Initial commit

config.json

@@ -0,0 +1,43 @@
+{
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "transformers_version": "4.2.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7459b9c013bd629e08ab34027b8a76c7c78f8cefb09dd8d64551d4aca7c7717
+size 655348359

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa4c69269df4af37801936db950ae88afc3d32b07d831dfef1b1a35e9e9d922
+size 333975623

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cba18a04b558db998d9950866adb595ee0952c7c7bc9600553a090ac3b4803
+size 623

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9910464083111202,
+  "global_step": 14500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.977217323946871e-05,
+      "loss": 3.4122,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9544346478937417e-05,
+      "loss": 3.3784,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9316519718406125e-05,
+      "loss": 3.3481,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9088692957874832e-05,
+      "loss": 3.3364,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.886086619734354e-05,
+      "loss": 3.3282,
+      "step": 2500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.863303943681225e-05,
+      "loss": 3.3188,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.840521267628096e-05,
+      "loss": 3.3164,
+      "step": 3500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8177385915749666e-05,
+      "loss": 3.3237,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7949559155218374e-05,
+      "loss": 3.3041,
+      "step": 4500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.772173239468708e-05,
+      "loss": 3.2969,
+      "step": 5000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.749390563415579e-05,
+      "loss": 3.3079,
+      "step": 5500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.7266078873624497e-05,
+      "loss": 3.2821,
+      "step": 6000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7038252113093204e-05,
+      "loss": 3.2939,
+      "step": 6500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6810425352561915e-05,
+      "loss": 3.2861,
+      "step": 7000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.658259859203062e-05,
+      "loss": 3.2938,
+      "step": 7500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.635477183149933e-05,
+      "loss": 3.2831,
+      "step": 8000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6126945070968035e-05,
+      "loss": 3.2811,
+      "step": 8500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5899118310436746e-05,
+      "loss": 3.2798,
+      "step": 9000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5671291549905454e-05,
+      "loss": 3.2675,
+      "step": 9500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.544346478937416e-05,
+      "loss": 3.2738,
+      "step": 10000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5215638028842869e-05,
+      "loss": 3.2673,
+      "step": 10500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4987811268311577e-05,
+      "loss": 3.2651,
+      "step": 11000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4759984507780286e-05,
+      "loss": 3.2829,
+      "step": 11500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.4532157747248993e-05,
+      "loss": 3.2623,
+      "step": 12000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4304330986717701e-05,
+      "loss": 3.2607,
+      "step": 12500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4076504226186409e-05,
+      "loss": 3.2648,
+      "step": 13000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.3848677465655116e-05,
+      "loss": 3.2718,
+      "step": 13500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3620850705123824e-05,
+      "loss": 3.2582,
+      "step": 14000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3393023944592533e-05,
+      "loss": 3.2499,
+      "step": 14500
+    }
+  ],
+  "max_steps": 43893,
+  "num_train_epochs": 3,
+  "total_flos": 7297427570688000,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4ba9681ac31f3fc0b7ab5d21b6aa905c707a9d1de1bc45b696b0b31cb0513f
+size 2031