Uploaded 10 files.

README.md

@@ -1,3 +1,42 @@
 ---
-license: agpl-3.0
+tags:
+- generated_from_trainer
+model-index:
+- name: pythia-160m-deduped-aid
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pythia-160m-deduped-aid
+
+![Example](https://cdn.discordapp.com/attachments/1042160561808482304/1070428486306631680/Screenshot_2023-02-01_11-40-08.png)
+
+## Model description
+
+This model is a finetune of [EleutherAI/pythia-160m-deduped](https://huggingface.co/EleutherAI/pythia-160m-deduped) (from when it was instead `pythia-125m-deduped`), on the [`text_adventures.txt`](https://github.com/Latitude-Archives/AIDungeon/blob/ca098ca7dab480d24e47954c8873b03ba1091ffc/data/text_adventures.txt) dataset originally intended for AI Dungeon 2. Performance will be very poor, as expected by the small model, and generations may be offensive thanks to its training data.
+
+This model was trained for testing purposes as the successor to [Merry/AID-Neo-125M](https://huggingface.co/Merry/AID-Neo-125M) and was intended for use with KoboldAI. A temperature of `0.5` and a repetition penalty of `1.05` were tested.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.1+cu116
+- Datasets 2.8.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.0144441036196583,
+    "train_runtime": 7319.7453,
+    "train_samples": 6682,
+    "train_samples_per_second": 2.739,
+    "train_steps_per_second": 1.369
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "EleutherAI/pythia-125m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a9b93c1343fee6bcbe12f516a9901c4d9d9cd7dd6056225a56e186b4db2b8e
+size 699685293

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": 1000000000000000019884624838656,
+  "name_or_path": "EleutherAI/pythia-125m-deduped",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.0144441036196583,
+    "train_runtime": 7319.7453,
+    "train_samples": 6682,
+    "train_samples_per_second": 2.739,
+    "train_steps_per_second": 1.369
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 10023,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.75057368053477e-05,
+      "loss": 3.0513,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.501147361069541e-05,
+      "loss": 2.9178,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.25172104160431e-05,
+      "loss": 2.7984,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.0022947221390805e-05,
+      "loss": 2.7266,
+      "step": 2000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.75286840267385e-05,
+      "loss": 2.6317,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.50344208320862e-05,
+      "loss": 2.5775,
+      "step": 3000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.2540157637433905e-05,
+      "loss": 2.3763,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.00458944427816e-05,
+      "loss": 2.0984,
+      "step": 4000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.7551631248129307e-05,
+      "loss": 2.0372,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.5057368053477002e-05,
+      "loss": 1.9558,
+      "step": 5000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2563104858824705e-05,
+      "loss": 1.9287,
+      "step": 5500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0068841664172404e-05,
+      "loss": 1.8788,
+      "step": 6000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7574578469520103e-05,
+      "loss": 1.828,
+      "step": 6500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.5080315274867803e-05,
+      "loss": 1.5557,
+      "step": 7000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2586052080215504e-05,
+      "loss": 1.3987,
+      "step": 7500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0091788885563205e-05,
+      "loss": 1.3584,
+      "step": 8000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.597525690910905e-06,
+      "loss": 1.3404,
+      "step": 8500
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.103262496258605e-06,
+      "loss": 1.3025,
+      "step": 9000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.6089993016063056e-06,
+      "loss": 1.2926,
+      "step": 9500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.147361069540058e-07,
+      "loss": 1.2727,
+      "step": 10000
+    },
+    {
+      "epoch": 3.0,
+      "step": 10023,
+      "total_flos": 1.5233919932694528e+16,
+      "train_loss": 2.0144441036196583,
+      "train_runtime": 7319.7453,
+      "train_samples_per_second": 2.739,
+      "train_steps_per_second": 1.369
+    }
+  ],
+  "max_steps": 10023,
+  "num_train_epochs": 3,
+  "total_flos": 1.5233919932694528e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89162fb42c80994ffb5cf2576404fd1a059f40165b766cdb77b8899ac87d3d5d
+size 3515