diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..409a62b95ae104b75c570a7adaeb11b203bbf8a3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,18 @@ 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 +adapters/consciousness-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/davinci-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/empathy-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/davinci/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/davinci/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/davinci/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/newton/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/newton/checkpoint-1125/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/newton/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/hf_download/newton/tokenizer.json filter=lfs diff=lfs merge=lfs -text +adapters/multi_perspective-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/newton-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/philosophy-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/quantum-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text +adapters/systems_architecture-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/adapters/.gitkeep b/adapters/.gitkeep new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/adapters/consciousness-lora-f16.gguf b/adapters/consciousness-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..8a917d37e5373a709aa18194651a173bfd77f72e --- /dev/null +++ b/adapters/consciousness-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c88d5e225e910402409cebaa9b330cba03bcd1330e8f1f069c9270353c269b5 +size 27281088 diff --git a/adapters/convert_peft_to_gguf.py b/adapters/convert_peft_to_gguf.py new file mode 100644 index 0000000000000000000000000000000000000000..d0f19f6edd6584996d3ad7151227804a5053c94b --- /dev/null +++ b/adapters/convert_peft_to_gguf.py @@ -0,0 +1,207 @@ +#!/usr/bin/env python3 +"""Convert PEFT LoRA safetensors to llama.cpp GGUF LoRA format. + +Lightweight converter — no torch/transformers dependency. +Only needs: safetensors, gguf, numpy, struct. + +Matches the exact format produced by llama.cpp's convert_lora_to_gguf.py. +""" + +import json +import struct +import sys +from pathlib import Path +import numpy as np + +# gguf uses its own writer +from gguf import GGUFWriter, GGMLQuantizationType + + +# PEFT tensor name -> GGUF tensor name mapping for LLama +# PEFT: base_model.model.model.layers.{i}.self_attn.{proj}.lora_{AB}.weight +# GGUF: blk.{i}.attn_{mapped_proj}.weight.lora_{ab} +PROJ_MAP = { + "q_proj": "attn_q", + "k_proj": "attn_k", + "v_proj": "attn_v", + "o_proj": "attn_output", +} + + +def bf16_to_f16(data_bytes: bytes) -> np.ndarray: + """Convert bfloat16 raw bytes to float16 numpy array. + + bf16: sign(1) + exp(8) + mantissa(7) + f16: sign(1) + exp(5) + mantissa(10) + + We go bf16 -> f32 -> f16 to avoid precision edge cases. + """ + # Read as uint16 (same byte layout as bf16) + bf16 = np.frombuffer(data_bytes, dtype=np.uint16) + # Convert bf16 to f32: shift left 16 bits + f32_bytes = np.zeros(len(bf16), dtype=np.uint32) + f32_bytes[:] = bf16.astype(np.uint32) << 16 + f32 = f32_bytes.view(np.float32) + # Convert f32 to f16 + return f32.astype(np.float16) + + +def read_safetensors(path: Path) -> dict: + """Read safetensors file, handling bf16 manually.""" + with open(path, "rb") as f: + # Header: 8-byte little-endian uint64 = header size + header_size = struct.unpack(" str | None: + """Map PEFT tensor name to GGUF tensor name. + + Input: base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight + Output: blk.0.attn_q.weight.lora_a + """ + parts = peft_name.split(".") + # Expected: base_model.model.model.layers.{i}.self_attn.{proj}.lora_{AB}.weight + try: + layer_idx = parts[4] # layer number + proj = parts[6] # q_proj, k_proj, etc. + lora_part = parts[7] # lora_A or lora_B + except IndexError: + return None + + gguf_proj = PROJ_MAP.get(proj) + if gguf_proj is None: + return None + + ab = lora_part.lower() # lora_a or lora_b + return f"blk.{layer_idx}.{gguf_proj}.weight.{ab}" + + +def convert(adapter_dir: Path, output_path: Path, adapter_name: str): + """Convert a PEFT LoRA adapter to GGUF format.""" + config_path = adapter_dir / "adapter_config.json" + safetensors_path = adapter_dir / "adapter_model.safetensors" + + if not config_path.exists(): + raise FileNotFoundError(f"No adapter_config.json in {adapter_dir}") + if not safetensors_path.exists(): + raise FileNotFoundError(f"No adapter_model.safetensors in {adapter_dir}") + + # Read config + with open(config_path) as f: + config = json.load(f) + + lora_alpha = config.get("lora_alpha", 32) + lora_rank = config.get("r", 16) + print(f" Config: rank={lora_rank}, alpha={lora_alpha}") + + # Read tensors + print(f" Reading safetensors...") + tensors = read_safetensors(safetensors_path) + print(f" Loaded {len(tensors)} tensors") + + # Create GGUF writer + writer = GGUFWriter(str(output_path), arch="llama") + + # Write metadata (matching the newton GGUF format exactly) + writer.add_string("general.type", "adapter") + writer.add_string("adapter.type", "lora") + writer.add_string("general.name", adapter_name) + writer.add_uint32("general.base_model.count", 1) + writer.add_string("general.base_model.0.name", "Llama 3.1 8B Instruct") + writer.add_string("general.base_model.0.organization", "Meta Llama") + writer.add_string("general.base_model.0.repo_url", + "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct") + writer.add_array("general.tags", [ + "base_model:adapter:meta-llama/Llama-3.1-8B-Instruct", + "lora", "sft", "transformers", "trl", "text-generation", + ]) + writer.add_float32("adapter.lora.alpha", float(lora_alpha)) + writer.add_uint32("general.quantization_version", 2) + + # Convert and add tensors + converted = 0 + for peft_name, data in sorted(tensors.items()): + gguf_name = peft_name_to_gguf(peft_name) + if gguf_name is None: + print(f" SKIP: {peft_name}") + continue + + # GGUF LoRA expects F16 (type=1) + writer.add_tensor(gguf_name, data, raw_dtype=GGMLQuantizationType.F16) + converted += 1 + + print(f" Converted {converted} tensors") + + # Write file + writer.write_header_to_file() + writer.write_kv_data_to_file() + writer.write_tensors_to_file() + writer.close() + + size_mb = output_path.stat().st_size / 1024 / 1024 + print(f" Output: {output_path} ({size_mb:.1f} MB)") + + +def main(): + adapters_dir = Path("J:/codette-training-lab/adapters") + hf_dir = adapters_dir / "hf_download" + + # Convert all adapters that have safetensors but no GGUF yet + to_convert = [] + for name in ["empathy", "philosophy", "quantum", + "consciousness", "multi_perspective", "systems_architecture"]: + src = hf_dir / name + dst = adapters_dir / f"{name}-lora-f16.gguf" + if src.exists() and (src / "adapter_model.safetensors").exists(): + if dst.exists(): + print(f"SKIP {name}: GGUF already exists") + else: + to_convert.append((name, src, dst)) + else: + print(f"SKIP {name}: no safetensors found") + + if not to_convert: + print("Nothing to convert!") + return + + for name, src, dst in to_convert: + print(f"\nConverting {name}...") + try: + convert(src, dst, name) + print(f"OK: {name}") + except Exception as e: + print(f"FAIL: {name}: {e}") + + +if __name__ == "__main__": + main() diff --git a/adapters/davinci-lora-f16.gguf b/adapters/davinci-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..ef621b89e9c4527d9c64c02b7b4a47c0f592216c --- /dev/null +++ b/adapters/davinci-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008fa6af197f27c0635e0220766af8a67dbb0d76c51a00f4f6c9a6b0a8c06bb5 +size 27281088 diff --git a/adapters/empathy-lora-f16.gguf b/adapters/empathy-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..1b7cb8bda919f9a794a307cdd7c1faa236004385 --- /dev/null +++ b/adapters/empathy-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a7c5f74e9985ca0408fccbcc2640cea80a8c7694c3104ce4d059dade14855e +size 27281088 diff --git a/adapters/hf_download/.cache/huggingface/.gitignore b/adapters/hf_download/.cache/huggingface/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f59ec20aabf5842d237244ece8c81ab184faeac1 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/.gitignore @@ -0,0 +1 @@ +* \ No newline at end of file diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..5c2cae50b18fe171747e12220534bbe8c058d3e8 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +5656a023ae422c09a8cadad322725b2b4e99c8c6 +1772982742.954254 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c4223fd66e2b2feae03574942fcbd57d8a5d1017 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982743.0280573 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f209d134954c8b01dd06864f3b28fcb0efc1ed8f --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +03f76f7744a6495586fa6e24433bd8f2ca6b56516b79f4fad768bd5dc83fd58b +1772982745.2292411 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..b4064c94410cc14c279f9072c6816062c3da53be --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982743.1740534 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..e625c7b0c22a1ae03361cbc71b339619a1a05113 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +35f6e0e06fbb5355b8afea90d8f546c40fb6d50e +1772982743.0992334 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c7d805acce7fd335167729d7b7a1b1d37a530445 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982743.193937 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..0a6eeb093ffb0b83c2daad73c5eaaa3031af622f --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +d3827e8946985310f1f9bd01c2aaf3778d08911a2d21de729b8c900c77936039 +1772982746.870133 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..b256ffa6704a58efcfac0efbbf5d660d5b42d00e --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982743.2263455 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/optimizer.pt.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/optimizer.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c0736b808bcbd6f7d440624a47a3bad9a646758a --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/optimizer.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +947653b830d6950537a7de10e3769878f674e06129580ad51009d9fe93254633 +1772982750.0713503 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/rng_state.pth.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/rng_state.pth.metadata new file mode 100644 index 0000000000000000000000000000000000000000..332cef00640106c8201c3b6d3e29444f852fd722 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/rng_state.pth.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +abcf9cee12e3b2d7ef53dd8425427fd15e6a6e3b1b7ab2fb87a9682dc5e34fa9 +1772982743.8634136 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/scheduler.pt.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/scheduler.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..00fbab45c4d99b7e8587c2a9c4f9c58f9a34b9d0 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/scheduler.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +820927e41cd14e86356818cda9df54ef4ef3f4c3a4d4b7a28cbf4df629afd0fd +1772982743.8644173 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..def7e973d8b0badb7eaa1ebf77b4fb0bd983d021 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982743.9062474 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..07398b54da6280e8b333d95bb9c0f995c2d572f7 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982743.3583183 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/trainer_state.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/trainer_state.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..6fdfd90a4d86141c9fc192e34da2d6a4cd996d53 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/trainer_state.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +1345c98368376e4536f835bf8dca10afa40cf742 +1772982743.4283683 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/training_args.bin.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/training_args.bin.metadata new file mode 100644 index 0000000000000000000000000000000000000000..101aff84a801e227616fe38da6ec4c4debd9acc5 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-500/training_args.bin.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6f21cb0f4416a41acd8ff9feb8c0f995a14287a039f7c3dc536cda4414e290f8 +1772982743.8644173 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..9a73ee8717c0a734045e0dbcdc0d34073a9ad516 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +35f6e0e06fbb5355b8afea90d8f546c40fb6d50e +1772982743.7069378 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..19ae61531676fd706683b0e91876603f53608286 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982743.8806453 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..e43620bef2a86c57ab2d4bee69c90b97aa7debb2 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +03f76f7744a6495586fa6e24433bd8f2ca6b56516b79f4fad768bd5dc83fd58b +1772982748.063234 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..5391d191255d6f9be0c4b9cb5c3b20e498dc0f41 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982744.061768 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/optimizer.pt.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/optimizer.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..b4dcfc169c2a4a69c09243c82954e81e079dbf15 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/optimizer.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +12ec721ffd7ea81911e8868ad42809f38c2ca2e1ee45363b256ba4c9f5338b28 +1772982749.944305 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/rng_state.pth.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/rng_state.pth.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f2c33873c7a0a09a805d982fc928bd4712718360 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/rng_state.pth.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6336e829a9ff8cce299b6fd18f96bdb30f66fa9d26a2d0e60c9f3abf68ca973d +1772982744.1810288 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/scheduler.pt.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/scheduler.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..6083eec0734f5c5d519be048cf7456626c911314 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/scheduler.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +a85b9d8d75b43f2deffbdf4c4ecce548860c65bc59c665b7c0dfc2918984f3a7 +1772982744.620344 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..a22bc50b701c3873dc3074ea000b1d3bce3063db --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982744.8302794 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..5ed62fafc3017f3a3dc30d283812eff75d691645 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982744.3912904 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/trainer_state.