Add files using upload-large-folder tool

base_checkpoints/d4/meta_000416.json

@@ -0,0 +1,56 @@
+{
+  "step": 416,
+  "val_bpb": 1.137863058912311,
+  "model_config": {
+    "sequence_len": 1024,
+    "pure_vocab_size": 4096,
+    "all_vocab_size": 4917,
+    "n_layer": 4,
+    "n_head": 2,
+    "n_kv_head": 2,
+    "n_embd": 256,
+    "prefix_pure_tokens": 1,
+    "mask_token_id": 4096
+  },
+  "user_config": {
+    "run": "pdlm_depth4_bs8_pr1_ratio40_causal",
+    "device_type": "",
+    "depth": 4,
+    "max_seq_len": 1024,
+    "block_size": 8,
+    "prefix_pure_tokens": 1,
+    "is_causal": true,
+    "num_iterations": -1,
+    "target_flops": -1.0,
+    "target_param_data_ratio": 40,
+    "device_batch_size": 64,
+    "total_batch_size": 524288,
+    "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": 99999,
+    "eval_tokens": 10485760,
+    "core_metric_every": -1,
+    "core_metric_max_per_task": 500,
+    "sample_every": 2000,
+    "save_every": -1,
+    "model_tag": ""
+  },
+  "device_batch_size": 64,
+  "max_seq_len": 1024,
+  "dataloader_state_dict": {
+    "pq_idx": 3,
+    "rg_idx": 129
+  },
+  "loop_state": {
+    "min_val_bpb": 1.137863058912311,
+    "smooth_train_loss": 2.1223166214609748,
+    "total_training_time": 308.1995761394501
+  }
+}

base_checkpoints/d4/model_000416.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64aa68c5df3e765120c62eee2e662dfd152fd361377d8656bd1c994153a2d933
+size 19305717

base_checkpoints/d4/optim_000416_rank0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa59aeb2c2c48281a6026592c20badb8b278d7978eb64defb7876092984676af
+size 26017109

report/base-model-training.md

@@ -0,0 +1,48 @@
+## Base model training
+timestamp: 2025-12-27 20:59:08
+
+- run: pdlm_depth4_bs8_pr1_ratio40_causal
+- device_type: 
+- depth: 4
+- max_seq_len: 1024
+- block_size: 8
+- prefix_pure_tokens: 1
+- is_causal: True
+- num_iterations: -1
+- target_flops: -1.0000
+- target_param_data_ratio: 40
+- device_batch_size: 64
+- total_batch_size: 524,288
+- 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: 99,999
+- eval_tokens: 10,485,760
+- core_metric_every: -1
+- core_metric_max_per_task: 500
+- sample_every: 2000
+- save_every: -1
+- model_tag: 
+- Number of parameters: 5,453,056
+- Number of FLOPs per token: 3.774874e+07
+- Calculated number of iterations: 416
+- Number of training tokens: 218,103,808
+- Tokens : Params ratio: 39.9966
+- DDP world size: 1
+- warmup_ratio: 0.0000
+- warmdown_ratio: 0.2000
+- final_lr_frac: 0.0000
+- Minimum validation bpb: 1.1379
+- Final validation bpb: 1.1379
+- CORE metric estimate: None
+- MFU %: 2.64%
+- Total training flops: 8.233143e+15
+- Total training time: 5.14m
+- Peak memory usage: 6905.37MiB
+

tokenizer/token_bytes.pt

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

tokenizer/token_maps.pt

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

tokenizer/tokenizer.pkl

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