Upload folder using huggingface_hub

meta_169150.json

@@ -0,0 +1,50 @@
+{
+  "step": 169150,
+  "val_bpb": 0.7045097392874156,
+  "model_config": {
+    "sequence_len": 2048,
+    "vocab_size": 65536,
+    "n_layer": 34,
+    "n_head": 17,
+    "n_kv_head": 17,
+    "n_embd": 2176
+  },
+  "user_config": {
+    "run": "d34ratio40-v2-resume",
+    "device_type": "",
+    "depth": 34,
+    "max_seq_len": 2048,
+    "num_iterations": -1,
+    "target_flops": -1.0,
+    "target_param_data_ratio": 40,
+    "device_batch_size": 4,
+    "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": 165000,
+    "eval_every": 250,
+    "eval_tokens": 10485760,
+    "core_metric_every": 2000,
+    "core_metric_max_per_task": 500,
+    "sample_every": 2000,
+    "save_every": 5000,
+    "model_tag": ""
+  },
+  "device_batch_size": 4,
+  "max_seq_len": 2048,
+  "dataloader_state_dict": {
+    "pq_idx": 1572,
+    "rg_idx": 16
+  },
+  "loop_state": {
+    "min_val_bpb": 0.7045097392874156,
+    "smooth_train_loss": 2.3114329221041356,
+    "total_training_time": 337992.5186035633
+  }
+}

model_169150.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d4f6a682ca1967e0bc24ed59d66693dc902308f219072382fd9b21c97e5e3f
+size 8583203839

token_bytes.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e280877820a90174f3b47bf797b67b9026cd859b7d6d5b7f78e64bcdaca126b4
+size 263721

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f28610ffd37a57d6631f8d7bd91929bd877ae3f4a87dcbdff00b07f6bd7cc3
+size 846092