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/trainer_state.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..042bef099581dff78c0c10864c6dcaaeb226c9ff --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/trainer_state.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +d2552641bece9fc1ad56230c3c633386f3e8e0a8 +1772982744.5735996 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/training_args.bin.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/training_args.bin.metadata new file mode 100644 index 0000000000000000000000000000000000000000..62e4832be319808977684418b67f4de3269c51a2 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/checkpoint-939/training_args.bin.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6f21cb0f4416a41acd8ff9feb8c0f995a14287a039f7c3dc536cda4414e290f8 +1772982744.8585858 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f74a6404d61681560ae63f9c7daabbe7d9062847 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982745.519444 diff --git a/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..6e81bfaa8429ed9bd5faf11d992a32e0a0e993eb --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/davinci/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982745.1185393 diff --git a/adapters/hf_download/.cache/huggingface/download/empathy/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/empathy/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..d5e96e5d7b471f39a55439e93c423b3f0b1dfb13 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/empathy/adapter_config.json.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +e436105a860fe50b72d2cc8f1e1b7300e6d03116 +1773025812.6514704 diff --git a/adapters/hf_download/.cache/huggingface/download/empathy/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/empathy/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..cc0b3c823d4dd2b1003d99c288293ea64b655c83 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/empathy/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +ae48e5ab42f5024f6e9ac24cbbc8e54d07a151740a4c6c5ea834fcaf78101d45 +1773025814.809387 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/newton/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..59ab56b0409150c00cccb8947b67aa9240e47fce --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +17d7bc43d9aae66692937db54d36ced3b88978ce +1772982733.3036044 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..ed8cc8bfd6cb136d0f481384915c25062a88edcf --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982733.4335587 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/newton/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..8249a7c8b142e532f91d06a25093a49f927c8a18 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +323635297b5e0c773a26c4451697f85a4ff3020e8864a138ba799a14da2627a2 +1772982740.8261943 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/newton/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..4255d3c294d5b015034b248341abfec22b4d0c8e --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982733.4335587 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..4aabbe3ee7329b971db1bac6718ac47737a80419 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +35f6e0e06fbb5355b8afea90d8f546c40fb6d50e +1772982733.5085428 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..41b5972a541cc5241014aa667182cb02aaf1cad4 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982733.4395387 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c90bf3f74afc204a28553d9a0609078b46b7ec6d --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +f41c14f1336f835fccc7fe9f0c53b2a0966f2388840ee6241fffd86a6a65108a +1772982737.3707821 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..16fe385b9f82ac573575f1d93fd6f6de85732bb8 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982733.5100255 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/optimizer.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/optimizer.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..364a3e5830b020f82c63c60e0bff08961d03a6ce --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/optimizer.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +44e023b856408604b2dac8f46a59a2c413f9c5171d8a8dd0bcb2e1266e8a17e0 +1772982737.4129932 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/rng_state.pth.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/rng_state.pth.metadata new file mode 100644 index 0000000000000000000000000000000000000000..30a8023b7907e837ba2f0659ea83d0f1adfa4d4c --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/rng_state.pth.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +58a9efb6a8371c0aa0c7c1f1395d8817f98251d4ccd6b17cd77847cecdf56a0b +1772982734.8024912 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/scheduler.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/scheduler.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..343b67e3041f754aabe953ea341fdb578cee09f4 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/scheduler.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +ede3d2a514005ed80690b07770eb75aab9fd0b335517babd631dfbc1716d09fd +1772982734.8004725 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..17702ac17632c1a1cc76cf25997160374f34c2ce --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982734.8103404 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..477b56f6756ce33a257ce26965ab17e7487702b5 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982733.661514 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/trainer_state.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/trainer_state.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..bdd9d90dbbcad0942cae884be123cd7086116f69 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/trainer_state.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6483faff277dd6a8e5bc5d2b50c8b44addf8a890 +1772982733.6765447 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/training_args.bin.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/training_args.bin.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f719cdbf952e64ccea2a0b1de505abc7951b9f62 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1000/training_args.bin.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +1772982734.8943338 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f2e2849c9bb7d399c2839c4842d19062264d17b3 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +35f6e0e06fbb5355b8afea90d8f546c40fb6d50e +1772982733.835505 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..19081ee3104d321fc1d028c8422f54f4f76df812 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982733.9967012 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..329023b3bd5b143e631aad91547b364f4e474492 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +323635297b5e0c773a26c4451697f85a4ff3020e8864a138ba799a14da2627a2 +1772982740.5517728 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..a2c6e04a0204c46fc8d2f5ccc5a62b19050ac57d --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982734.9568727 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/optimizer.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/optimizer.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..bb99ef590335326513fd6fc5b8e72097065b616a --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/optimizer.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +0613cd7692608d4f46da8fb85a3e7b638bf5c9637f9cfc5d1454e781d35e5997 +1772982742.703926 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/rng_state.pth.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/rng_state.pth.metadata new file mode 100644 index 0000000000000000000000000000000000000000..584e3b75961b518be771a420badaf0871141acdc --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/rng_state.pth.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +c207979b56e7df5b5e151c53b37e511fa7122539c6e7e5570ee51af2a0968967 +1772982735.2729495 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/scheduler.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/scheduler.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..e0261cae793c230c19a98177e8662e60ab3c8be7 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/scheduler.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +cb2a37c55dd5d7928c5b2c15b7d4f650fade3ddb7af6dc8961ca05874b789488 +1772982735.700157 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..125598829b090566d33df81e63c9ce906945bdc7 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982737.2973056 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..1199f7cf42ac83e8183cad4e6160ce9dbc1c5c4b --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982735.4601185 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/trainer_state.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/trainer_state.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..cf2382ddff092753d6205ed3bbd492d1365822e0 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/trainer_state.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +3a8ad9308698e15be4f948c09a49201e307c512c +1772982735.6476727 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/training_args.bin.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/training_args.bin.metadata new file mode 100644 index 0000000000000000000000000000000000000000..0d68bb2808a6b264ac2e676aa61a1d5a10ac7e69 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-1125/training_args.bin.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +1772982735.96847 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/README.md.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..551fa588ec11bff053a0b7222dc6d3beaf433188 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/README.md.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +35f6e0e06fbb5355b8afea90d8f546c40fb6d50e +1772982735.9190946 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..4a8739d6c0e198b2e2163903e1a6f34aad303e9f --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +64a158266c0996f78496250ff985d9b9f2287d17 +1772982736.080655 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..07b24981139ba84e904cf3168a2e9def6e0f148d --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b2e3fa39229c6ec9a3ae3953299dd1633da0fe90c86d1cbd81f4670401ecc4d6 +1772982741.3015609 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/chat_template.jinja.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/chat_template.jinja.metadata new file mode 100644 index 0000000000000000000000000000000000000000..17110da2b81e64047e93ccc7bc9066021fb755d8 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/chat_template.jinja.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +33089ace1be88f22a10fe861ad49718d5d886090 +1772982736.303774 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/optimizer.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/optimizer.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..0f527b75b52788f0d367da3133d82412ced10048 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/optimizer.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +e02efb59f2ff28dda0a4a4530d4c7f101cf666c78420719d9db581857205db1e +1772982739.648607 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/rng_state.pth.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/rng_state.pth.metadata new file mode 100644 index 0000000000000000000000000000000000000000..0a4a87cbbe4351795b8c9e0fd0f7e97959523a0d --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/rng_state.pth.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +e06ed9055f2879d20734525b54e3185ffbd4df450c6774c39d8caa49df8499ed +1772982737.7733862 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/scheduler.pt.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/scheduler.pt.metadata new file mode 100644 index 0000000000000000000000000000000000000000..bb4630e8ae8de1b191b602d6780644a39c454fbc --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/scheduler.pt.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +c5f2b5fa48c7f09e4487186c3527dd0cb37a3de8892b16ebca696ce3df604cb5 +1772982737.7733862 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..8069615d2d5cdf5b0821fbc5e7615009caa2bd21 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982738.178079 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..dd3b2de2b67f8b084212da5a54a90caef467522a --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982737.9974525 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/trainer_state.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/trainer_state.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..3694a331c3d62b38ff9f6ceaa294133473d38e3a --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/trainer_state.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +44b699a99affa0a5c28ecc181604bddbb2188e47 +1772982738.0305486 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/training_args.bin.metadata b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/training_args.bin.metadata new file mode 100644 index 0000000000000000000000000000000000000000..6f81a8f12b0d08497a6c83f3f8709886dcb91d55 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/checkpoint-500/training_args.bin.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +1772982738.3241432 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/tokenizer.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/tokenizer.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..04bd29ddc931959fdad6ea2ebc72c0121b723dd9 --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1772982738.8585577 diff --git a/adapters/hf_download/.cache/huggingface/download/newton/tokenizer_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/newton/tokenizer_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..9a306658232afa76ae63a4e89444794202fa08ab --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/newton/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8e8a69fa26ba42756f7402791b56900a6058fb47 +b0c736827e07464a3cdd67acebb3699bfd0a38d1 +1772982738.3617792 diff --git a/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f6bf380a4039ddea6baf4cffc99b68230c71fccb --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_config.json.