 4769
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.3010414482421195e-05,
+      "loss": 1.3461,
+      "step": 5000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2311455930663311e-05,
+      "loss": 1.3293,
+      "step": 5500
+    }
+  ],
+  "max_steps": 14307,
+  "num_train_epochs": 3,
+  "total_flos": 1436968817786880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7830e8f39d7a68e67b32d873381b4d836869bb69c5ec3c7779953956adedd94
+size 3579