Add files using upload-large-folder tool

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/meta_005000.json

@@ -0,0 +1,59 @@
+{
+  "step": 5000,
+  "val_bpb": 0,
+  "model_config": {
+    "sequence_len": 1024,
+    "pure_vocab_size": 4096,
+    "all_vocab_size": 4917,
+    "n_layer": 8,
+    "n_head": 4,
+    "n_kv_head": 4,
+    "n_embd": 512,
+    "prefix_pure_tokens": 1,
+    "mask_token_id": 4096,
+    "is_causal": false
+  },
+  "user_config": {
+    "run": "pdlm_d8_bs4_pr1_r25_non_ca_samenoisy",
+    "device_type": "",
+    "depth": 8,
+    "max_seq_len": 1024,
+    "block_size": 4,
+    "prefix_pure_tokens": 1,
+    "is_causal": false,
+    "noise_total_steps": 0,
+    "debug": false,
+    "num_iterations": -1,
+    "target_flops": -1.0,
+    "target_param_data_ratio": 25,
+    "device_batch_size": 64,
+    "total_batch_size": 131072,
+    "embedding_lr": 0.2,
+    "unembedding_lr": 0.004,
+    "weight_decay": 0.0,
+    "matrix_lr": 0.02,
+    "grad_clip": 1.0,
+    "warmup_ratio": 0.0,
+    "warmdown_ratio": 0.2,
+    "final_lr_frac": 0.0,
+    "resume_from_step": -1,
+    "eval_every": -1,
+    "eval_tokens": 10485760,
+    "core_metric_every": -1,
+    "core_metric_max_per_task": 500,
+    "sample_every": 2000,
+    "save_every": 5000,
+    "model_tag": ""
+  },
+  "device_batch_size": 64,
+  "max_seq_len": 1024,
+  "dataloader_state_dict": {
+    "pq_idx": 10,
+    "rg_idx": 123
+  },
+  "loop_state": {
+    "min_val_bpb": Infinity,
+    "smooth_train_loss": 1.559914570357708,
+    "total_training_time": 3959.402800321579
+  }
+}

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/meta_005680.json

@@ -0,0 +1,59 @@
+{
+  "step": 5680,
+  "val_bpb": 0,
+  "model_config": {
+    "sequence_len": 1024,
+    "pure_vocab_size": 4096,
+    "all_vocab_size": 4917,
+    "n_layer": 8,
+    "n_head": 4,
+    "n_kv_head": 4,
+    "n_embd": 512,
+    "prefix_pure_tokens": 1,
+    "mask_token_id": 4096,
+    "is_causal": false
+  },
+  "user_config": {
+    "run": "pdlm_d8_bs4_pr1_r25_non_ca_samenoisy",
+    "device_type": "",
+    "depth": 8,
+    "max_seq_len": 1024,
+    "block_size": 4,
+    "prefix_pure_tokens": 1,
+    "is_causal": false,
+    "noise_total_steps": 0,
+    "debug": false,
+    "num_iterations": -1,
+    "target_flops": -1.0,
+    "target_param_data_ratio": 25,
+    "device_batch_size": 64,
+    "total_batch_size": 131072,
+    "embedding_lr": 0.2,
+    "unembedding_lr": 0.004,
+    "weight_decay": 0.0,
+    "matrix_lr": 0.02,
+    "grad_clip": 1.0,
+    "warmup_ratio": 0.0,
+    "warmdown_ratio": 0.2,
+    "final_lr_frac": 0.0,
+    "resume_from_step": -1,
+    "eval_every": -1,
+    "eval_tokens": 10485760,
+    "core_metric_every": -1,
+    "core_metric_max_per_task": 500,
+    "sample_every": 2000,
+    "save_every": 5000,
+    "model_tag": ""
+  },
+  "device_batch_size": 64,
+  "max_seq_len": 1024,
+  "dataloader_state_dict": {
+    "pq_idx": 12,
+    "rg_idx": 23
+  },
+  "loop_state": {
+    "min_val_bpb": Infinity,
+    "smooth_train_loss": 1.551141215111763,
+    "total_training_time": 4498.662185430527
+  }
+}