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +e436105a860fe50b72d2cc8f1e1b7300e6d03116 +1773025815.2149265 diff --git a/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..8f1a2273945d335b5b01aa0fed24e998d6725dcb --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/philosophy/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +8f1e0fd3925a2d53626c02c09e001d0efdf0e1b122d4b4a93b2fdcbf1132be02 +1773025816.6735163 diff --git a/adapters/hf_download/.cache/huggingface/download/quantum/adapter_config.json.metadata b/adapters/hf_download/.cache/huggingface/download/quantum/adapter_config.json.metadata new file mode 100644 index 0000000000000000000000000000000000000000..534c4810eafd059a00a8a60d2a5aaa5065015cdb --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/quantum/adapter_config.json.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +e436105a860fe50b72d2cc8f1e1b7300e6d03116 +1773025817.344815 diff --git a/adapters/hf_download/.cache/huggingface/download/quantum/adapter_model.safetensors.metadata b/adapters/hf_download/.cache/huggingface/download/quantum/adapter_model.safetensors.metadata new file mode 100644 index 0000000000000000000000000000000000000000..7af4414e52f1ad1c6d60823e263e2282d467b51f --- /dev/null +++ b/adapters/hf_download/.cache/huggingface/download/quantum/adapter_model.safetensors.metadata @@ -0,0 +1,3 @@ +a4568498a30e1a3a8d26a45f3dcdfeef43b0aa16 +daba59d3101ca1d0b42077187173d137c7894ff810c91e08e276ae0b3877bab9 +1773025818.6255836 diff --git a/adapters/hf_download/consciousness/adapter_config.json b/adapters/hf_download/consciousness/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8b2de52cc3e7a37fd794f63fc3ef18381217d301 --- /dev/null +++ b/adapters/hf_download/consciousness/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj", + "k_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/consciousness/adapter_model.safetensors b/adapters/hf_download/consciousness/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12023c0a7afabcdfb8c04849330d8b45adc0ad21 --- /dev/null +++ b/adapters/hf_download/consciousness/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66930f755168eb2cfd2ae1b754fcc51080acdc1050a221f1373d5ff234b23bb6 +size 27297544 diff --git a/adapters/hf_download/davinci/README.md b/adapters/hf_download/davinci/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5656a023ae422c09a8cadad322725b2b4e99c8c6 --- /dev/null +++ b/adapters/hf_download/davinci/README.md @@ -0,0 +1,62 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +model_name: davinci +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +licence: license +pipeline_tag: text-generation +--- + +# Model Card for davinci + +This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with SFT. + +### Framework versions + +- PEFT 0.18.1 +- TRL: 0.29.0 +- Transformers: 5.3.0 +- Pytorch: 2.10.0 +- Datasets: 4.6.1 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/adapters/hf_download/davinci/adapter_config.json b/adapters/hf_download/davinci/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/davinci/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/davinci/adapter_model.safetensors b/adapters/hf_download/davinci/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..137224dde740e715c9144e000de74dd6b5b1479b --- /dev/null +++ b/adapters/hf_download/davinci/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f76f7744a6495586fa6e24433bd8f2ca6b56516b79f4fad768bd5dc83fd58b +size 27297544 diff --git a/adapters/hf_download/davinci/chat_template.jinja b/adapters/hf_download/davinci/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/davinci/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/davinci/checkpoint-500/README.md b/adapters/hf_download/davinci/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..35f6e0e06fbb5355b8afea90d8f546c40fb6d50e --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/README.md @@ -0,0 +1,209 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.18.1 \ No newline at end of file diff --git a/adapters/hf_download/davinci/checkpoint-500/adapter_config.json b/adapters/hf_download/davinci/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/davinci/checkpoint-500/adapter_model.safetensors b/adapters/hf_download/davinci/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4bd69b0f25c1647638ed76450bf30ef211af3a1 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3827e8946985310f1f9bd01c2aaf3778d08911a2d21de729b8c900c77936039 +size 27297544 diff --git a/adapters/hf_download/davinci/checkpoint-500/chat_template.jinja b/adapters/hf_download/davinci/checkpoint-500/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/davinci/checkpoint-500/optimizer.pt b/adapters/hf_download/davinci/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..57e9462ea6c500ac1bfe1855c77e5ff983099f60 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947653b830d6950537a7de10e3769878f674e06129580ad51009d9fe93254633 +size 54745547 diff --git a/adapters/hf_download/davinci/checkpoint-500/rng_state.pth b/adapters/hf_download/davinci/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c445fffebb647682e970887c674492889614ccc --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abcf9cee12e3b2d7ef53dd8425427fd15e6a6e3b1b7ab2fb87a9682dc5e34fa9 +size 14645 diff --git a/adapters/hf_download/davinci/checkpoint-500/scheduler.pt b/adapters/hf_download/davinci/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9062e78f9b0f3bccbe28b0515f79a7b1e93e638 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820927e41cd14e86356818cda9df54ef4ef3f4c3a4d4b7a28cbf4df629afd0fd +size 1465 diff --git a/adapters/hf_download/davinci/checkpoint-500/tokenizer.json b/adapters/hf_download/davinci/checkpoint-500/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/davinci/checkpoint-500/tokenizer_config.json b/adapters/hf_download/davinci/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/davinci/checkpoint-500/trainer_state.json b/adapters/hf_download/davinci/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1345c98368376e4536f835bf8dca10afa40cf742 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/trainer_state.json @@ -0,0 +1,534 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.5984, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 2.765847223997116, + "epoch": 0.032, + "grad_norm": 0.2578125, + "learning_rate": 6.206896551724138e-05, + "loss": 2.887763786315918, + "mean_token_accuracy": 0.46187404468655585, + "num_tokens": 56152.0, + "step": 10 + }, + { + "entropy": 2.2775970876216887, + "epoch": 0.064, + "grad_norm": 0.2236328125, + "learning_rate": 0.00013103448275862068, + "loss": 2.460337448120117, + "mean_token_accuracy": 0.506013386696577, + "num_tokens": 112587.0, + "step": 20 + }, + { + "entropy": 1.8153630286455154, + "epoch": 0.096, + "grad_norm": 0.27734375, + "learning_rate": 0.0002, + "loss": 1.7399822235107423, + "mean_token_accuracy": 0.6103868752717971, + "num_tokens": 168621.0, + "step": 30 + }, + { + "entropy": 1.185289441049099, + "epoch": 0.128, + "grad_norm": 0.30859375, + "learning_rate": 0.0001978021978021978, + "loss": 1.1186148643493652, + "mean_token_accuracy": 0.7334396600723266, + "num_tokens": 224707.0, + "step": 40 + }, + { + "entropy": 0.8306711494922638, + "epoch": 0.16, + "grad_norm": 0.291015625, + "learning_rate": 0.00019560439560439562, + "loss": 0.7544202327728271, + "mean_token_accuracy": 0.8217264339327812, + "num_tokens": 281529.0, + "step": 50 + }, + { + "entropy": 0.5289712496101856, + "epoch": 0.192, + "grad_norm": 0.3046875, + "learning_rate": 0.00019340659340659342, + "loss": 0.452878475189209, + "mean_token_accuracy": 0.8946282967925072, + "num_tokens": 338008.0, + "step": 60 + }, + { + "entropy": 0.34988002628088, + "epoch": 0.224, + "grad_norm": 0.2734375, + "learning_rate": 0.00019120879120879122, + "loss": 0.29230058193206787, + "mean_token_accuracy": 0.9343003541231155, + "num_tokens": 394904.0, + "step": 70 + }, + { + "entropy": 0.25185412392020223, + "epoch": 0.256, + "grad_norm": 0.251953125, + "learning_rate": 0.00018901098901098903, + "loss": 0.20802268981933594, + "mean_token_accuracy": 0.9522816658020019, + "num_tokens": 451161.0, + "step": 80 + }, + { + "entropy": 0.2018993068486452, + "epoch": 0.288, + "grad_norm": 0.244140625, + "learning_rate": 0.00018681318681318683, + "loss": 0.17179200649261475, + "mean_token_accuracy": 0.9587775945663453, + "num_tokens": 507727.0, + "step": 90 + }, + { + "entropy": 0.16806554533541201, + "epoch": 0.32, + "grad_norm": 0.2158203125, + "learning_rate": 0.00018461538461538463, + "loss": 0.14763951301574707, + "mean_token_accuracy": 0.9639375448226929, + "num_tokens": 564343.0, + "step": 100 + }, + { + "entropy": 0.14694931916892529, + "epoch": 0.352, + "grad_norm": 0.185546875, + "learning_rate": 0.0001824175824175824, + "loss": 0.127738356590271, + "mean_token_accuracy": 0.966508974134922, + "num_tokens": 620780.0, + "step": 110 + }, + { + "entropy": 0.13702088352292777, + "epoch": 0.384, + "grad_norm": 0.201171875, + "learning_rate": 0.00018021978021978024, + "loss": 0.1153560996055603, + "mean_token_accuracy": 0.9671898797154427, + "num_tokens": 676485.0, + "step": 120 + }, + { + "entropy": 0.12865546997636557, + "epoch": 0.416, + "grad_norm": 0.091796875, + "learning_rate": 0.00017802197802197802, + "loss": 0.10538246631622314, + "mean_token_accuracy": 0.9685350403189659, + "num_tokens": 732104.0, + "step": 130 + }, + { + "entropy": 0.11221796181052923, + "epoch": 0.448, + "grad_norm": 0.1220703125, + "learning_rate": 0.00017582417582417582, + "loss": 0.09550263285636902, + "mean_token_accuracy": 0.9704204052686691, + "num_tokens": 788648.0, + "step": 140 + }, + { + "entropy": 0.11187596172094345, + "epoch": 0.48, + "grad_norm": 0.142578125, + "learning_rate": 0.00017362637362637365, + "loss": 0.09267887473106384, + "mean_token_accuracy": 0.9708487093448639, + "num_tokens": 845277.0, + "step": 150 + }, + { + "entropy": 0.10449027251452207, + "epoch": 0.512, + "grad_norm": 0.11474609375, + "learning_rate": 0.00017142857142857143, + "loss": 0.09188109636306763, + "mean_token_accuracy": 0.9701150968670845, + "num_tokens": 901601.0, + "step": 160 + }, + { + "entropy": 0.10061556100845337, + "epoch": 0.544, + "grad_norm": 0.078125, + "learning_rate": 0.00016923076923076923, + "loss": 0.08688170909881592, + "mean_token_accuracy": 0.9714163467288017, + "num_tokens": 958510.0, + "step": 170 + }, + { + "entropy": 0.09703337252140046, + "epoch": 0.576, + "grad_norm": 0.11865234375, + "learning_rate": 0.00016703296703296706, + "loss": 0.08396151661872864, + "mean_token_accuracy": 0.9724744081497192, + "num_tokens": 1014706.0, + "step": 180 + }, + { + "entropy": 0.09241664204746484, + "epoch": 0.608, + "grad_norm": 0.078125, + "learning_rate": 0.00016483516483516484, + "loss": 0.08444164395332336, + "mean_token_accuracy": 0.9721407666802406, + "num_tokens": 1071133.0, + "step": 190 + }, + { + "entropy": 0.09338212702423335, + "epoch": 0.64, + "grad_norm": 0.1142578125, + "learning_rate": 0.00016263736263736264, + "loss": 0.08270348310470581, + "mean_token_accuracy": 0.9724765837192535, + "num_tokens": 1127600.0, + "step": 200 + }, + { + "entropy": 0.09137626234441995, + "epoch": 0.672, + "grad_norm": 0.07275390625, + "learning_rate": 0.00016043956043956044, + "loss": 0.08120843768119812, + "mean_token_accuracy": 0.9727972850203515, + "num_tokens": 1183826.0, + "step": 210 + }, + { + "entropy": 0.08943495023995637, + "epoch": 0.704, + "grad_norm": 0.09228515625, + "learning_rate": 0.00015824175824175824, + "loss": 0.0806293785572052, + "mean_token_accuracy": 0.9729145392775536, + "num_tokens": 1240123.0, + "step": 220 + }, + { + "entropy": 0.08839260842651128, + "epoch": 0.736, + "grad_norm": 0.1171875, + "learning_rate": 0.00015604395604395605, + "loss": 0.07906079888343812, + "mean_token_accuracy": 0.9728850305080414, + "num_tokens": 1296696.0, + "step": 230 + }, + { + "entropy": 0.08858597576618195, + "epoch": 0.768, + "grad_norm": 0.1552734375, + "learning_rate": 0.00015384615384615385, + "loss": 0.08044076561927796, + "mean_token_accuracy": 0.9724162057042122, + "num_tokens": 1352831.0, + "step": 240 + }, + { + "entropy": 0.09007721468806267, + "epoch": 0.8, + "grad_norm": 0.10107421875, + "learning_rate": 0.00015164835164835165, + "loss": 0.08158640861511231, + "mean_token_accuracy": 0.9722792387008667, + "num_tokens": 1409271.0, + "step": 250 + }, + { + "entropy": 0.08655472807586193, + "epoch": 0.832, + "grad_norm": 0.07373046875, + "learning_rate": 0.00014945054945054946, + "loss": 0.08008719682693481, + "mean_token_accuracy": 0.9734297141432762, + "num_tokens": 1465271.0, + "step": 260 + }, + { + "entropy": 0.08689612131565809, + "epoch": 0.864, + "grad_norm": 0.1416015625, + "learning_rate": 0.00014725274725274726, + "loss": 0.07870798110961914, + "mean_token_accuracy": 0.9730307757854462, + "num_tokens": 1521295.0, + "step": 270 + }, + { + "entropy": 0.08382895905524493, + "epoch": 0.896, + "grad_norm": 0.09033203125, + "learning_rate": 0.00014505494505494506, + "loss": 0.07732324004173279, + "mean_token_accuracy": 0.9730261951684952, + "num_tokens": 1577651.0, + "step": 280 + }, + { + "entropy": 0.08625071458518505, + "epoch": 0.928, + "grad_norm": 0.095703125, + "learning_rate": 0.00014285714285714287, + "loss": 0.07772318720817566, + "mean_token_accuracy": 0.9722341999411583, + "num_tokens": 1633578.0, + "step": 290 + }, + { + "entropy": 0.08320586234331132, + "epoch": 0.96, + "grad_norm": 0.0654296875, + "learning_rate": 0.00014065934065934067, + "loss": 0.077446448802948, + "mean_token_accuracy": 0.972867003083229, + "num_tokens": 1690062.0, + "step": 300 + }, + { + "entropy": 0.08028208408504725, + "epoch": 0.992, + "grad_norm": 0.052001953125, + "learning_rate": 0.00013846153846153847, + "loss": 0.07448889017105102, + "mean_token_accuracy": 0.9736120477318764, + "num_tokens": 1747161.0, + "step": 310 + }, + { + "entropy": 0.08117271979388438, + "epoch": 1.0224, + "grad_norm": 0.072265625, + "learning_rate": 0.00013626373626373628, + "loss": 0.0744770348072052, + "mean_token_accuracy": 0.9738528257922122, + "num_tokens": 1800329.0, + "step": 320 + }, + { + "entropy": 0.080937241576612, + "epoch": 1.0544, + "grad_norm": 0.061767578125, + "learning_rate": 0.00013406593406593405, + "loss": 0.0741479218006134, + "mean_token_accuracy": 0.9734442710876465, + "num_tokens": 1856800.0, + "step": 330 + }, + { + "entropy": 0.07824601717293263, + "epoch": 1.0864, + "grad_norm": 0.06103515625, + "learning_rate": 0.00013186813186813188, + "loss": 0.07381554841995239, + "mean_token_accuracy": 0.973892730474472, + "num_tokens": 1912949.0, + "step": 340 + }, + { + "entropy": 0.0771486822515726, + "epoch": 1.1184, + "grad_norm": 0.060302734375, + "learning_rate": 0.0001296703296703297, + "loss": 0.0723546326160431, + "mean_token_accuracy": 0.974125075340271, + "num_tokens": 1969412.0, + "step": 350 + }, + { + "entropy": 0.07591825406998395, + "epoch": 1.1504, + "grad_norm": 