End of training

README.md

@@ -8,6 +8,12 @@ tags:
 - diffusers
 - textual_inversion
 - diffusers-training
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+- diffusers-training
 base_model: runwayml/stable-diffusion-v1-5
 inference: true
 ---

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb22100d6b5189ce8491b9e15ae328c9729a9a9f29e47ea21c7106722636260
-size 492268240
+oid sha256:1351a55c93c53cd409f77fb646070f4ca77403c931f39ee34e817b82b327799e
+size 492268952

checkpoint-1000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079b06fd59ca1fefc2b56352c39c2e777c95ad6b67b78e9ba616e2d7070077d1
+oid sha256:a805b04b45027d272aad5b2f21500dddc50333285534bb289808e2cce1418b7f
 size 303570914

checkpoint-1000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c072939cfb24d694d4be71201664e06c5e18977e002867e79a601b41789fdb0
+oid sha256:97daea2a4503e4aed486cdc1c86226f85202cd4ec1e5e5779fdff90216df4792
 size 15124

checkpoint-1000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0d829441992ff2ab1f7502a3a94afc011706461052e42e18e5b963678527c4
+oid sha256:76821af0fdb32e3f19270e410db4daed3d905717577593ac24dd05143d81886e
 size 1000

checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815797063c4b40d30499945e3cfe9ac4394d82adbb9299ba1292eade29d578d3
-size 492268240
+oid sha256:08a6cf1323cab7bb95ff3efc3001401abf5bc8131514597edee28f0041facb25
+size 492268952

checkpoint-1500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a994767c9415e65830f1151ff250ba5e2e6f941d3229a118e6d73a5edba09d1b
+oid sha256:bf1fd8741defceca336bd9d1d7a1ff24ffda73857e8e3ee6f323bba669d4e28e
 size 303570914

checkpoint-1500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38271f25110697834cb3e24f81ef6ac3ad516ff5c15bfc3e403d149298a546e1
-size 15060
+oid sha256:94ad94cbe7ce5f7ee44ff2d3e907799470bc877be2894751209399870fd4f635
+size 15124

checkpoint-1500/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0746407d5e6c8d929c4e940db747c88272550cab75cfb856468297d71d7802ca
+oid sha256:f516ad5468f03f56a944ca66b4817da8b9af1a6647f8cd7f666ce71d3c0833e7
 size 1000

checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8768b7a7ed1b3b0ff8f0efa01ef11c0bc7a4aabe580297f690b460ffd265f7d
-size 492268240
+oid sha256:5a15b6eba6752eb3c759e5e684e2e578c9874b8d68caa43a9598ff39534980d5
+size 492268952

checkpoint-2000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f8e5ff0dead6ed7851e1e4c0d80d8b5c336d466bb75ff0a9a3144958892398
+oid sha256:637890490fec525bdabe70ed435e0a1d019c8ce4ba59c715e7672971585dc3c5
 size 303570914

checkpoint-2000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1d67ab4bae44d8194b7a47825150236ac7666685423a1832cb57b50e504df1
-size 15060
+oid sha256:7eb38f7f2fb54d46f480089357cf9b5d5b716f470582a6b77a555501f392ce9b
+size 15124

checkpoint-2000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5484c6ff4bca55d86f0d54575371a1f3b26246b4ff863161800c9be8539d8c77
+oid sha256:e9be685bdb49b9911fb7d9a6ca4439f26664c681cbd5c6694ce908b13a0cdec6
 size 1000

checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe7587b5477d13b767a2e313a5951b4d14d754ffb09e9cc4ad39368b5939940
-size 492268240
+oid sha256:68b0c77a17effb63b822913320e2ab9e15d92afb7cfdff2f16dc8014c4e2b109
+size 492268952

checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5cbe976d3f83e8f7e1e60406b0b3dbfdb265c8c98c0884b3d767e85c553215
+oid sha256:83e453dd8a79e5819eb3862b2e6c6c4c9503a79f130109883a3d4947424f56fe
 size 303570914

checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e2b64f65bfb48ad6f912ff036aaabb48f2d7a5de836dd22128137ef232f0fb
+oid sha256:d53b3e3beefefa265325953ea279119ebbd6e3236157e63df819761a51dcb3e9
 size 15124

