Upload 10 files

README.md

@@ -1,3 +1,40 @@
 ---
-license: agpl-3.0
+tags:
+- generated_from_trainer
+model-index:
+- name: pythia-70m-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-70m-deduped-aid
+
+## Model description
+
+This model is a finetune of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) (from when it was instead `pythia-19m-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 and was intended for use with KoboldAI. A temperature of `0.5` and a repetition penalty of `1.01` were tested.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- 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": 2.7053030034203553,
+    "train_runtime": 2600.5654,
+    "train_samples": 6682,
+    "train_samples_per_second": 7.708,
+    "train_steps_per_second": 1.928
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "EleutherAI/pythia-19m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "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 sha256:8f949f4a07d0e6a57a76207ee4a55ab4ee6d203a2f81997a43a48fab9438ef8a
+size 306903691

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-19m-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": 2.7053030034203553,
+    "train_runtime": 2600.5654,
+    "train_samples": 6682,
+    "train_samples_per_second": 7.708,
+    "train_steps_per_second": 1.928
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5013,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.501296628765211e-05,
+      "loss": 3.2601,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.002593257530421e-05,
+      "loss": 3.0867,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.5038898862956315e-05,
+      "loss": 2.9927,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.005186515060842e-05,
+      "loss": 2.8095,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.506483143826052e-05,
+      "loss": 2.6831,
+      "step": 2500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0077797725912628e-05,
+      "loss": 2.6323,
+      "step": 3000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.5090764013564732e-05,
+      "loss": 2.5364,
+      "step": 3500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0103730301216837e-05,
+      "loss": 2.3822,
+      "step": 4000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.116696588868941e-06,
+      "loss": 2.35,
+      "step": 4500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.296628765210453e-07,
+      "loss": 2.332,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "step": 5013,
+      "total_flos": 5501794620801024.0,
+      "train_loss": 2.7053030034203553,
+      "train_runtime": 2600.5654,
+      "train_samples_per_second": 7.708,
+      "train_steps_per_second": 1.928
+    }
+  ],
+  "max_steps": 5013,
+  "num_train_epochs": 3,
+  "total_flos": 5501794620801024.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551c877e293b5ce3197b9d2dbe0c895398d804a7e12af6ffa2f9355b1e8d97b4
+size 3515