0.052734375, + "learning_rate": 0.00012747252747252746, + "loss": 0.07068771123886108, + "mean_token_accuracy": 0.9741279140114785, + "num_tokens": 2025544.0, + "step": 360 + }, + { + "entropy": 0.0768967004492879, + "epoch": 1.1824, + "grad_norm": 0.0517578125, + "learning_rate": 0.00012527472527472527, + "loss": 0.07226019501686096, + "mean_token_accuracy": 0.974024161696434, + "num_tokens": 2082060.0, + "step": 370 + }, + { + "entropy": 0.07532943487167358, + "epoch": 1.2144, + "grad_norm": 0.0693359375, + "learning_rate": 0.0001230769230769231, + "loss": 0.07127081751823425, + "mean_token_accuracy": 0.9739077508449554, + "num_tokens": 2138526.0, + "step": 380 + }, + { + "entropy": 0.07546288054436445, + "epoch": 1.2464, + "grad_norm": 0.0732421875, + "learning_rate": 0.00012087912087912087, + "loss": 0.0715237319469452, + "mean_token_accuracy": 0.974101935327053, + "num_tokens": 2194683.0, + "step": 390 + }, + { + "entropy": 0.07725638337433338, + "epoch": 1.2784, + "grad_norm": 0.049560546875, + "learning_rate": 0.00011868131868131869, + "loss": 0.07198636531829834, + "mean_token_accuracy": 0.9740697085857392, + "num_tokens": 2251274.0, + "step": 400 + }, + { + "entropy": 0.07509954180568457, + "epoch": 1.3104, + "grad_norm": 0.1591796875, + "learning_rate": 0.0001164835164835165, + "loss": 0.07245813012123108, + "mean_token_accuracy": 0.97386264950037, + "num_tokens": 2307625.0, + "step": 410 + }, + { + "entropy": 0.07573851495981217, + "epoch": 1.3424, + "grad_norm": 0.11572265625, + "learning_rate": 0.00011428571428571428, + "loss": 0.07237505316734313, + "mean_token_accuracy": 0.9742786347866058, + "num_tokens": 2363944.0, + "step": 420 + }, + { + "entropy": 0.07536402009427548, + "epoch": 1.3744, + "grad_norm": 0.07861328125, + "learning_rate": 0.0001120879120879121, + "loss": 0.07097623944282531, + "mean_token_accuracy": 0.9736705645918846, + "num_tokens": 2420074.0, + "step": 430 + }, + { + "entropy": 0.07416129969060421, + "epoch": 1.4064, + "grad_norm": 0.052734375, + "learning_rate": 0.0001098901098901099, + "loss": 0.07140442728996277, + "mean_token_accuracy": 0.9747859939932824, + "num_tokens": 2476657.0, + "step": 440 + }, + { + "entropy": 0.07501455284655094, + "epoch": 1.4384000000000001, + "grad_norm": 0.05712890625, + "learning_rate": 0.0001076923076923077, + "loss": 0.07142727375030518, + "mean_token_accuracy": 0.9742778673768043, + "num_tokens": 2533642.0, + "step": 450 + }, + { + "entropy": 0.07456400785595178, + "epoch": 1.4704, + "grad_norm": 0.04736328125, + "learning_rate": 0.0001054945054945055, + "loss": 0.06932693123817443, + "mean_token_accuracy": 0.9749433383345604, + "num_tokens": 2590615.0, + "step": 460 + }, + { + "entropy": 0.07349070943892003, + "epoch": 1.5024, + "grad_norm": 0.0634765625, + "learning_rate": 0.00010329670329670331, + "loss": 0.06970517039299011, + "mean_token_accuracy": 0.9744679152965545, + "num_tokens": 2647074.0, + "step": 470 + }, + { + "entropy": 0.07532282676547766, + "epoch": 1.5344, + "grad_norm": 0.0498046875, + "learning_rate": 0.0001010989010989011, + "loss": 0.07047909498214722, + "mean_token_accuracy": 0.9740379452705383, + "num_tokens": 2703311.0, + "step": 480 + }, + { + "entropy": 0.07352385744452476, + "epoch": 1.5664, + "grad_norm": 0.05126953125, + "learning_rate": 9.89010989010989e-05, + "loss": 0.07030070424079896, + "mean_token_accuracy": 0.9743834063410759, + "num_tokens": 2759737.0, + "step": 490 + }, + { + "entropy": 0.07334190551191569, + "epoch": 1.5984, + "grad_norm": 0.050048828125, + "learning_rate": 9.670329670329671e-05, + "loss": 0.06969634890556335, + "mean_token_accuracy": 0.9740354612469673, + "num_tokens": 2815903.0, + "step": 500 + } + ], + "logging_steps": 10, + "max_steps": 939, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.3093502396768256e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/adapters/hf_download/davinci/checkpoint-500/training_args.bin b/adapters/hf_download/davinci/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e381391affd5717baa5678f5cd89f25daccbe0e --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f21cb0f4416a41acd8ff9feb8c0f995a14287a039f7c3dc536cda4414e290f8 +size 5585 diff --git a/adapters/hf_download/davinci/checkpoint-939/README.md b/adapters/hf_download/davinci/checkpoint-939/README.md new file mode 100644 index 0000000000000000000000000000000000000000..35f6e0e06fbb5355b8afea90d8f546c40fb6d50e --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/README.md @@ -0,0 +1,209 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.18.1 \ No newline at end of file diff --git a/adapters/hf_download/davinci/checkpoint-939/adapter_config.json b/adapters/hf_download/davinci/checkpoint-939/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/davinci/checkpoint-939/adapter_model.safetensors b/adapters/hf_download/davinci/checkpoint-939/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..137224dde740e715c9144e000de74dd6b5b1479b --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f76f7744a6495586fa6e24433bd8f2ca6b56516b79f4fad768bd5dc83fd58b +size 27297544 diff --git a/adapters/hf_download/davinci/checkpoint-939/chat_template.jinja b/adapters/hf_download/davinci/checkpoint-939/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/davinci/checkpoint-939/optimizer.pt b/adapters/hf_download/davinci/checkpoint-939/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a529a16b53b43ad929e3de5c69123dc37094a34 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ec721ffd7ea81911e8868ad42809f38c2ca2e1ee45363b256ba4c9f5338b28 +size 54745547 diff --git a/adapters/hf_download/davinci/checkpoint-939/rng_state.pth b/adapters/hf_download/davinci/checkpoint-939/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9c1c90eb296da11ecd46e4e4c9e4a1d4a58acb4 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6336e829a9ff8cce299b6fd18f96bdb30f66fa9d26a2d0e60c9f3abf68ca973d +size 14645 diff --git a/adapters/hf_download/davinci/checkpoint-939/scheduler.pt b/adapters/hf_download/davinci/checkpoint-939/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c383ba0bd9e9b0a87e222bb556a1972e7cd582 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85b9d8d75b43f2deffbdf4c4ecce548860c65bc59c665b7c0dfc2918984f3a7 +size 1465 diff --git a/adapters/hf_download/davinci/checkpoint-939/tokenizer.json b/adapters/hf_download/davinci/checkpoint-939/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/davinci/checkpoint-939/tokenizer_config.json b/adapters/hf_download/davinci/checkpoint-939/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/davinci/checkpoint-939/trainer_state.json b/adapters/hf_download/davinci/checkpoint-939/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d2552641bece9fc1ad56230c3c633386f3e8e0a8 --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/trainer_state.json @@ -0,0 +1,964 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 939, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 2.765847223997116, + "epoch": 0.032, + "grad_norm": 0.2578125, + "learning_rate": 6.206896551724138e-05, + "loss": 2.887763786315918, + "mean_token_accuracy": 0.46187404468655585, + "num_tokens": 56152.0, + "step": 10 + }, + { + "entropy": 2.2775970876216887, + "epoch": 0.064, + "grad_norm": 0.2236328125, + "learning_rate": 0.00013103448275862068, + "loss": 2.460337448120117, + "mean_token_accuracy": 0.506013386696577, + "num_tokens": 112587.0, + "step": 20 + }, + { + "entropy": 1.8153630286455154, + "epoch": 0.096, + "grad_norm": 0.27734375, + "learning_rate": 0.0002, + "loss": 1.7399822235107423, + "mean_token_accuracy": 0.6103868752717971, + "num_tokens": 168621.0, + "step": 30 + }, + { + "entropy": 1.185289441049099, + "epoch": 0.128, + "grad_norm": 0.30859375, + "learning_rate": 0.0001978021978021978, + "loss": 1.1186148643493652, + "mean_token_accuracy": 0.7334396600723266, + "num_tokens": 224707.0, + "step": 40 + }, + { + "entropy": 0.8306711494922638, + "epoch": 0.16, + "grad_norm": 0.291015625, + "learning_rate": 0.00019560439560439562, + "loss": 0.7544202327728271, + "mean_token_accuracy": 0.8217264339327812, + "num_tokens": 281529.0, + "step": 50 + }, + { + "entropy": 0.5289712496101856, + "epoch": 0.192, + "grad_norm": 0.3046875, + "learning_rate": 0.00019340659340659342, + "loss": 0.452878475189209, + "mean_token_accuracy": 0.8946282967925072, + "num_tokens": 338008.0, + "step": 60 + }, + { + "entropy": 0.34988002628088, + "epoch": 0.224, + "grad_norm": 0.2734375, + "learning_rate": 0.00019120879120879122, + "loss": 0.29230058193206787, + "mean_token_accuracy": 0.9343003541231155, + "num_tokens": 394904.0, + "step": 70 + }, + { + "entropy": 0.25185412392020223, + "epoch": 0.256, + "grad_norm": 0.251953125, + "learning_rate": 0.00018901098901098903, + "loss": 0.20802268981933594, + "mean_token_accuracy": 0.9522816658020019, + "num_tokens": 451161.0, + "step": 80 + }, + { + "entropy": 0.2018993068486452, + "epoch": 0.288, + "grad_norm": 0.244140625, + "learning_rate": 0.00018681318681318683, + "loss": 0.17179200649261475, + "mean_token_accuracy": 0.9587775945663453, + "num_tokens": 507727.0, + "step": 90 + }, + { + "entropy": 0.16806554533541201, + "epoch": 0.32, + "grad_norm": 0.2158203125, + "learning_rate": 0.00018461538461538463, + "loss": 0.14763951301574707, + "mean_token_accuracy": 0.9639375448226929, + "num_tokens": 564343.0, + "step": 100 + }, + { + "entropy": 0.14694931916892529, + "epoch": 0.352, + "grad_norm": 0.185546875, + "learning_rate": 0.0001824175824175824, + "loss": 0.127738356590271, + "mean_token_accuracy": 0.966508974134922, + "num_tokens": 620780.0, + "step": 110 + }, + { + "entropy": 0.13702088352292777, + "epoch": 0.384, + "grad_norm": 0.201171875, + "learning_rate": 0.00018021978021978024, + "loss": 0.1153560996055603, + "mean_token_accuracy": 0.9671898797154427, + "num_tokens": 676485.0, + "step": 120 + }, + { + "entropy": 0.12865546997636557, + "epoch": 0.416, + "grad_norm": 0.091796875, + "learning_rate": 0.00017802197802197802, + "loss": 0.10538246631622314, + "mean_token_accuracy": 0.9685350403189659, + "num_tokens": 732104.0, + "step": 130 + }, + { + "entropy": 0.11221796181052923, + "epoch": 0.448, + "grad_norm": 0.1220703125, + "learning_rate": 0.00017582417582417582, + "loss": 0.09550263285636902, + "mean_token_accuracy": 0.9704204052686691, + "num_tokens": 788648.0, + "step": 140 + }, + { + "entropy": 0.11187596172094345, + "epoch": 0.48, + "grad_norm": 0.142578125, + "learning_rate": 0.00017362637362637365, + "loss": 0.09267887473106384, + "mean_token_accuracy": 0.9708487093448639, + "num_tokens": 845277.0, + "step": 150 + }, + { + "entropy": 0.10449027251452207, + "epoch": 0.512, + "grad_norm": 0.11474609375, + "learning_rate": 0.00017142857142857143, + "loss": 0.09188109636306763, + "mean_token_accuracy": 0.9701150968670845, + "num_tokens": 901601.0, + "step": 160 + }, + { + "entropy": 0.10061556100845337, + "epoch": 0.544, + "grad_norm": 0.078125, + "learning_rate": 0.00016923076923076923, + "loss": 0.08688170909881592, + "mean_token_accuracy": 0.9714163467288017, + "num_tokens": 958510.0, + "step": 170 + }, + { + "entropy": 0.09703337252140046, + "epoch": 0.576, + "grad_norm": 0.11865234375, + "learning_rate": 0.00016703296703296706, + "loss": 0.08396151661872864, + "mean_token_accuracy": 0.9724744081497192, + "num_tokens": 1014706.0, + "step": 180 + }, + { + "entropy": 0.09241664204746484, + "epoch": 0.608, + "grad_norm": 0.078125, + "learning_rate": 0.00016483516483516484, + "loss": 0.08444164395332336, + "mean_token_accuracy": 0.9721407666802406, + "num_tokens": 1071133.0, + "step": 190 + }, + { + "entropy": 0.09338212702423335, + "epoch": 0.64, + "grad_norm": 0.1142578125, + "learning_rate": 0.00016263736263736264, + "loss": 0.08270348310470581, + "mean_token_accuracy": 0.9724765837192535, + "num_tokens": 1127600.0, + "step": 200 + }, + { + "entropy": 0.09137626234441995, + "epoch": 0.672, + "grad_norm": 0.07275390625, + "learning_rate": 0.00016043956043956044, + "loss": 0.08120843768119812, + "mean_token_accuracy": 0.9727972850203515, + "num_tokens": 1183826.0, + "step": 210 + }, + { + "entropy": 0.08943495023995637, + "epoch": 0.704, + "grad_norm": 0.09228515625, + "learning_rate": 0.00015824175824175824, + "loss": 0.0806293785572052, + "mean_token_accuracy": 0.9729145392775536, + "num_tokens": 1240123.0, + "step": 220 + }, + { + "entropy": 0.08839260842651128, + "epoch": 0.736, + "grad_norm": 0.1171875, + "learning_rate": 0.00015604395604395605, + "loss": 0.07906079888343812, + "mean_token_accuracy": 0.9728850305080414, + "num_tokens": 1296696.0, + "step": 230 + }, + { + "entropy": 0.08858597576618195, + "epoch": 0.768, + "grad_norm": 0.1552734375, + "learning_rate": 0.00015384615384615385, + "loss": 0.08044076561927796, + "mean_token_accuracy": 0.9724162057042122, + "num_tokens": 1352831.0, + "step": 240 + }, + { + "entropy": 0.09007721468806267, + "epoch": 0.8, + "grad_norm": 0.10107421875, + "learning_rate": 0.00015164835164835165, + "loss": 0.08158640861511231, + "mean_token_accuracy": 0.9722792387008667, + "num_tokens": 1409271.0, + "step": 250 + }, + { + "entropy": 0.08655472807586193, + "epoch": 0.832, + "grad_norm": 0.07373046875, + "learning_rate": 0.00014945054945054946, + "loss": 0.08008719682693481, + "mean_token_accuracy": 0.9734297141432762, + "num_tokens": 1465271.0, + "step": 260 + }, + { + "entropy": 0.08689612131565809, + "epoch": 0.864, + "grad_norm": 0.1416015625, + "learning_rate": 0.00014725274725274726, + "loss": 0.07870798110961914, + "mean_token_accuracy": 0.9730307757854462, + "num_tokens": 1521295.0, + "step": 270 + }, + { + "entropy": 0.08382895905524493, + "epoch": 0.896, + "grad_norm": 0.09033203125, + "learning_rate": 0.00014505494505494506, + "loss": 0.07732324004173279, + "mean_token_accuracy": 0.9730261951684952, + "num_tokens": 1577651.0, + "step": 280 + }, + { + "entropy": 0.08625071458518505, + "epoch": 0.928, + "grad_norm": 0.095703125, + "learning_rate": 0.00014285714285714287, + "loss": 0.07772318720817566, + "mean_token_accuracy": 0.9722341999411583, + "num_tokens": 1633578.0, + "step": 290 + }, + { + "entropy": 0.08320586234331132, + "epoch": 0.96, + "grad_norm": 0.0654296875, + "learning_rate": 0.00014065934065934067, + "loss": 0.077446448802948, + "mean_token_accuracy": 0.972867003083229, + "num_tokens": 1690062.0, + "step": 300 + }, + { + "entropy": 0.08028208408504725, + "epoch": 0.992, + "grad_norm": 0.052001953125, + "learning_rate": 0.00013846153846153847, + "loss": 0.07448889017105102, + "mean_token_accuracy": 0.9736120477318764, + "num_tokens": 1747161.0, + "step": 310 + }, + { + "entropy": 0.08117271979388438, + "epoch": 1.0224, + "grad_norm": 