Upload folder using huggingface_hub

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/metrics.json

@@ -0,0 +1,28 @@
+{
+  "batch_nums": [
+    1
+  ],
+  "losses": [
+    13.95216178894043
+  ],
+  "accuracies": [
+    0.0014594988897442818
+  ],
+  "grad_norms": [
+    4.199021339416504
+  ],
+  "eval_batch_nums": [],
+  "eval_losses": [],
+  "eval_accuracies": [],
+  "eval_perplexities": [],
+  "tokens_per_sec": [
+    20541.347184770988
+  ],
+  "eval_tokens_per_sec": [],
+  "batch_time_deltas": [
+    0.3880486488342285
+  ],
+  "last_batch_time": 1757017024.370311,
+  "eval_time_deltas": [],
+  "last_eval_time": 1757017023.982263
+}

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d185c61f0fffaf51a641b7c4de5c2e62778fb8446b0f99908cf101e299942a67
+size 135137571

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62782c1cebfd7181ff19821058bb3f23e3bee871d555326fd4ae0338626d5430
+size 270310603

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/random_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e98648b1ad2a9d085ffe6102fd07ba734b5ebbd39f312017b9d896fc3f8a453
+size 13655

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/tokenizer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/tokenizer/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

scaling-series-v1-debug/control_64m_s42/checkpoint_000001/training_state.json

@@ -0,0 +1,5 @@
+{
+  "global_batch": 1,
+  "effective_batch": 1,
+  "miniepoch_num": 1
+}