Initial commit

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "dbmdz/german-gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 52000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 52000,
+  "gradient_checkpointing": false,
+  "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,
+  "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": 52000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4552f9f917e257a00050ef225526ae54cd3308d49e380de933294109754b308e
+size 1006320279

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687b0f9bd63e0e933c7593fb0757d3533282397c9f5f3db6d5c42e99c2ff7181
+size 515762811

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11755783d41a03b52b62fcfc991d5f2d83c48ec66e9368f3be434c9f86e1bebc
+size 623

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9382957884427032,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 5e-05,
+      "loss": 4.8251,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.787270251872022e-05,
+      "loss": 4.4562,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.574540503744044e-05,
+      "loss": 4.3579,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.3618107556160655e-05,
+      "loss": 4.2909,
+      "step": 2000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.149081007488088e-05,
+      "loss": 4.2459,
+      "step": 2500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.936351259360109e-05,
+      "loss": 4.2102,
+      "step": 3000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.723621511232131e-05,
+      "loss": 4.1895,
+      "step": 3500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.510891763104153e-05,
+      "loss": 4.1604,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.2981620149761745e-05,
+      "loss": 4.044,
+      "step": 4500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.085432266848196e-05,
+      "loss": 4.0203,
+      "step": 5000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.872702518720218e-05,
+      "loss": 4.0172,
+      "step": 5500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.6599727705922394e-05,
+      "loss": 4.0025,
+      "step": 6000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.4472430224642616e-05,
+      "loss": 3.9855,
+      "step": 6500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.234513274336283e-05,
+      "loss": 3.9791,
+      "step": 7000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.021783526208305e-05,
+      "loss": 3.9777,
+      "step": 7500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.809053778080327e-05,
+      "loss": 3.9665,
+      "step": 8000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5963240299523484e-05,
+      "loss": 3.903,
+      "step": 8500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3835942818243706e-05,
+      "loss": 3.8656,
+      "step": 9000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1708645336963923e-05,
+      "loss": 3.8674,
+      "step": 9500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 9.58134785568414e-06,
+      "loss": 3.8754,
+      "step": 10000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.4540503744043575e-06,
+      "loss": 3.8795,
+      "step": 10500
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.326752893124575e-06,
+      "loss": 3.8656,
+      "step": 11000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.1994554118447927e-06,
+      "loss": 3.8711,
+      "step": 11500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.0721579305650103e-06,
+      "loss": 3.8594,
+      "step": 12000
+    }
+  ],
+  "max_steps": 12252,
+  "num_train_epochs": 3,
+  "total_flos": 37091057394253824,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89eaccee81c0d9c06ce21b08024d4060ece18e6defc73a10d1e1590e43f2015d
+size 2031