0.072265625, + "learning_rate": 0.00013626373626373628, + "loss": 0.0744770348072052, + "mean_token_accuracy": 0.9738528257922122, + "num_tokens": 1800329.0, + "step": 320 + }, + { + "entropy": 0.080937241576612, + "epoch": 1.0544, + "grad_norm": 0.061767578125, + "learning_rate": 0.00013406593406593405, + "loss": 0.0741479218006134, + "mean_token_accuracy": 0.9734442710876465, + "num_tokens": 1856800.0, + "step": 330 + }, + { + "entropy": 0.07824601717293263, + "epoch": 1.0864, + "grad_norm": 0.06103515625, + "learning_rate": 0.00013186813186813188, + "loss": 0.07381554841995239, + "mean_token_accuracy": 0.973892730474472, + "num_tokens": 1912949.0, + "step": 340 + }, + { + "entropy": 0.0771486822515726, + "epoch": 1.1184, + "grad_norm": 0.060302734375, + "learning_rate": 0.0001296703296703297, + "loss": 0.0723546326160431, + "mean_token_accuracy": 0.974125075340271, + "num_tokens": 1969412.0, + "step": 350 + }, + { + "entropy": 0.07591825406998395, + "epoch": 1.1504, + "grad_norm": 0.052734375, + "learning_rate": 0.00012747252747252746, + "loss": 0.07068771123886108, + "mean_token_accuracy": 0.9741279140114785, + "num_tokens": 2025544.0, + "step": 360 + }, + { + "entropy": 0.0768967004492879, + "epoch": 1.1824, + "grad_norm": 0.0517578125, + "learning_rate": 0.00012527472527472527, + "loss": 0.07226019501686096, + "mean_token_accuracy": 0.974024161696434, + "num_tokens": 2082060.0, + "step": 370 + }, + { + "entropy": 0.07532943487167358, + "epoch": 1.2144, + "grad_norm": 0.0693359375, + "learning_rate": 0.0001230769230769231, + "loss": 0.07127081751823425, + "mean_token_accuracy": 0.9739077508449554, + "num_tokens": 2138526.0, + "step": 380 + }, + { + "entropy": 0.07546288054436445, + "epoch": 1.2464, + "grad_norm": 0.0732421875, + "learning_rate": 0.00012087912087912087, + "loss": 0.0715237319469452, + "mean_token_accuracy": 0.974101935327053, + "num_tokens": 2194683.0, + "step": 390 + }, + { + "entropy": 0.07725638337433338, + "epoch": 1.2784, + "grad_norm": 0.049560546875, + "learning_rate": 0.00011868131868131869, + "loss": 0.07198636531829834, + "mean_token_accuracy": 0.9740697085857392, + "num_tokens": 2251274.0, + "step": 400 + }, + { + "entropy": 0.07509954180568457, + "epoch": 1.3104, + "grad_norm": 0.1591796875, + "learning_rate": 0.0001164835164835165, + "loss": 0.07245813012123108, + "mean_token_accuracy": 0.97386264950037, + "num_tokens": 2307625.0, + "step": 410 + }, + { + "entropy": 0.07573851495981217, + "epoch": 1.3424, + "grad_norm": 0.11572265625, + "learning_rate": 0.00011428571428571428, + "loss": 0.07237505316734313, + "mean_token_accuracy": 0.9742786347866058, + "num_tokens": 2363944.0, + "step": 420 + }, + { + "entropy": 0.07536402009427548, + "epoch": 1.3744, + "grad_norm": 0.07861328125, + "learning_rate": 0.0001120879120879121, + "loss": 0.07097623944282531, + "mean_token_accuracy": 0.9736705645918846, + "num_tokens": 2420074.0, + "step": 430 + }, + { + "entropy": 0.07416129969060421, + "epoch": 1.4064, + "grad_norm": 0.052734375, + "learning_rate": 0.0001098901098901099, + "loss": 0.07140442728996277, + "mean_token_accuracy": 0.9747859939932824, + "num_tokens": 2476657.0, + "step": 440 + }, + { + "entropy": 0.07501455284655094, + "epoch": 1.4384000000000001, + "grad_norm": 0.05712890625, + "learning_rate": 0.0001076923076923077, + "loss": 0.07142727375030518, + "mean_token_accuracy": 0.9742778673768043, + "num_tokens": 2533642.0, + "step": 450 + }, + { + "entropy": 0.07456400785595178, + "epoch": 1.4704, + "grad_norm": 0.04736328125, + "learning_rate": 0.0001054945054945055, + "loss": 0.06932693123817443, + "mean_token_accuracy": 0.9749433383345604, + "num_tokens": 2590615.0, + "step": 460 + }, + { + "entropy": 0.07349070943892003, + "epoch": 1.5024, + "grad_norm": 0.0634765625, + "learning_rate": 0.00010329670329670331, + "loss": 0.06970517039299011, + "mean_token_accuracy": 0.9744679152965545, + "num_tokens": 2647074.0, + "step": 470 + }, + { + "entropy": 0.07532282676547766, + "epoch": 1.5344, + "grad_norm": 0.0498046875, + "learning_rate": 0.0001010989010989011, + "loss": 0.07047909498214722, + "mean_token_accuracy": 0.9740379452705383, + "num_tokens": 2703311.0, + "step": 480 + }, + { + "entropy": 0.07352385744452476, + "epoch": 1.5664, + "grad_norm": 0.05126953125, + "learning_rate": 9.89010989010989e-05, + "loss": 0.07030070424079896, + "mean_token_accuracy": 0.9743834063410759, + "num_tokens": 2759737.0, + "step": 490 + }, + { + "entropy": 0.07334190551191569, + "epoch": 1.5984, + "grad_norm": 0.050048828125, + "learning_rate": 9.670329670329671e-05, + "loss": 0.06969634890556335, + "mean_token_accuracy": 0.9740354612469673, + "num_tokens": 2815903.0, + "step": 500 + }, + { + "entropy": 0.07266121916472912, + "epoch": 1.6303999999999998, + "grad_norm": 0.0615234375, + "learning_rate": 9.450549450549451e-05, + "loss": 0.06949952840805054, + "mean_token_accuracy": 0.9742880925536156, + "num_tokens": 2872194.0, + "step": 510 + }, + { + "entropy": 0.07272388003766536, + "epoch": 1.6623999999999999, + "grad_norm": 0.076171875, + "learning_rate": 9.230769230769232e-05, + "loss": 0.06940392851829529, + "mean_token_accuracy": 0.9741565704345703, + "num_tokens": 2928523.0, + "step": 520 + }, + { + "entropy": 0.07339652627706528, + "epoch": 1.6944, + "grad_norm": 0.0595703125, + "learning_rate": 9.010989010989012e-05, + "loss": 0.06963216066360474, + "mean_token_accuracy": 0.9739155307412147, + "num_tokens": 2984536.0, + "step": 530 + }, + { + "entropy": 0.07244944609701634, + "epoch": 1.7264, + "grad_norm": 0.055908203125, + "learning_rate": 8.791208791208791e-05, + "loss": 0.06880267858505248, + "mean_token_accuracy": 0.9742810636758804, + "num_tokens": 3041273.0, + "step": 540 + }, + { + "entropy": 0.07108333166688681, + "epoch": 1.7584, + "grad_norm": 0.046630859375, + "learning_rate": 8.571428571428571e-05, + "loss": 0.06817492246627807, + "mean_token_accuracy": 0.9747302502393722, + "num_tokens": 3097967.0, + "step": 550 + }, + { + "entropy": 0.07293068561702967, + "epoch": 1.7904, + "grad_norm": 0.047119140625, + "learning_rate": 8.351648351648353e-05, + "loss": 0.06863305568695069, + "mean_token_accuracy": 0.9745977595448494, + "num_tokens": 3154269.0, + "step": 560 + }, + { + "entropy": 0.07215537298470735, + "epoch": 1.8224, + "grad_norm": 0.044677734375, + "learning_rate": 8.131868131868132e-05, + "loss": 0.0701857328414917, + "mean_token_accuracy": 0.9745570942759514, + "num_tokens": 3210196.0, + "step": 570 + }, + { + "entropy": 0.07419390864670276, + "epoch": 1.8544, + "grad_norm": 0.0498046875, + "learning_rate": 7.912087912087912e-05, + "loss": 0.06985241174697876, + "mean_token_accuracy": 0.9743385434150695, + "num_tokens": 3266168.0, + "step": 580 + }, + { + "entropy": 0.07155264187604189, + "epoch": 1.8864, + "grad_norm": 0.047119140625, + "learning_rate": 7.692307692307693e-05, + "loss": 0.06801514625549317, + "mean_token_accuracy": 0.9741999164223671, + "num_tokens": 3322720.0, + "step": 590 + }, + { + "entropy": 0.07301885243505239, + "epoch": 1.9184, + "grad_norm": 0.052978515625, + "learning_rate": 7.472527472527473e-05, + "loss": 0.06798295974731446, + "mean_token_accuracy": 0.9746290504932403, + "num_tokens": 3379106.0, + "step": 600 + }, + { + "entropy": 0.07121691349893808, + "epoch": 1.9504000000000001, + "grad_norm": 0.04736328125, + "learning_rate": 7.252747252747253e-05, + "loss": 0.068598073720932, + "mean_token_accuracy": 0.9740164309740067, + "num_tokens": 3435455.0, + "step": 610 + }, + { + "entropy": 0.07093659751117229, + "epoch": 1.9824000000000002, + "grad_norm": 0.04345703125, + "learning_rate": 7.032967032967034e-05, + "loss": 0.06840575337409974, + "mean_token_accuracy": 0.9743095189332962, + "num_tokens": 3491913.0, + "step": 620 + }, + { + "entropy": 0.07206394935124799, + "epoch": 2.0128, + "grad_norm": 0.046142578125, + "learning_rate": 6.813186813186814e-05, + "loss": 0.06758478283882141, + "mean_token_accuracy": 0.974631174614555, + "num_tokens": 3545532.0, + "step": 630 + }, + { + "entropy": 0.07083711996674538, + "epoch": 2.0448, + "grad_norm": 0.043701171875, + "learning_rate": 6.593406593406594e-05, + "loss": 0.06740251779556275, + "mean_token_accuracy": 0.9746132045984268, + "num_tokens": 3601750.0, + "step": 640 + }, + { + "entropy": 0.06940150745213032, + "epoch": 2.0768, + "grad_norm": 0.044677734375, + "learning_rate": 6.373626373626373e-05, + "loss": 0.06656463742256165, + "mean_token_accuracy": 0.9751317039132118, + "num_tokens": 3658200.0, + "step": 650 + }, + { + "entropy": 0.06972125004976988, + "epoch": 2.1088, + "grad_norm": 0.053955078125, + "learning_rate": 6.153846153846155e-05, + "loss": 0.06672356724739074, + "mean_token_accuracy": 0.9748880088329315, + "num_tokens": 3714571.0, + "step": 660 + }, + { + "entropy": 0.07049978096038104, + "epoch": 2.1408, + "grad_norm": 0.048583984375, + "learning_rate": 5.9340659340659345e-05, + "loss": 0.06648544073104859, + "mean_token_accuracy": 0.9752828374505043, + "num_tokens": 3771237.0, + "step": 670 + }, + { + "entropy": 0.07016281113028526, + "epoch": 2.1728, + "grad_norm": 0.053466796875, + "learning_rate": 5.714285714285714e-05, + "loss": 0.06775825023651123, + "mean_token_accuracy": 0.9741855576634407, + "num_tokens": 3827333.0, + "step": 680 + }, + { + "entropy": 0.0697398909367621, + "epoch": 2.2048, + "grad_norm": 0.0478515625, + "learning_rate": 5.494505494505495e-05, + "loss": 0.06558757424354553, + "mean_token_accuracy": 0.9750754848122597, + "num_tokens": 3884047.0, + "step": 690 + }, + { + "entropy": 0.07038046848028898, + "epoch": 2.2368, + "grad_norm": 0.0537109375, + "learning_rate": 5.274725274725275e-05, + "loss": 0.06697022914886475, + "mean_token_accuracy": 0.9747041672468185, + "num_tokens": 3939674.0, + "step": 700 + }, + { + "entropy": 0.06939303996041417, + "epoch": 2.2688, + "grad_norm": 0.049560546875, + "learning_rate": 5.054945054945055e-05, + "loss": 0.06623688936233521, + "mean_token_accuracy": 0.9746327564120293, + "num_tokens": 3995336.0, + "step": 710 + }, + { + "entropy": 0.06911874655634165, + "epoch": 2.3008, + "grad_norm": 0.05078125, + "learning_rate": 4.8351648351648355e-05, + "loss": 0.06572118401527405, + "mean_token_accuracy": 0.9751049995422363, + "num_tokens": 4052061.0, + "step": 720 + }, + { + "entropy": 0.07011389117687941, + "epoch": 2.3327999999999998, + "grad_norm": 0.109375, + "learning_rate": 4.615384615384616e-05, + "loss": 0.06583920121192932, + "mean_token_accuracy": 0.9755928933620452, + "num_tokens": 4108527.0, + "step": 730 + }, + { + "entropy": 0.0693218169733882, + "epoch": 2.3648, + "grad_norm": 0.043212890625, + "learning_rate": 4.3956043956043955e-05, + "loss": 0.06613236665725708, + "mean_token_accuracy": 0.9750977262854577, + "num_tokens": 4164949.0, + "step": 740 + }, + { + "entropy": 0.06911731557920575, + "epoch": 2.3968, + "grad_norm": 0.07177734375, + "learning_rate": 4.1758241758241765e-05, + "loss": 0.06604759097099304, + "mean_token_accuracy": 0.9754573971033096, + "num_tokens": 4221691.0, + "step": 750 + }, + { + "entropy": 0.06993914116173983, + "epoch": 2.4288, + "grad_norm": 0.04833984375, + "learning_rate": 3.956043956043956e-05, + "loss": 0.06716731190681458, + "mean_token_accuracy": 0.975093024969101, + "num_tokens": 4278417.0, + "step": 760 + }, + { + "entropy": 0.06964065954089164, + "epoch": 2.4608, + "grad_norm": 0.048095703125, + "learning_rate": 3.7362637362637365e-05, + "loss": 0.06574493050575256, + "mean_token_accuracy": 0.9751413717865944, + "num_tokens": 4334891.0, + "step": 770 + }, + { + "entropy": 0.07056677304208278, + "epoch": 2.4928, + "grad_norm": 0.051513671875, + "learning_rate": 3.516483516483517e-05, + "loss": 0.0663109302520752, + "mean_token_accuracy": 0.975189596414566, + "num_tokens": 4390612.0, + "step": 780 + }, + { + "entropy": 0.06927145700901746, + "epoch": 2.5248, + "grad_norm": 0.052978515625, + "learning_rate": 3.296703296703297e-05, + "loss": 0.06642587780952454, + "mean_token_accuracy": 0.9745640248060227, + "num_tokens": 4446472.0, + "step": 790 + }, + { + "entropy": 0.07022066749632358, + "epoch": 2.5568, + "grad_norm": 0.053466796875, + "learning_rate": 3.0769230769230774e-05, + "loss": 0.06618784666061402, + "mean_token_accuracy": 0.9756692573428154, + "num_tokens": 4502636.0, + "step": 800 + }, + { + "entropy": 0.06819943720474839, + "epoch": 2.5888, + "grad_norm": 0.046630859375, + "learning_rate": 2.857142857142857e-05, + "loss": 0.06411008238792419, + "mean_token_accuracy": 0.9754757001996041, + "num_tokens": 4559884.0, + "step": 810 + }, + { + "entropy": 0.06905186725780368, + "epoch": 2.6208, + "grad_norm": 0.046875, + "learning_rate": 2.6373626373626374e-05, + "loss": 0.06473379135131836, + "mean_token_accuracy": 0.9757311746478081, + "num_tokens": 4617030.0, + "step": 820 + }, + { + "entropy": 0.06890011681243777, + "epoch": 2.6528, + "grad_norm": 0.0517578125, + "learning_rate": 2.4175824175824177e-05, + "loss": 0.06536944508552552, + "mean_token_accuracy": 0.9754818379878998, + "num_tokens": 4673956.0, + "step": 830 + }, + { + "entropy": 0.07007441222667694, + "epoch": 2.6848, + "grad_norm": 0.0576171875, + "learning_rate": 2.1978021978021977e-05, + "loss": 0.06617265939712524, + "mean_token_accuracy": 0.9750760287046433, + "num_tokens": 4729829.0, + "step": 840 + }, + { + "entropy": 0.06897767269983887, + "epoch": 2.7168, + "grad_norm": 0.050048828125, + "learning_rate": 1.978021978021978e-05, + "loss": 0.06520164012908936, + "mean_token_accuracy": 0.9748285204172135, + "num_tokens": 4785877.0, + "step": 850 + }, + { + "entropy": 0.06972532533109188, + "epoch": 2.7488, + "grad_norm": 0.0498046875, + "learning_rate": 1.7582417582417584e-05, + "loss": 0.06575180888175965, + "mean_token_accuracy": 0.9751192405819893, + "num_tokens": 4842245.0, + "step": 860 + }, + { + "entropy": 0.0695738073438406, + "epoch": 2.7808, + "grad_norm": 0.05322265625, + "learning_rate": 1.5384615384615387e-05, + "loss": 0.06541760563850403, + "mean_token_accuracy": 0.9751872330904007, + "num_tokens": 4898430.0, + "step": 870 + }, + { + "entropy": 0.06915857251733541, + "epoch": 2.8128, + "grad_norm": 0.0517578125, + "learning_rate": 1.3186813186813187e-05, + "loss": 0.06457725763320923, + "mean_token_accuracy": 0.9754222899675369, + "num_tokens": 4954992.0, + "step": 880 + }, + { + "entropy": 0.06952376030385495, + "epoch": 2.8448, + "grad_norm": 0.05078125, + "learning_rate": 1.0989010989010989e-05, + "loss": 0.06499672532081605, + "mean_token_accuracy": 0.9750340938568115, + "num_tokens": 5011180.0, + "step": 890 + }, + { + "entropy": 0.07051521427929401, + "epoch": 2.8768000000000002, + "grad_norm": 0.050537109375, + "learning_rate": 