checkpoint-500/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cad514bb36617120f19b7cde3b36a22bc8becf6cc6cfb2166811645c215cccb
+oid sha256:c7115382e2fcdb8f40cd76a0514e9c1ce9a9384121abbed239ca23efe95e4919
 size 1000

feature_extractor/preprocessor_config.json

@@ -8,6 +8,7 @@
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
     0.48145466,
     0.4578275,

learned_embeds-steps-1000.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71d14f4f5decdd57bcfcb064c0510664daa50a6a7867ef2952f435a1c88dc36
-size 3184
+oid sha256:80035df587d14b2b4ae8079f5c48a9e87a0618703f94ab92d16c60c684e62107
+size 3192

learned_embeds-steps-1500.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e964964454c4a2ac58aa46d530a78518b377f6eb31a633170ce6e832f941ab
-size 3184
+oid sha256:4b5b9a73a9798962b5d33ee9fd4777266b0d1daab4b0016b5c0e99bfb53ee46f
+size 3192

learned_embeds-steps-2000.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9ad912475684bc90aa935becf62dee138888ec221b12b0e3ddd8d912ad4f45
-size 3184
+oid sha256:000cac0fff109f4409bd06dc26e399de58144ae2db984b87994a7ce8a40e72f6
+size 3192

learned_embeds-steps-500.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e47045d5ac992495f5271430d701990d44bb187008fcdbdb3b321be29f3ddd8
-size 3184
+oid sha256:e6d726db9b92840ccc586e0cc1ac207eebcc59c79b7221fe8c42291995c10c54
+size 3192

learned_embeds.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c590d9109aa754a1f19757f216fab90db9356be04185b768adc899e7386aae1
-size 3184
+oid sha256:000cac0fff109f4409bd06dc26e399de58144ae2db984b87994a7ce8a40e72f6
+size 3192

logs/textual_inversion/1710833904.3659587/events.out.tfevents.1710833904.slabgpu07.3107370.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fade829cefda2e2ceb399486d42962053b2acafde5187618df338de2c0d2981
+size 2355

logs/textual_inversion/1710833904.3781576/hparams.yml

@@ -0,0 +1,48 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: cat
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 2000
+mixed_precision: bf16
+no_safe_serialization: false
+num_train_epochs: 32
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat2
+placeholder_token: <benchmark-cat>
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: ./benchmark_dataset/pet_cat1
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/textual_inversion/events.out.tfevents.1710833904.slabgpu07.3107370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c0783612045dd1d206d9427465013369b61f460422fe30998bf7fc8326d2cd
+size 665854

safety_checker/config.json

@@ -1,4 +1,5 @@
 {
+  "_commit_hash": "1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9",
   "_name_or_path": "/mnt/slurm_home/jxjiang/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
@@ -8,21 +9,160 @@
   "model_type": "clip",
   "projection_dim": 768,
   "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
     "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
     "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
     "model_type": "clip_text_model",
-    "num_attention_heads": 12
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": null,
   "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
     "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
     "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 24,
-    "patch_size": 14
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
   }
 }

safety_checker/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
-size 1215979664
+oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
+size 1215981832

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.29.2",
   "vocab_size": 49409
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:560b204d9a6aeb9b36553cd1cf60ff5903c791e52f15d884c39dd2e48f96a2be
-size 492268240
+oid sha256:5a15b6eba6752eb3c759e5e684e2e578c9874b8d68caa43a9598ff39534980d5
+size 492268952

tokenizer/added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<cat-toy>": 49408
+  "<benchmark-cat>": 49408
 }

tokenizer/tokenizer_config.json

@@ -1,38 +1,33 @@
 {
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49408": {
-      "content": "<cat-toy>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
   },
-  "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27cd69d4a0aa32105087a619f32a51bc087e133be93fe23da92f3c0bcc07d79
-size 3438167536
+oid sha256:8b97572ccea4b162ef98e0dbcf78041de75721a56f1efba795cb55195ff4777a
+size 1719125992

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
-size 334643268
+oid sha256:0f3f3f38d1393f412ccfbd044b4920b7aee74c520dc01436fac38e456bf83d5e
+size 167335590