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/model_005000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98991e9922212df95c7d67b24056c53b23c096f9b74511c6eef0be5c99099d9
+size 114107621

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/model_005680.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8935720be3ab2a76ccceb3007a26e5cd2560704f97c231de5ce28abd153584
+size 114107621

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/optim_005000_rank0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0a35a2c9dc2b3e89876f395c40cd0472ff50870e717ced247c7e8ad988a644
+size 127528469

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/base_checkpoints/d8/optim_005680_rank0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07223f1f8653e8b6a0c604d97b2a48c8a23e8b72fde48a1365d9e78e0c8fb57
+size 127528469

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/report/base-model-training.md

@@ -0,0 +1,50 @@
+## Base model training
+timestamp: 2026-01-02 21:00:50
+
+- run: pdlm_d8_bs4_pr1_r25_non_ca_samenoisy
+- device_type: 
+- depth: 8
+- max_seq_len: 1024
+- block_size: 4
+- prefix_pure_tokens: 1
+- is_causal: False
+- noise_total_steps: 0
+- debug: False
+- num_iterations: -1
+- target_flops: -1.0000
+- target_param_data_ratio: 25
+- device_batch_size: 64
+- total_batch_size: 131,072
+- embedding_lr: 0.2000
+- unembedding_lr: 0.0040
+- weight_decay: 0.0000
+- matrix_lr: 0.0200
+- grad_clip: 1.0000
+- warmup_ratio: 0.0000
+- warmdown_ratio: 0.2000
+- final_lr_frac: 0.0000
+- resume_from_step: -1
+- eval_every: -1
+- eval_tokens: 10,485,760
+- core_metric_every: -1
+- core_metric_max_per_task: 500
+- sample_every: 2000
+- save_every: 5000
+- model_tag: 
+- Number of parameters: 29,780,480
+- Number of FLOPs per token: 2.139095e+08
+- Calculated number of iterations: 5680
+- Number of training tokens: 744,488,960
+- Tokens : Params ratio: 24.9992
+- DDP world size: 1
+- warmup_ratio: 0.0000
+- warmdown_ratio: 0.2000
+- final_lr_frac: 0.0000
+- Minimum validation bpb: inf
+- Final validation bpb: 0
+- CORE metric estimate: None
+- MFU %: 3.58%
+- Total training flops: 1.592533e+17
+- Total training time: 74.98m
+- Peak memory usage: 21217.98MiB
+

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/report/header.md

@@ -0,0 +1,36 @@
+# nanochat training report
+
+Generated: 2026-01-02 19:43:57
+
+## Environment
+
+### Git Information
+- Branch: tokenizer
+- Commit: 72f06c8 (clean)
+- Message: add response to the dump file
+
+### Hardware
+- Platform: Linux
+- CPUs: 6 cores (12 logical)
+- Memory: 167.1 GB
+- GPUs: 1x NVIDIA A100-SXM4-80GB
+- GPU Memory: 79.3 GB total
+- CUDA Version: 12.6
+- Hourly Rate: $1.79/hour
+
+### Software
+- Python: 3.12.12
+- PyTorch: 2.9.0+cu126
+
+
+### Bloat
+- Characters: 543,851
+- Lines: 13,317
+- Files: 72
+- Tokens (approx): 135,962
+- Dependencies (uv.lock lines): 2,218
+
+Run started: 2026-01-02 19:43:58
+
+---
+

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/tokenizer/token_bytes.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8b99c0d5a1b87b87118e840f69510440302023cd514b241614fb562373d7ce
+size 17961

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/tokenizer/token_maps.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e018730860c8e77e8cbba4b57ac9c7ba6798b5926dce925743959b932a099964
+size 1850237

pdlm_d8_bs4_pr1_r25_non_ca_samenoisy/tokenizer/tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f874c4250ec76e2e8c4f97e91c55cfdf74d9f8eedaae14cd22db36bb718ee19
+size 61662