8.791208791208792e-06, + "loss": 0.06588171124458313, + "mean_token_accuracy": 0.9754653736948967, + "num_tokens": 5067372.0, + "step": 900 + }, + { + "entropy": 0.0689331229776144, + "epoch": 2.9088000000000003, + "grad_norm": 0.05322265625, + "learning_rate": 6.5934065934065935e-06, + "loss": 0.06466820240020751, + "mean_token_accuracy": 0.9759261250495911, + "num_tokens": 5124244.0, + "step": 910 + }, + { + "entropy": 0.06952993655577303, + "epoch": 2.9408, + "grad_norm": 0.046142578125, + "learning_rate": 4.395604395604396e-06, + "loss": 0.0658172309398651, + "mean_token_accuracy": 0.9749145016074181, + "num_tokens": 5180364.0, + "step": 920 + }, + { + "entropy": 0.06960295150056481, + "epoch": 2.9728, + "grad_norm": 0.05126953125, + "learning_rate": 2.197802197802198e-06, + "loss": 0.06470752358436585, + "mean_token_accuracy": 0.9757384702563285, + "num_tokens": 5237172.0, + "step": 930 + } + ], + "logging_steps": 10, + "max_steps": 939, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.4584794460995584e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/adapters/hf_download/davinci/checkpoint-939/training_args.bin b/adapters/hf_download/davinci/checkpoint-939/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e381391affd5717baa5678f5cd89f25daccbe0e --- /dev/null +++ b/adapters/hf_download/davinci/checkpoint-939/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f21cb0f4416a41acd8ff9feb8c0f995a14287a039f7c3dc536cda4414e290f8 +size 5585 diff --git a/adapters/hf_download/davinci/tokenizer.json b/adapters/hf_download/davinci/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/davinci/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/davinci/tokenizer_config.json b/adapters/hf_download/davinci/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/davinci/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/empathy/adapter_config.json b/adapters/hf_download/empathy/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e436105a860fe50b72d2cc8f1e1b7300e6d03116 --- /dev/null +++ b/adapters/hf_download/empathy/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "o_proj", + "k_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/empathy/adapter_model.safetensors b/adapters/hf_download/empathy/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acfccf7bc054e8763450e24a5d3b4b634b3723d8 --- /dev/null +++ b/adapters/hf_download/empathy/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae48e5ab42f5024f6e9ac24cbbc8e54d07a151740a4c6c5ea834fcaf78101d45 +size 27297544 diff --git a/adapters/hf_download/multi_perspective/adapter_config.json b/adapters/hf_download/multi_perspective/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8b2de52cc3e7a37fd794f63fc3ef18381217d301 --- /dev/null +++ b/adapters/hf_download/multi_perspective/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj", + "k_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/multi_perspective/adapter_model.safetensors b/adapters/hf_download/multi_perspective/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb3e4afa6a3bfdd84d5eb8e83c2eba10faa5aae8 --- /dev/null +++ b/adapters/hf_download/multi_perspective/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20e769754d0d81f77712a36fe50ebc10dc08309e884871c6efb12f3497d6200 +size 27297544 diff --git a/adapters/hf_download/newton/README.md b/adapters/hf_download/newton/README.md new file mode 100644 index 0000000000000000000000000000000000000000..17d7bc43d9aae66692937db54d36ced3b88978ce --- /dev/null +++ b/adapters/hf_download/newton/README.md @@ -0,0 +1,62 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +model_name: newton +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +licence: license +pipeline_tag: text-generation +--- + +# Model Card for newton + +This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with SFT. + +### Framework versions + +- PEFT 0.18.1 +- TRL: 0.29.0 +- Transformers: 5.3.0 +- Pytorch: 2.10.0 +- Datasets: 4.6.1 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/adapters/hf_download/newton/adapter_config.json b/adapters/hf_download/newton/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/newton/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/newton/adapter_model.safetensors b/adapters/hf_download/newton/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea7158bf5b63e323655dd7f350a2256b9523d741 --- /dev/null +++ b/adapters/hf_download/newton/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323635297b5e0c773a26c4451697f85a4ff3020e8864a138ba799a14da2627a2 +size 27297544 diff --git a/adapters/hf_download/newton/chat_template.jinja b/adapters/hf_download/newton/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/newton/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/newton/checkpoint-1000/README.md b/adapters/hf_download/newton/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..35f6e0e06fbb5355b8afea90d8f546c40fb6d50e --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/README.md @@ -0,0 +1,209 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.18.1 \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-1000/adapter_config.json b/adapters/hf_download/newton/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-1000/adapter_model.safetensors b/adapters/hf_download/newton/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..649b04103e55e8c532b5509a0d37a49428e4de5a --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41c14f1336f835fccc7fe9f0c53b2a0966f2388840ee6241fffd86a6a65108a +size 27297544 diff --git a/adapters/hf_download/newton/checkpoint-1000/chat_template.jinja b/adapters/hf_download/newton/checkpoint-1000/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/newton/checkpoint-1000/optimizer.pt b/adapters/hf_download/newton/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..638aebdf1eb9e767b5c0853f5e088e589b71c465 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e023b856408604b2dac8f46a59a2c413f9c5171d8a8dd0bcb2e1266e8a17e0 +size 54745547 diff --git a/adapters/hf_download/newton/checkpoint-1000/rng_state.pth b/adapters/hf_download/newton/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..93e361eb513c28a7ccc3dd92396d95b630fd3bfe --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a9efb6a8371c0aa0c7c1f1395d8817f98251d4ccd6b17cd77847cecdf56a0b +size 14645 diff --git a/adapters/hf_download/newton/checkpoint-1000/scheduler.pt b/adapters/hf_download/newton/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f63d4aca91b727178ad90c0229133c94d96338ee --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ede3d2a514005ed80690b07770eb75aab9fd0b335517babd631dfbc1716d09fd +size 1465 diff --git a/adapters/hf_download/newton/checkpoint-1000/tokenizer.json b/adapters/hf_download/newton/checkpoint-1000/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/newton/checkpoint-1000/tokenizer_config.json b/adapters/hf_download/newton/checkpoint-1000/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/newton/checkpoint-1000/trainer_state.json b/adapters/hf_download/newton/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6483faff277dd6a8e5bc5d2b50c8b44addf8a890 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/trainer_state.json @@ -0,0 +1,1034 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.6666666666666665, + "eval_steps": 500, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 2.6570239067077637, + "epoch": 0.02666666666666667, + "grad_norm": 0.287109375, + "learning_rate": 5.294117647058824e-05, + "loss": 2.800247573852539, + "mean_token_accuracy": 0.4749053567647934, + "num_tokens": 56906.0, + "step": 10 + }, + { + "entropy": 2.2495410323143004, + "epoch": 0.05333333333333334, + "grad_norm": 0.265625, + "learning_rate": 0.00011176470588235294, + "loss": 2.4327199935913084, + "mean_token_accuracy": 0.5111239477992058, + "num_tokens": 113827.0, + "step": 20 + }, + { + "entropy": 1.8682004392147065, + "epoch": 0.08, + "grad_norm": 0.306640625, + "learning_rate": 0.00017058823529411766, + "loss": 1.789840316772461, + "mean_token_accuracy": 0.599884121119976, + "num_tokens": 170403.0, + "step": 30 + }, + { + "entropy": 1.2546741724014283, + "epoch": 0.10666666666666667, + "grad_norm": 0.306640625, + "learning_rate": 0.00019908340971585702, + "loss": 1.2151795387268067, + "mean_token_accuracy": 0.7106126025319099, + "num_tokens": 227456.0, + "step": 40 + }, + { + "entropy": 0.8836664661765099, + "epoch": 0.13333333333333333, + "grad_norm": 0.28515625, + "learning_rate": 0.00019725022914757106, + "loss": 0.8311976432800293, + "mean_token_accuracy": 0.7977700293064117, + "num_tokens": 284368.0, + "step": 50 + }, + { + "entropy": 0.6855858579277992, + "epoch": 0.16, + "grad_norm": 0.314453125, + "learning_rate": 0.00019541704857928507, + "loss": 0.6242359638214111, + "mean_token_accuracy": 0.847702169418335, + "num_tokens": 341357.0, + "step": 60 + }, + { + "entropy": 0.4690785683691502, + "epoch": 0.18666666666666668, + "grad_norm": 0.248046875, + "learning_rate": 0.00019358386801099912, + "loss": 0.40251870155334474, + "mean_token_accuracy": 0.9024116918444633, + "num_tokens": 398280.0, + "step": 70 + }, + { + "entropy": 0.34345744624733926, + "epoch": 0.21333333333333335, + "grad_norm": 0.27734375, + "learning_rate": 0.0001917506874427131, + "loss": 0.28333656787872313, + "mean_token_accuracy": 0.9320006996393204, + "num_tokens": 455232.0, + "step": 80 + }, + { + "entropy": 0.25451925955712795, + "epoch": 0.24, + "grad_norm": 0.208984375, + "learning_rate": 0.00018991750687442712, + "loss": 0.21085577011108397, + "mean_token_accuracy": 0.949009683728218, + "num_tokens": 511782.0, + "step": 90 + }, + { + "entropy": 0.19814539551734925, + "epoch": 0.26666666666666666, + "grad_norm": 0.296875, + "learning_rate": 0.00018808432630614116, + "loss": 0.1717105984687805, + "mean_token_accuracy": 0.9577329605817795, + "num_tokens": 568641.0, + "step": 100 + }, + { + "entropy": 0.18550167009234428, + "epoch": 0.29333333333333333, + "grad_norm": 0.21875, + "learning_rate": 0.00018625114573785518, + "loss": 0.15982584953308104, + "mean_token_accuracy": 0.9591923207044601, + "num_tokens": 626038.0, + "step": 110 + }, + { + "entropy": 0.16009770445525645, + "epoch": 0.32, + "grad_norm": 0.2109375, + "learning_rate": 0.00018441796516956922, + "loss": 0.12815338373184204, + "mean_token_accuracy": 0.9657398357987403, + "num_tokens": 682880.0, + "step": 120 + }, + { + "entropy": 0.14740683771669866, + "epoch": 0.3466666666666667, + "grad_norm": 0.2431640625, + "learning_rate": 0.00018258478460128323, + "loss": 0.1188442587852478, + "mean_token_accuracy": 0.9664651393890381, + "num_tokens": 739719.0, + "step": 130 + }, + { + "entropy": 0.13307180535048246, + "epoch": 0.37333333333333335, + "grad_norm": 0.1474609375, + "learning_rate": 0.00018075160403299728, + "loss": 0.11054203510284424, + "mean_token_accuracy": 0.9669812738895416, + "num_tokens": 795894.0, + "step": 140 + }, + { + "entropy": 0.12216594349592924, + "epoch": 0.4, + "grad_norm": 0.1240234375, + "learning_rate": 0.0001789184234647113, + "loss": 0.10401068925857544, + "mean_token_accuracy": 0.9683825269341468, + "num_tokens": 852124.0, + "step": 150 + }, + { + "entropy": 0.11619068495929241, + "epoch": 0.4266666666666667, + "grad_norm": 0.12060546875, + "learning_rate": 0.0001770852428964253, + "loss": 0.0976063370704651, + "mean_token_accuracy": 0.9695558726787568, + "num_tokens": 909328.0, + "step": 160 + }, + { + "entropy": 0.10669020470231771, + "epoch": 0.4533333333333333, + "grad_norm": 0.1279296875, + "learning_rate": 0.00017525206232813932, + "loss": 0.09338906407356262, + "mean_token_accuracy": 0.970247569680214, + "num_tokens": 966577.0, + "step": 170 + }, + { + "entropy": 0.10276608634740114, + "epoch": 0.48, + "grad_norm": 0.115234375, + "learning_rate": 0.00017341888175985334, + "loss": 0.09135337471961975, + "mean_token_accuracy": 0.9711026951670647, + "num_tokens": 1022961.0, + "step": 180 + }, + { + "entropy": 0.10297673251479864, + "epoch": 0.5066666666666667, + "grad_norm": 0.11474609375, + "learning_rate": 0.00017158570119156738, + "loss": 0.08887208104133607, + "mean_token_accuracy": 0.9709939315915108, + "num_tokens": 1079479.0, + "step": 190 + }, + { + "entropy": 0.09722564350813627, + "epoch": 0.5333333333333333, + "grad_norm": 0.1044921875, + "learning_rate": 0.0001697525206232814, + "loss": 0.08848196864128113, + "mean_token_accuracy": 0.9712936446070671, + "num_tokens": 1135784.0, + "step": 200 + }, + { + "entropy": 0.09498227294534445, + "epoch": 0.56, + "grad_norm": 0.2236328125, + "learning_rate": 0.00016791934005499544, + "loss": 0.08531092405319214, + "mean_token_accuracy": 0.9717509031295777, + "num_tokens": 1192723.0, + "step": 210 + }, + { + "entropy": 0.09660841915756464, + "epoch": 0.5866666666666667, + "grad_norm": 0.154296875, + "learning_rate": 0.00016608615948670945, + "loss": 0.08432384729385375, + "mean_token_accuracy": 0.9723995119333267, + "num_tokens": 1248974.0, + "step": 220 + }, + { + "entropy": 0.09139632768929004, + "epoch": 0.6133333333333333, + "grad_norm": 0.08203125, + "learning_rate": 0.0001642529789184235, + "loss": 0.08340675234794617, + "mean_token_accuracy": 0.9725200146436691, + "num_tokens": 1306125.0, + "step": 230 + }, + { + "entropy": 0.09041857812553644, + "epoch": 0.64, + "grad_norm": 0.0751953125, + "learning_rate": 0.0001624197983501375, + "loss": 0.08240053057670593, + "mean_token_accuracy": 0.9727400034666062, + "num_tokens": 1362509.0, + "step": 240 + }, + { + "entropy": 0.08917351886630058, + "epoch": 0.6666666666666666, + "grad_norm": 0.11181640625, + "learning_rate": 0.00016058661778185152, + "loss": 0.08038315176963806, + "mean_token_accuracy": 0.9722966447472572, + "num_tokens": 1419155.0, + "step": 250 + }, + { + "entropy": 0.08846015091985464, + "epoch": 0.6933333333333334, + "grad_norm": 0.07421875, + "learning_rate": 0.00015875343721356554, + "loss": 0.08111950755119324, + "mean_token_accuracy": 0.9725704893469811, + "num_tokens": 1475233.0, + "step": 260 + }, + { + "entropy": 0.08615751322358847, + "epoch": 0.72, + "grad_norm": 0.103515625, + "learning_rate": 0.00015692025664527955, + "loss": 0.07856618165969849, + "mean_token_accuracy": 0.9734801158308983, + "num_tokens": 1531666.0, + "step": 270 + }, + { + "entropy": 0.08350808713585138, + "epoch": 0.7466666666666667, + "grad_norm": 0.0869140625, + "learning_rate": 0.0001550870760769936, + "loss": 0.07699183821678161, + "mean_token_accuracy": 0.9737285181879998, + "num_tokens": 1588686.0, + "step": 280 + }, + { + "entropy": 0.08553262427449226, + "epoch": 0.7733333333333333, + "grad_norm": 0.140625, + "learning_rate": 0.0001532538955087076, + "loss": 0.07849866151809692, + "mean_token_accuracy": 0.9727597609162331, + "num_tokens": 