all model files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "ml6team/gpt2-medium-dutch-finetune-oscar",
+  "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,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.21.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f72c02f7976a1d4968696d76552e39f121c391bf0551bcc9c551e717283a75c
+size 1444566873

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35de88870223780f616932cc3bd78b0d1fb39d8d7bded25042574a7ad725a47c
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77aecd454679862164d5eb8d2932154d0fd7739bee3ed5579936dfee43ded1a1
+size 623

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 65.78947368421052,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 13.16,
+      "learning_rate": 5e-05,
+      "loss": 3.454,
+      "step": 500
+    },
+    {
+      "epoch": 26.32,
+      "learning_rate": 4.519230769230769e-05,
+      "loss": 0.7914,
+      "step": 1000
+    },
+    {
+      "epoch": 39.47,
+      "learning_rate": 4.038461538461539e-05,
+      "loss": 0.1775,
+      "step": 1500
+    },
+    {
+      "epoch": 52.63,
+      "learning_rate": 3.557692307692308e-05,
+      "loss": 0.0932,
+      "step": 2000
+    },
+    {
+      "epoch": 65.79,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.0703,
+      "step": 2500
+    }
+  ],
+  "max_steps": 5700,
+  "num_train_epochs": 150,
+  "total_flos": 9181367241277440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036dc520d9664e8e59a2e09f52de15512c896aef8168c274f067180b7240d12e
+size 3311