Add model.

README.md

@@ -1,3 +1,31 @@
 ---
+language:
+- en
+metrics:
+- accuracy
+co2_eq_emissions:
+      emissions: "10"
+      source: "mlco2.github.io"
+      training_type: "fine-tuning"
+      geographical_location: "West Java, Indonesia"
+      hardware_used: "1 T4"
 license: cc-by-nc-sa-4.0
+widget:
+- text: 'You: "Hey kekbot! What\'s up?"\nKekbot: "'
+  example_title: "Asking what's up"
+- text: 'You: "Hey kekbot! How r u?"\nKekbot: "'
+  example_title: "Asking how he is"
 ---
+> THIS MODEL IS INTENDED FOR RESEARCH PURPOSES ONLY
+# Kekbot Mini
+
+Based on a `distilgpt2` model, fine-tuned to a select subset (65k<= messages) of Art Union's general-chat channel chat history.
+
+### Limits and biases
+As this is trained on chat history, it is possible that discriminatory or even offensive materials to be outputted. 
+Author holds his ground on the fact that ML models are mere statistical representation of the dataset used to train it, 
+and that due to the nature of the dataset it is practically impossible to be certain of 
+the degree of "cleanliness" that the data contained within holds.
+
+Author can confirm, however, that from heuristical testing that the model was not found to be offensive 
+to the author himself, hopefully this opinion stays true for everyone in the audience.

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5450006982265047,
+    "eval_loss": 2.7938177585601807,
+    "eval_runtime": 1.1695,
+    "eval_samples": 28,
+    "eval_samples_per_second": 23.942,
+    "eval_steps_per_second": 3.42,
+    "perplexity": 16.34329560585662,
+    "train_loss": 2.866144816080729,
+    "train_runtime": 358.7849,
+    "train_samples": 527,
+    "train_samples_per_second": 8.813,
+    "train_steps_per_second": 2.207
+}

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": "4.20.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2f62432c7ddfba09749700ec285391d4197d4d1b9dbdcfd381548a31ecc112
+size 333969117

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "distilgpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 792,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.8434343434343433e-05,
+      "loss": 2.936,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "step": 792,
+      "total_flos": 826220325371904.0,
+      "train_loss": 2.866144816080729,
+      "train_runtime": 358.7849,
+      "train_samples_per_second": 8.813,
+      "train_steps_per_second": 2.207
+    }
+  ],
+  "max_steps": 792,
+  "num_train_epochs": 6,
+  "total_flos": 826220325371904.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4a45d2b29115fe42958b26f36eca2a446ea4d40b3afa14281303baeaeecc19
+size 3247