1645610.0, + "step": 290 + }, + { + "entropy": 0.08688175324350596, + "epoch": 0.8, + "grad_norm": 0.1318359375, + "learning_rate": 0.00015142071494042165, + "loss": 0.0791881263256073, + "mean_token_accuracy": 0.9728336438536644, + "num_tokens": 1702234.0, + "step": 300 + }, + { + "entropy": 0.08647099416702986, + "epoch": 0.8266666666666667, + "grad_norm": 0.076171875, + "learning_rate": 0.00014958753437213567, + "loss": 0.07916317582130432, + "mean_token_accuracy": 0.9720797210931778, + "num_tokens": 1758523.0, + "step": 310 + }, + { + "entropy": 0.08278416823595762, + "epoch": 0.8533333333333334, + "grad_norm": 0.076171875, + "learning_rate": 0.00014775435380384968, + "loss": 0.07689375281333924, + "mean_token_accuracy": 0.9735667318105697, + "num_tokens": 1815080.0, + "step": 320 + }, + { + "entropy": 0.08433555215597152, + "epoch": 0.88, + "grad_norm": 0.0888671875, + "learning_rate": 0.00014592117323556373, + "loss": 0.07733245491981507, + "mean_token_accuracy": 0.973043854534626, + "num_tokens": 1872283.0, + "step": 330 + }, + { + "entropy": 0.0831523710861802, + "epoch": 0.9066666666666666, + "grad_norm": 0.185546875, + "learning_rate": 0.00014408799266727771, + "loss": 0.07743646502494812, + "mean_token_accuracy": 0.9724773317575455, + "num_tokens": 1929120.0, + "step": 340 + }, + { + "entropy": 0.08173599634319544, + "epoch": 0.9333333333333333, + "grad_norm": 0.08447265625, + "learning_rate": 0.00014225481209899176, + "loss": 0.07464101910591125, + "mean_token_accuracy": 0.9732464775443077, + "num_tokens": 1986433.0, + "step": 350 + }, + { + "entropy": 0.08154450561851263, + "epoch": 0.96, + "grad_norm": 0.197265625, + "learning_rate": 0.00014042163153070577, + "loss": 0.07836683988571166, + "mean_token_accuracy": 0.9733009964227677, + "num_tokens": 2043465.0, + "step": 360 + }, + { + "entropy": 0.08830973766744137, + "epoch": 0.9866666666666667, + "grad_norm": 0.0634765625, + "learning_rate": 0.0001385884509624198, + "loss": 0.07805899381637574, + "mean_token_accuracy": 0.9734541475772858, + "num_tokens": 2100933.0, + "step": 370 + }, + { + "entropy": 0.08108338043093681, + "epoch": 1.0133333333333334, + "grad_norm": 0.05859375, + "learning_rate": 0.00013675527039413383, + "loss": 0.07582586407661437, + "mean_token_accuracy": 0.9734946370124817, + "num_tokens": 2157057.0, + "step": 380 + }, + { + "entropy": 0.0781314555555582, + "epoch": 1.04, + "grad_norm": 0.05078125, + "learning_rate": 0.00013492208982584784, + "loss": 0.0714304804801941, + "mean_token_accuracy": 0.975023752450943, + "num_tokens": 2214085.0, + "step": 390 + }, + { + "entropy": 0.07955040819942952, + "epoch": 1.0666666666666667, + "grad_norm": 0.08984375, + "learning_rate": 0.00013308890925756189, + "loss": 0.07331350445747375, + "mean_token_accuracy": 0.9737342849373818, + "num_tokens": 2270765.0, + "step": 400 + }, + { + "entropy": 0.07677881456911564, + "epoch": 1.0933333333333333, + "grad_norm": 0.07177734375, + "learning_rate": 0.0001312557286892759, + "loss": 0.07168130278587341, + "mean_token_accuracy": 0.9739445611834526, + "num_tokens": 2327512.0, + "step": 410 + }, + { + "entropy": 0.07667716387659311, + "epoch": 1.12, + "grad_norm": 0.0771484375, + "learning_rate": 0.00012942254812098992, + "loss": 0.07219807505607605, + "mean_token_accuracy": 0.9742562755942344, + "num_tokens": 2384423.0, + "step": 420 + }, + { + "entropy": 0.07681187009438872, + "epoch": 1.1466666666666667, + "grad_norm": 0.0615234375, + "learning_rate": 0.00012758936755270393, + "loss": 0.07280588746070862, + "mean_token_accuracy": 0.9735747814178467, + "num_tokens": 2441102.0, + "step": 430 + }, + { + "entropy": 0.07602620646357536, + "epoch": 1.1733333333333333, + "grad_norm": 0.06982421875, + "learning_rate": 0.00012575618698441797, + "loss": 0.07293958067893982, + "mean_token_accuracy": 0.9740705206990242, + "num_tokens": 2497642.0, + "step": 440 + }, + { + "entropy": 0.07798876240849495, + "epoch": 1.2, + "grad_norm": 0.07421875, + "learning_rate": 0.000123923006416132, + "loss": 0.07215467095375061, + "mean_token_accuracy": 0.9742186814546585, + "num_tokens": 2554273.0, + "step": 450 + }, + { + "entropy": 0.07671927772462368, + "epoch": 1.2266666666666666, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012208982584784603, + "loss": 0.07254356741905213, + "mean_token_accuracy": 0.9733539551496506, + "num_tokens": 2610932.0, + "step": 460 + }, + { + "entropy": 0.07502734698355198, + "epoch": 1.2533333333333334, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012025664527956005, + "loss": 0.07076438069343567, + "mean_token_accuracy": 0.9745794385671616, + "num_tokens": 2668226.0, + "step": 470 + }, + { + "entropy": 0.07516032289713621, + "epoch": 1.28, + "grad_norm": 0.045654296875, + "learning_rate": 0.00011842346471127406, + "loss": 0.0711740493774414, + "mean_token_accuracy": 0.9735412746667862, + "num_tokens": 2725180.0, + "step": 480 + }, + { + "entropy": 0.07623793687671424, + "epoch": 1.3066666666666666, + "grad_norm": 0.053955078125, + "learning_rate": 0.00011659028414298809, + "loss": 0.07199874520301819, + "mean_token_accuracy": 0.9739259093999862, + "num_tokens": 2782069.0, + "step": 490 + }, + { + "entropy": 0.07468608934432268, + "epoch": 1.3333333333333333, + "grad_norm": 0.046142578125, + "learning_rate": 0.0001147571035747021, + "loss": 0.07050397992134094, + "mean_token_accuracy": 0.9742979735136033, + "num_tokens": 2838772.0, + "step": 500 + }, + { + "entropy": 0.07314184289425611, + "epoch": 1.3599999999999999, + "grad_norm": 0.0732421875, + "learning_rate": 0.00011292392300641615, + "loss": 0.06992406845092773, + "mean_token_accuracy": 0.9748412847518921, + "num_tokens": 2896384.0, + "step": 510 + }, + { + "entropy": 0.07735273949801921, + "epoch": 1.3866666666666667, + "grad_norm": 0.042236328125, + "learning_rate": 0.00011109074243813016, + "loss": 0.07089330554008484, + "mean_token_accuracy": 0.973857656121254, + "num_tokens": 2953074.0, + "step": 520 + }, + { + "entropy": 0.07427110467106104, + "epoch": 1.4133333333333333, + "grad_norm": 0.05615234375, + "learning_rate": 0.00010925756186984419, + "loss": 0.07023302912712097, + "mean_token_accuracy": 0.9745061740279197, + "num_tokens": 3009599.0, + "step": 530 + }, + { + "entropy": 0.07496015410870313, + "epoch": 1.44, + "grad_norm": 0.04150390625, + "learning_rate": 0.0001074243813015582, + "loss": 0.07044907808303832, + "mean_token_accuracy": 0.97446711063385, + "num_tokens": 3065550.0, + "step": 540 + }, + { + "entropy": 0.07237969692796468, + "epoch": 1.4666666666666668, + "grad_norm": 0.0537109375, + "learning_rate": 0.00010559120073327222, + "loss": 0.06903309226036072, + "mean_token_accuracy": 0.9751396328210831, + "num_tokens": 3122339.0, + "step": 550 + }, + { + "entropy": 0.07292939173057675, + "epoch": 1.4933333333333334, + "grad_norm": 0.044921875, + "learning_rate": 0.00010375802016498626, + "loss": 0.06951733827590942, + "mean_token_accuracy": 0.9748973533511162, + "num_tokens": 3179284.0, + "step": 560 + }, + { + "entropy": 0.0735103216022253, + "epoch": 1.52, + "grad_norm": 0.0595703125, + "learning_rate": 0.00010192483959670028, + "loss": 0.06886410713195801, + "mean_token_accuracy": 0.9742336764931678, + "num_tokens": 3236634.0, + "step": 570 + }, + { + "entropy": 0.07244595270603896, + "epoch": 1.5466666666666666, + "grad_norm": 0.049072265625, + "learning_rate": 0.0001000916590284143, + "loss": 0.06925945878028869, + "mean_token_accuracy": 0.9746079474687577, + "num_tokens": 3293217.0, + "step": 580 + }, + { + "entropy": 0.0733188034966588, + "epoch": 1.5733333333333333, + "grad_norm": 0.04833984375, + "learning_rate": 9.825847846012832e-05, + "loss": 0.06935187578201293, + "mean_token_accuracy": 0.9748518764972687, + "num_tokens": 3349872.0, + "step": 590 + }, + { + "entropy": 0.07255212999880314, + "epoch": 1.6, + "grad_norm": 0.04736328125, + "learning_rate": 9.642529789184235e-05, + "loss": 0.07008358240127563, + "mean_token_accuracy": 0.9742572873830795, + "num_tokens": 3406930.0, + "step": 600 + }, + { + "entropy": 0.0732356732711196, + "epoch": 1.6266666666666667, + "grad_norm": 0.0498046875, + "learning_rate": 9.459211732355638e-05, + "loss": 0.06836349368095399, + "mean_token_accuracy": 0.9751275479793549, + "num_tokens": 3464439.0, + "step": 610 + }, + { + "entropy": 0.07225457970052958, + "epoch": 1.6533333333333333, + "grad_norm": 0.04443359375, + "learning_rate": 9.27589367552704e-05, + "loss": 0.06948843002319335, + "mean_token_accuracy": 0.9739401176571846, + "num_tokens": 3521325.0, + "step": 620 + }, + { + "entropy": 0.07250613961368799, + "epoch": 1.6800000000000002, + "grad_norm": 0.04931640625, + "learning_rate": 9.092575618698442e-05, + "loss": 0.06941892504692078, + "mean_token_accuracy": 0.9748956650495529, + "num_tokens": 3577996.0, + "step": 630 + }, + { + "entropy": 0.0732794025912881, + "epoch": 1.7066666666666666, + "grad_norm": 0.04736328125, + "learning_rate": 8.909257561869845e-05, + "loss": 0.06896185874938965, + "mean_token_accuracy": 0.9750035509467125, + "num_tokens": 3634811.0, + "step": 640 + }, + { + "entropy": 0.07183574195951223, + "epoch": 1.7333333333333334, + "grad_norm": 0.0498046875, + "learning_rate": 8.725939505041248e-05, + "loss": 0.0701564073562622, + "mean_token_accuracy": 0.9742208927869797, + "num_tokens": 3691017.0, + "step": 650 + }, + { + "entropy": 0.07327579502016306, + "epoch": 1.76, + "grad_norm": 0.07470703125, + "learning_rate": 8.54262144821265e-05, + "loss": 0.06881371140480042, + "mean_token_accuracy": 0.9741959020495414, + "num_tokens": 3747546.0, + "step": 660 + }, + { + "entropy": 0.07111402666196227, + "epoch": 1.7866666666666666, + "grad_norm": 0.05712890625, + "learning_rate": 8.359303391384051e-05, + "loss": 0.06966341137886048, + "mean_token_accuracy": 0.9747162073850631, + "num_tokens": 3804126.0, + "step": 670 + }, + { + "entropy": 0.07224018704146147, + "epoch": 1.8133333333333335, + "grad_norm": 0.04541015625, + "learning_rate": 8.175985334555454e-05, + "loss": 0.06840948462486267, + "mean_token_accuracy": 0.9747431293129921, + "num_tokens": 3861006.0, + "step": 680 + }, + { + "entropy": 0.07255861330777406, + "epoch": 1.8399999999999999, + "grad_norm": 0.045654296875, + "learning_rate": 7.992667277726857e-05, + "loss": 0.06987766623497009, + "mean_token_accuracy": 0.9739771053195, + "num_tokens": 3916797.0, + "step": 690 + }, + { + "entropy": 0.07260533329099417, + "epoch": 1.8666666666666667, + "grad_norm": 0.048583984375, + "learning_rate": 7.809349220898258e-05, + "loss": 0.06835905909538269, + "mean_token_accuracy": 0.9750322937965393, + "num_tokens": 3973197.0, + "step": 700 + }, + { + "entropy": 0.0710109818726778, + "epoch": 1.8933333333333333, + "grad_norm": 0.041748046875, + "learning_rate": 7.626031164069661e-05, + "loss": 0.0677144169807434, + "mean_token_accuracy": 0.9751162648200988, + "num_tokens": 4030212.0, + "step": 710 + }, + { + "entropy": 0.070679662656039, + "epoch": 1.92, + "grad_norm": 0.0458984375, + "learning_rate": 7.442713107241064e-05, + "loss": 0.0661697268486023, + "mean_token_accuracy": 0.9755514889955521, + "num_tokens": 4087699.0, + "step": 720 + }, + { + "entropy": 0.0694987777620554, + "epoch": 1.9466666666666668, + "grad_norm": 0.115234375, + "learning_rate": 7.259395050412467e-05, + "loss": 0.06822068691253662, + "mean_token_accuracy": 0.97522524446249, + "num_tokens": 4144740.0, + "step": 730 + }, + { + "entropy": 0.07208629371598363, + "epoch": 1.9733333333333334, + "grad_norm": 0.04443359375, + "learning_rate": 7.076076993583868e-05, + "loss": 0.06933082938194275, + "mean_token_accuracy": 0.9743774682283401, + "num_tokens": 4201289.0, + "step": 740 + }, + { + "entropy": 0.07209395840764046, + "epoch": 2.0, + "grad_norm": 0.04833984375, + "learning_rate": 6.89275893675527e-05, + "loss": 0.06815703511238098, + "mean_token_accuracy": 0.974660362303257, + "num_tokens": 4257958.0, + "step": 750 + }, + { + "entropy": 0.07068475261330605, + "epoch": 2.026666666666667, + "grad_norm": 0.042236328125, + "learning_rate": 6.709440879926673e-05, + "loss": 0.0669311225414276, + "mean_token_accuracy": 0.9747605755925178, + "num_tokens": 4314723.0, + "step": 760 + }, + { + "entropy": 0.06951902080327273, + "epoch": 2.0533333333333332, + "grad_norm": 0.0419921875, + "learning_rate": 6.526122823098076e-05, + "loss": 0.0668017327785492, + "mean_token_accuracy": 0.9751198858022689, + "num_tokens": 4371457.0, + "step": 770 + }, + { + "entropy": 0.07024376196786761, + "epoch": 2.08, + "grad_norm": 0.047607421875, + "learning_rate": 6.342804766269478e-05, + "loss": 0.06699610352516175, + "mean_token_accuracy": 0.9748657032847404, + "num_tokens": 4427543.0, + "step": 780 + }, + { + "entropy": 0.06954137068241835, + "epoch": 2.1066666666666665, + "grad_norm": 0.043212890625, + "learning_rate": 6.15948670944088e-05, + "loss": 0.06581668257713318, + "mean_token_accuracy": 0.9755794301629066, + "num_tokens": 4484853.0, + "step": 790 + }, + { + "entropy": 0.06969003304839134, + "epoch": 2.1333333333333333, + "grad_norm": 0.05859375, + "learning_rate": 5.976168652612283e-05, + "loss": 0.06605738401412964, + "mean_token_accuracy": 0.9751082003116608, + "num_tokens": 4540895.0, + "step": 800 + }, + { + "entropy": 0.07048749346286058, + "epoch": 2.16, + "grad_norm": 0.04931640625, + "learning_rate": 5.792850595783685e-05, + "loss": 0.06759686470031738, + "mean_token_accuracy": 0.9748542428016662, + "num_tokens": 4597531.0, + "step": 810 + }, + { + "entropy": 0.0699356870725751, + "epoch": 2.1866666666666665, + "grad_norm": 0.0498046875, + "learning_rate": 5.6095325389550866e-05, + "loss": 0.06627315282821655, + "mean_token_accuracy": 0.9759758025407791, + "num_tokens": 4654517.0, + "step": 820 + }, + { + "entropy": 0.06981293484568596, + "epoch": 2.2133333333333334, + "grad_norm": 0.04833984375, + "learning_rate": 5.4262144821264894e-05, + "loss": 0.06639997959136963, + "mean_token_accuracy": 0.9752195671200752, + "num_tokens": 4711508.0, + "step": 830 + }, + { + "entropy": 0.06960875494405627, + "epoch": 2.24, + "grad_norm": 0.04736328125, + "learning_rate": 5.2428964252978916e-05, + "loss": 0.06645302176475525, + "mean_token_accuracy": 0.9757942840456962, + "num_tokens": 4768589.0, + "step": 840 + }, + { + "entropy": 0.06928735189139842, + "epoch": 2.2666666666666666, + "grad_norm": 0.06005859375, + "learning_rate": 5.0595783684692945e-05, + "loss": 0.06615262627601623, + "mean_token_accuracy": 0.975421866774559, + "num_tokens": 4825447.0, + "step": 850 + }, + { + "entropy": 0.0701323315501213, + "epoch": 2.2933333333333334, + "grad_norm": 0.043701171875, + "learning_rate": 4.876260311640697e-05, + "loss": 