Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,140 @@
+{
+  "architecture": "AutoDiffusionLM",
+  "architectures": [
+    "MyDecoderOnlyModel"
+  ],
+  "batch_size": 2,
+  "bias": false,
+  "block_size": "${model.length}",
+  "checkpointing": {
+    "resume_ckpt_path": "${.save_dir}/checkpoints/last.ckpt",
+    "resume_from_ckpt": true,
+    "save_dir": "${cwd:}"
+  },
+  "complex_attention": false,
+  "data": {
+    "output_dir": "./data/pt/huggingface/preprocessed_datasets",
+    "train": "./dataset/da"
+  },
+  "data_path": "./dataset/da",
+  "debug": false,
+  "diffusion": "absorbing_state",
+  "dropout": 0.0,
+  "embedding_type": "default",
+  "eval": {
+    "checkpoint_path": "${cwd:}/checkpoints/last.ckpt",
+    "compute_perplexity_on_sanity": false,
+    "disable_ema": false,
+    "gen_ppl_eval_model_name_or_path": "gpt2-large",
+    "generate_samples": false,
+    "perplexity_batch_size": 8
+  },
+  "flash_attention": false,
+  "hidden_dim": 512,
+  "hydra": {
+    "job": {
+      "chdir": true
+    },
+    "run": {
+      "dir": "./"
+    }
+  },
+  "intermediate_size": 512,
+  "loader": {
+    "batch_size": "${div_up:${.global_batch_size}, ${eval:${trainer.devices} * ${trainer.num_nodes}}}",
+    "eval_batch_size": "${div_up:${.eval_global_batch_size}, ${eval:${trainer.devices} * ${trainer.num_nodes}}}",
+    "eval_global_batch_size": "${.global_batch_size}",
+    "global_batch_size": 512,
+    "num_workers": "${eval:\"len(__import__('os').sched_getaffinity(0))\"}",
+    "pin_memory": true
+  },
+  "max_input_ids_length": 4000,
+  "max_seq_len": 512,
+  "mode": "train",
+  "model": {
+    "custom_model_load_path": "./model/",
+    "deepspeed": null,
+    "kernel_injection": {
+      "enable": true
+    },
+    "length": 512,
+    "offload_optimizer": {
+      "device": "cpu",
+      "pin_memory": true
+    },
+    "offload_param": {
+      "device": "cpu",
+      "pin_memory": true
+    },
+    "pipeline": {
+      "enabled": true,
+      "num_stages": 8,
+      "stage_id": "${LOCAL_RANK}"
+    },
+    "save_dir": "./model",
+    "tensor_parallel": {
+      "enabled": true,
+      "size": 8
+    },
+    "zero_stage": 2
+  },
+  "model_type": "autodiffusion",
+  "multiple_of": 32,
+  "n_layers": 8,
+  "num_attention_heads": 8,
+  "optim": {
+    "beta1": 0.9,
+    "beta2": 0.999,
+    "eps": "1e-8",
+    "lr": "3e-4",
+    "weight_decay": 0
+  },
+  "rope_beta": 10000.0,
+  "rope_scaling_factor": 1.0,
+  "rope_scaling_type": "dynamic",
+  "sampling": {
+    "first_hitting": true,
+    "kv_cache": false,
+    "logdir": "./samples_${algo.name}_len${model.length}_blocksize${block_size}",
+    "noise_removal": false,
+    "nucleus_p": 1.0,
+    "num_sample_batches": 1,
+    "var_length": false
+  },
+  "seed": 42,
+  "tokenizer_cache": "./tokenizer/cache/FacebookAI/xlm-roberta-base",
+  "tokenizer_name": "FacebookAI/xlm-roberta-base",
+  "torch_dtype": "float32",
+  "training": {
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.95,
+    "adam_epsilon": "1e-8",
+    "batch_size": 8,
+    "debug": false,
+    "epochs": 1,
+    "final_path": "./checkpoints/last.ckpt/final_model",
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "gradient_accumulation_steps": 1,
+    "gradient_checkpointing": false,
+    "gradient_checkpointing_kwargs": {},
+    "learning_rate": "1e-4",
+    "learning_rate_decay": 0.0,
+    "log_step": 100,
+    "max_grad_norm": 1.0,
+    "output_path": "./checkpoints/last.ckpt",
+    "seed": 42,
+    "steps_per_epoch": 100,
+    "warmup_steps": 1000,
+    "weight_decay": 0.0
+  },
+  "transformers_version": "4.51.3",
+  "vocab_size": 250002,
+  "wandb": {
+    "group": null,
+    "job_type": null,
+    "name": null,
+    "notes": "Block Denoising Discrete Diffusion Language Models",
+    "project": "autodiffusion"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d29f4604ad902b9333b750cd541edd02b20f02dd795d924f9644a4b83b113b9
+size 1032366384

random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398e28fa41dc4179a48c98efe15e0a19f453a864a2ddc4b4320a19969c99764e
+size 15580

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1d2e42a2a0d9ba0909ff5128e887b29b6ecd591483df42b3d5058d40a325c7
+size 5304