Super-squash branch 'main' using huggingface_hub

Co-authored-by: SFconvertbot <SFconvertbot@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,87 @@
+---
+tags:
+- generated_from_trainer
+- stable diffusion
+- beautiful
+- masterpiece
+datasets:
+- Gustavosta/Stable-Diffusion-Prompts
+model-index:
+- name: tiny-gpt2-magicprompt
+  results: []
+widget:
+ - text: "morning sun over Jakarta"
+   example_title: "morning sun"
+ - text: "WARNING: pip is"
+   example_title: "pip"
+ - text: "sentient cheese"
+   example_title: "sentient cheese"
+ - text: "cheeps are"
+   example_title: "cheeps"
+parameters:
+  min_length: 32
+  max_length: 64
+  no_repeat_ngram_size: 1
+  do_sample: True
+---
+
+
+# tiny-gpt2-magicprompt
+
+
+~~Generate/augment your prompt, stable diffusion style.~~ Enter a new dimension of creativity
+
+This model is a fine-tuned version of [sshleifer/tiny-gpt2](https://huggingface.co/sshleifer/tiny-gpt2) on the Gustavosta/Stable-Diffusion-Prompts dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.7918
+- perplexity: 48618.8756
+
+## Intended uses & limitations
+
+???
+
+## Training and evaluation data
+
+refer to the `Gustavosta/Stable-Diffusion-Prompts` dataset.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 10.8201       | 0.96  | 16   | 10.8191         |
+| 10.8167       | 1.96  | 32   | 10.8145         |
+| 10.8117       | 2.96  | 48   | 10.8095         |
+| 10.8058       | 3.96  | 64   | 10.8025         |
+| 10.7997       | 4.96  | 80   | 10.7989         |
+| 10.7959       | 5.96  | 96   | 10.7947         |
+| 10.7934       | 6.96  | 112  | 10.7925         |
+| 10.7924       | 7.96  | 128  | 10.7919         |
+| 10.7921       | 8.96  | 144  | 10.7918         |
+| 10.792        | 9.96  | 160  | 10.7918         |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 9.96,
+    "eval_loss": 10.791767120361328,
+    "eval_runtime": 5.99,
+    "eval_samples": 444,
+    "eval_samples_per_second": 74.123,
+    "eval_steps_per_second": 18.531,
+    "perplexity": 48618.875553525686,
+    "train_loss": 11.18234748840332,
+    "train_runtime": 256.0921,
+    "train_samples": 8516,
+    "train_samples_per_second": 332.537,
+    "train_steps_per_second": 0.625
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "sshleifer/tiny-gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 2,
+  "n_head": 2,
+  "n_inner": null,
+  "n_layer": 2,
+  "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,
+      "no_repeat_ngram_size": 2,
+      "repetition_penalty": 4.5,
+      "max_length": 48
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.96,
+    "eval_loss": 10.791767120361328,
+    "eval_runtime": 5.99,
+    "eval_samples": 444,
+    "eval_samples_per_second": 74.123,
+    "eval_steps_per_second": 18.531,
+    "perplexity": 48618.875553525686
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dab14e92b6aed2ecce2f51fe5451cfeac14420af24a5d0ee8820964617851f4
+size 2510830

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f524ede18c754cab273e7799daa996271fe23cdfef14fe89a01e2dad8ad8c8e
+size 2517777

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "sshleifer/tiny-gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--sshleifer--tiny-gpt2/snapshots/5f91d94bd9cd7190a9f3216ff93cd1dd95f2c7be/special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.96,
+    "train_loss": 11.18234748840332,
+    "train_runtime": 256.0921,
+    "train_samples": 8516,
+    "train_samples_per_second": 332.537,
+    "train_steps_per_second": 0.625
+}

trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.962406015037594,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 6.25e-05,
+      "loss": 10.8217,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.995728791936504e-05,
+      "loss": 10.8213,
+      "step": 10
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.947761466636014e-05,
+      "loss": 10.8201,
+      "step": 15
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 10.819129943847656,
+      "eval_runtime": 6.4186,
+      "eval_samples_per_second": 69.174,
+      "eval_steps_per_second": 17.294,
+      "step": 16
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 9.847001329696653e-05,
+      "loss": 12.1716,
+      "step": 20
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.694523495787149e-05,
+      "loss": 10.8181,
+      "step": 25
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 9.491954909459895e-05,
+      "loss": 10.8167,
+      "step": 30
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 10.81454086303711,
+      "eval_runtime": 6.3633,
+      "eval_samples_per_second": 69.775,
+      "eval_steps_per_second": 17.444,
+      "step": 32
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.241456985587868e-05,
+      "loss": 12.1668,
+      "step": 35
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.945702546981969e-05,
+      "loss": 10.8133,
+      "step": 40
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.60784730526531e-05,
+      "loss": 10.8117,
+      "step": 45
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 10.809527397155762,
+      "eval_runtime": 6.247,
+      "eval_samples_per_second": 71.074,
+      "eval_steps_per_second": 17.769,
+      "step": 48
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 8.231496189304704e-05,
+      "loss": 12.1615,
+      "step": 50
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.820664880476256e-05,
+      "loss": 10.8084,
+      "step": 55
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 10.8058,
+      "step": 60
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 10.802533149719238,
+      "eval_runtime": 5.8936,
+      "eval_samples_per_second": 75.335,
+      "eval_steps_per_second": 18.834,
+      "step": 64
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 12.1538,
+      "step": 65
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.426681121245527e-05,
+      "loss": 10.802,
+      "step": 70
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 5.924722336357793e-05,
+      "loss": 10.8007,
+      "step": 75
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 10.7997,
+      "step": 80
+    },
+    {
+      "epoch": 4.96,
+      "eval_loss": 10.798870086669922,
+      "eval_runtime": 6.2383,
+      "eval_samples_per_second": 71.174,
+      "eval_steps_per_second": 17.793,
+      "step": 80
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 4.8966654938622295e-05,
+      "loss": 12.148,
+      "step": 85
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 4.381536843653262e-05,
+      "loss": 10.7968,
+      "step": 90
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 3.87300721992097e-05,
+      "loss": 10.7959,
+      "step": 95
+    },
+    {
+      "epoch": 5.96,
+      "eval_loss": 10.794721603393555,
+      "eval_runtime": 6.3176,
+      "eval_samples_per_second": 70.28,
+      "eval_steps_per_second": 17.57,
+      "step": 96
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 3.3765026539765834e-05,
+      "loss": 12.1442,
+      "step": 100
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 2.8973208692864624e-05,
+      "loss": 10.7943,
+      "step": 105
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 2.4405747545519963e-05,
+      "loss": 10.7934,
+      "step": 110
+    },
+    {
+      "epoch": 6.96,
+      "eval_loss": 10.792530059814453,
+      "eval_runtime": 6.3054,
+      "eval_samples_per_second": 70.416,
+      "eval_steps_per_second": 17.604,
+      "step": 112
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 2.0111378089837956e-05,
+      "loss": 12.1419,
+      "step": 115
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 10.7926,
+      "step": 120
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 1.2521795812943704e-05,
+      "loss": 10.7924,
+      "step": 125
+    },
+    {
+      "epoch": 7.96,
+      "eval_loss": 10.791926383972168,
+      "eval_runtime": 5.785,
+      "eval_samples_per_second": 76.75,
+      "eval_steps_per_second": 19.187,
+      "step": 128
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 9.307564136490254e-06,
+      "loss": 12.1411,
+      "step": 130
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 6.527522369181655e-06,
+      "loss": 10.7921,
+      "step": 135
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 10.7921,
+      "step": 140
+    },
+    {
+      "epoch": 8.96,
+      "eval_loss": 10.79179859161377,
+      "eval_runtime": 6.2936,
+      "eval_samples_per_second": 70.548,
+      "eval_steps_per_second": 17.637,
+      "step": 144
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 2.3837118562592797e-06,
+      "loss": 12.1411,
+      "step": 145
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 1.064157733632276e-06,
+      "loss": 10.792,
+      "step": 150
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 2.667509943378721e-07,
+      "loss": 10.792,
+      "step": 155
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 0.0,
+      "loss": 10.792,
+      "step": 160
+    },
+    {
+      "epoch": 9.96,
+      "eval_loss": 10.791767120361328,
+      "eval_runtime": 5.8131,
+      "eval_samples_per_second": 76.379,
+      "eval_steps_per_second": 19.095,
+      "step": 160
+    },
+    {
+      "epoch": 9.96,
+      "step": 160,
+      "total_flos": 39596851200.0,
+      "train_loss": 11.18234748840332,
+      "train_runtime": 256.0921,
+      "train_samples_per_second": 332.537,
+      "train_steps_per_second": 0.625
+    }
+  ],
+  "max_steps": 160,
+  "num_train_epochs": 10,
+  "total_flos": 39596851200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9898973cea8c762a9cf27d5d9600cb8f1d87e0fa027798e8e32396be472be2
+size 3387