0.06594157218933105, + "mean_token_accuracy": 0.9752340018749237, + "num_tokens": 4882324.0, + "step": 860 + }, + { + "entropy": 0.06790421595796943, + "epoch": 2.32, + "grad_norm": 0.0439453125, + "learning_rate": 4.6929422548120995e-05, + "loss": 0.06551963090896606, + "mean_token_accuracy": 0.9751909494400024, + "num_tokens": 4939254.0, + "step": 870 + }, + { + "entropy": 0.07054078914225101, + "epoch": 2.3466666666666667, + "grad_norm": 0.051025390625, + "learning_rate": 4.509624197983501e-05, + "loss": 0.06690743565559387, + "mean_token_accuracy": 0.9751562505960465, + "num_tokens": 4995524.0, + "step": 880 + }, + { + "entropy": 0.06957337409257888, + "epoch": 2.3733333333333335, + "grad_norm": 0.049560546875, + "learning_rate": 4.326306141154904e-05, + "loss": 0.06609007120132446, + "mean_token_accuracy": 0.9754323452711106, + "num_tokens": 5052578.0, + "step": 890 + }, + { + "entropy": 0.07044977657496929, + "epoch": 2.4, + "grad_norm": 0.0517578125, + "learning_rate": 4.142988084326306e-05, + "loss": 0.06621668338775635, + "mean_token_accuracy": 0.9750386416912079, + "num_tokens": 5108922.0, + "step": 900 + }, + { + "entropy": 0.06792065436020493, + "epoch": 2.4266666666666667, + "grad_norm": 0.046875, + "learning_rate": 3.959670027497709e-05, + "loss": 0.06501899361610412, + "mean_token_accuracy": 0.9760412231087685, + "num_tokens": 5166394.0, + "step": 910 + }, + { + "entropy": 0.06912549249827862, + "epoch": 2.453333333333333, + "grad_norm": 0.046142578125, + "learning_rate": 3.776351970669111e-05, + "loss": 0.06575977206230163, + "mean_token_accuracy": 0.975604172050953, + "num_tokens": 5223123.0, + "step": 920 + }, + { + "entropy": 0.06817780192941428, + "epoch": 2.48, + "grad_norm": 0.0439453125, + "learning_rate": 3.593033913840513e-05, + "loss": 0.06491979956626892, + "mean_token_accuracy": 0.9758375898003578, + "num_tokens": 5280867.0, + "step": 930 + }, + { + "entropy": 0.06880640015006065, + "epoch": 2.506666666666667, + "grad_norm": 0.050048828125, + "learning_rate": 3.409715857011916e-05, + "loss": 0.0658724844455719, + "mean_token_accuracy": 0.9759016156196594, + "num_tokens": 5337629.0, + "step": 940 + }, + { + "entropy": 0.06923360927030445, + "epoch": 2.533333333333333, + "grad_norm": 0.055908203125, + "learning_rate": 3.2263978001833184e-05, + "loss": 0.06607494950294494, + "mean_token_accuracy": 0.9753221690654754, + "num_tokens": 5394318.0, + "step": 950 + }, + { + "entropy": 0.06904373681172729, + "epoch": 2.56, + "grad_norm": 0.04541015625, + "learning_rate": 3.0430797433547202e-05, + "loss": 0.06557352542877197, + "mean_token_accuracy": 0.9759575456380845, + "num_tokens": 5450413.0, + "step": 960 + }, + { + "entropy": 0.06914114560931921, + "epoch": 2.586666666666667, + "grad_norm": 0.046875, + "learning_rate": 2.8597616865261228e-05, + "loss": 0.06594338417053222, + "mean_token_accuracy": 0.9751049831509591, + "num_tokens": 5507306.0, + "step": 970 + }, + { + "entropy": 0.0688713699579239, + "epoch": 2.6133333333333333, + "grad_norm": 0.052001953125, + "learning_rate": 2.6764436296975253e-05, + "loss": 0.06489255428314208, + "mean_token_accuracy": 0.9756928265094758, + "num_tokens": 5564241.0, + "step": 980 + }, + { + "entropy": 0.0688857214525342, + "epoch": 2.64, + "grad_norm": 0.053466796875, + "learning_rate": 2.4931255728689275e-05, + "loss": 0.06557077169418335, + "mean_token_accuracy": 0.9758043006062508, + "num_tokens": 5620870.0, + "step": 990 + }, + { + "entropy": 0.06913622673600912, + "epoch": 2.6666666666666665, + "grad_norm": 0.060302734375, + "learning_rate": 2.30980751604033e-05, + "loss": 0.06396430134773254, + "mean_token_accuracy": 0.9762534514069557, + "num_tokens": 5677975.0, + "step": 1000 + } + ], + "logging_steps": 10, + "max_steps": 1125, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.647683611123712e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/adapters/hf_download/newton/checkpoint-1000/training_args.bin b/adapters/hf_download/newton/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8901e185bda1f9aa496576388f82681270b50795 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +size 5585 diff --git a/adapters/hf_download/newton/checkpoint-1125/README.md b/adapters/hf_download/newton/checkpoint-1125/README.md new file mode 100644 index 0000000000000000000000000000000000000000..35f6e0e06fbb5355b8afea90d8f546c40fb6d50e --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/README.md @@ -0,0 +1,209 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.18.1 \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-1125/adapter_config.json b/adapters/hf_download/newton/checkpoint-1125/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-1125/adapter_model.safetensors b/adapters/hf_download/newton/checkpoint-1125/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea7158bf5b63e323655dd7f350a2256b9523d741 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323635297b5e0c773a26c4451697f85a4ff3020e8864a138ba799a14da2627a2 +size 27297544 diff --git a/adapters/hf_download/newton/checkpoint-1125/chat_template.jinja b/adapters/hf_download/newton/checkpoint-1125/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/newton/checkpoint-1125/optimizer.pt b/adapters/hf_download/newton/checkpoint-1125/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c988f5bc13126181cbb166e3b368057a389d8407 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0613cd7692608d4f46da8fb85a3e7b638bf5c9637f9cfc5d1454e781d35e5997 +size 54745547 diff --git a/adapters/hf_download/newton/checkpoint-1125/rng_state.pth b/adapters/hf_download/newton/checkpoint-1125/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd292b7fc11251f2cf77ded2f403451471e3db82 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c207979b56e7df5b5e151c53b37e511fa7122539c6e7e5570ee51af2a0968967 +size 14645 diff --git a/adapters/hf_download/newton/checkpoint-1125/scheduler.pt b/adapters/hf_download/newton/checkpoint-1125/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0219842344a54bb44bbab85ef27c09f6795c674 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2a37c55dd5d7928c5b2c15b7d4f650fade3ddb7af6dc8961ca05874b789488 +size 1465 diff --git a/adapters/hf_download/newton/checkpoint-1125/tokenizer.json b/adapters/hf_download/newton/checkpoint-1125/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/newton/checkpoint-1125/tokenizer_config.json b/adapters/hf_download/newton/checkpoint-1125/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/newton/checkpoint-1125/trainer_state.json b/adapters/hf_download/newton/checkpoint-1125/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..3a8ad9308698e15be4f948c09a49201e307c512c --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/trainer_state.json @@ -0,0 +1,1154 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1125, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 2.6570239067077637, + "epoch": 0.02666666666666667, + "grad_norm": 0.287109375, + "learning_rate": 5.294117647058824e-05, + "loss": 2.800247573852539, + "mean_token_accuracy": 0.4749053567647934, + "num_tokens": 56906.0, + "step": 10 + }, + { + "entropy": 2.2495410323143004, + "epoch": 0.05333333333333334, + "grad_norm": 0.265625, + "learning_rate": 0.00011176470588235294, + "loss": 2.4327199935913084, + "mean_token_accuracy": 0.5111239477992058, + "num_tokens": 113827.0, + "step": 20 + }, + { + "entropy": 1.8682004392147065, + "epoch": 0.08, + "grad_norm": 0.306640625, + "learning_rate": 0.00017058823529411766, + "loss": 1.789840316772461, + "mean_token_accuracy": 0.599884121119976, + "num_tokens": 170403.0, + "step": 30 + }, + { + "entropy": 1.2546741724014283, + "epoch": 0.10666666666666667, + "grad_norm": 0.306640625, + "learning_rate": 0.00019908340971585702, + "loss": 1.2151795387268067, + "mean_token_accuracy": 0.7106126025319099, + "num_tokens": 227456.0, + "step": 40 + }, + { + "entropy": 0.8836664661765099, + "epoch": 0.13333333333333333, + "grad_norm": 0.28515625, + "learning_rate": 0.00019725022914757106, + "loss": 0.8311976432800293, + "mean_token_accuracy": 0.7977700293064117, + "num_tokens": 284368.0, + "step": 50 + }, + { + "entropy": 0.6855858579277992, + "epoch": 0.16, + "grad_norm": 0.314453125, + "learning_rate": 0.00019541704857928507, + "loss": 0.6242359638214111, + "mean_token_accuracy": 0.847702169418335, + "num_tokens": 341357.0, + "step": 60 + }, + { + "entropy": 0.4690785683691502, + "epoch": 0.18666666666666668, + "grad_norm": 0.248046875, + "learning_rate": 0.00019358386801099912, + "loss": 0.40251870155334474, + "mean_token_accuracy": 0.9024116918444633, + "num_tokens": 398280.0, + "step": 70 + }, + { + "entropy": 0.34345744624733926, + "epoch": 0.21333333333333335, + "grad_norm": 0.27734375, + "learning_rate": 0.0001917506874427131, + "loss": 0.28333656787872313, + "mean_token_accuracy": 0.9320006996393204, + "num_tokens": 455232.0, + "step": 80 + }, + { + "entropy": 0.25451925955712795, + "epoch": 0.24, + "grad_norm": 0.208984375, + "learning_rate": 0.00018991750687442712, + "loss": 0.21085577011108397, + "mean_token_accuracy": 0.949009683728218, + "num_tokens": 511782.0, + "step": 90 + }, + { + "entropy": 0.19814539551734925, + "epoch": 0.26666666666666666, + "grad_norm": 0.296875, + "learning_rate": 0.00018808432630614116, + "loss": 0.1717105984687805, + "mean_token_accuracy": 0.9577329605817795, + "num_tokens": 568641.0, + "step": 100 + }, + { + "entropy": 0.18550167009234428, + "epoch": 0.29333333333333333, + "grad_norm": 0.21875, + "learning_rate": 0.00018625114573785518, + "loss": 0.15982584953308104, + "mean_token_accuracy": 0.9591923207044601, + "num_tokens": 626038.0, + "step": 110 + }, + { + "entropy": 0.16009770445525645, + "epoch": 0.32, + "grad_norm": 0.2109375, + "learning_rate": 0.00018441796516956922, + "loss": 0.12815338373184204, + "mean_token_accuracy": 0.9657398357987403, + "num_tokens": 682880.0, + "step": 120 + }, + { + "entropy": 0.14740683771669866, + "epoch": 0.3466666666666667, + "grad_norm": 0.2431640625, + "learning_rate": 0.00018258478460128323, + "loss": 0.1188442587852478, + "mean_token_accuracy": 0.9664651393890381, + "num_tokens": 739719.0, + "step": 130 + }, + { + "entropy": 0.13307180535048246, + "epoch": 0.37333333333333335, + "grad_norm": 0.1474609375, + "learning_rate": 0.00018075160403299728, + "loss": 0.11054203510284424, + "mean_token_accuracy": 0.9669812738895416, + "num_tokens": 795894.0, + "step": 140 + }, + { + "entropy": 0.12216594349592924, + "epoch": 0.4, + "grad_norm": 0.1240234375, + "learning_rate": 0.0001789184234647113, + "loss": 0.10401068925857544, + "mean_token_accuracy": 0.9683825269341468, + "num_tokens": 852124.0, + "step": 150 + }, + { + "entropy": 0.11619068495929241, + "epoch": 0.4266666666666667, + "grad_norm": 0.12060546875, + "learning_rate": 0.0001770852428964253, + "loss": 0.0976063370704651, + "mean_token_accuracy": 0.9695558726787568, + "num_tokens": 909328.0, + "step": 160 + }, + { + "entropy": 0.10669020470231771, + "epoch": 0.4533333333333333, + "grad_norm": 0.1279296875, + "learning_rate": 0.00017525206232813932, + "loss": 0.09338906407356262, + "mean_token_accuracy": 0.970247569680214, + "num_tokens": 966577.0, + "step": 170 + }, + { + "entropy": 0.10276608634740114, + "epoch": 0.48, + "grad_norm": 0.115234375, + "learning_rate": 0.00017341888175985334, + "loss": 0.09135337471961975, + "mean_token_accuracy": 0.9711026951670647, + "num_tokens": 1022961.0, + "step": 180 + }, + { + "entropy": 0.10297673251479864, + "epoch": 0.5066666666666667, + "grad_norm": 0.11474609375, + "learning_rate": 0.00017158570119156738, + "loss": 0.08887208104133607, + "mean_token_accuracy": 0.9709939315915108, + "num_tokens": 1079479.0, + "step": 190 + }, + { + "entropy": 0.09722564350813627, + "epoch": 0.5333333333333333, + "grad_norm": 0.1044921875, + "learning_rate": 0.0001697525206232814, + "loss": 0.08848196864128113, + "mean_token_accuracy": 0.9712936446070671, + "num_tokens": 1135784.0, + "step": 200 + }, + { + "entropy": 0.09498227294534445, + "epoch": 0.56, + "grad_norm": 0.2236328125, + "learning_rate": 0.00016791934005499544, + "loss": 0.08531092405319214, + "mean_token_accuracy": 0.9717509031295777, + "num_tokens": 1192723.0, + "step": 210 + }, + { + "entropy": 0.09660841915756464, + "epoch": 0.5866666666666667, + "grad_norm": 0.154296875, + "learning_rate": 0.00016608615948670945, + "loss": 0.08432384729385375, + "mean_token_accuracy": 0.9723995119333267, + "num_tokens": 1248974.0, + "step": 220 + }, + { + "entropy": 0.09139632768929004, + "epoch": 0.6133333333333333, + "grad_norm": 0.08203125, + "learning_rate": 0.0001642529789184235, + "loss": 0.08340675234794617, + "mean_token_accuracy": 0.9725200146436691, + "num_tokens": 1306125.0, + "step": 230 + }, + { + "entropy": 0.09041857812553644, + "epoch": 0.64, + "grad_norm": 0.0751953125, + "learning_rate": 0.0001624197983501375, + "loss": 0.08240053057670593, + "mean_token_accuracy": 0.9727400034666062, + "num_tokens": 1362509.0, + "step": 240 + }, + { + "entropy": 0.08917351886630058, + "epoch": 0.6666666666666666, + "grad_norm": 0.11181640625, + "learning_rate": 0.00016058661778185152, + "loss": 0.08038315176963806, + "mean_token_accuracy": 0.9722966447472572, + "num_tokens": 1419155.0, + "step": 250 + }, + { + "entropy": 0.08846015091985464, + "epoch": 0.6933333333333334, + "grad_norm": 0.07421875, + "learning_rate": 0.00015875343721356554, + "loss": 0.08111950755119324, + "mean_token_accuracy": 0.9725704893469811, + "num_tokens": 1475233.0, + "step": 260 + }, + { + "entropy": 0.08615751322358847, + "epoch": 0.72, + "grad_norm": 0.103515625, + "learning_rate": 0.00015692025664527955, + "loss": 0.07856618165969849, + "mean_token_accuracy": 0.9734801158308983, + "num_tokens": 1531666.0, + "step": 270 + }, + { + "entropy": 0.08350808713585138, + "epoch": 0.7466666666666667, + "grad_norm": 0.0869140625, + "learning_rate": 0.0001550870760769936, + "loss": 0.07699183821678161, + "mean_token_accuracy": 0.9737285181879998, + "num_tokens": 1588686.0, + "step": 280 + }, + { + "entropy": 0.08553262427449226, + "epoch": 0.7733333333333333, + "grad_norm": 0.140625, + "learning_rate": 0.0001532538955087076, + "loss": 0.07849866151809692, + "mean_token_accuracy": 0.9727597609162331, + "num_tokens": 1645610.0, + "step": 290 + }, + { + "entropy": 0.08688175324350596, + "epoch": 0.8, + "grad_norm": 0.1318359375, + "learning_rate": 0.00015142071494042165, + "loss": 0.0791881263256073, + "mean_token_accuracy": 0.9728336438536644, + "num_tokens": 1702234.0, + "step": 300 + }, + { + "entropy": 0.08647099416702986, + "epoch": 0.8266666666666667, + "grad_norm": 0.076171875, + "learning_rate": 0.00014958753437213567, + "loss": 0.07916317582130432, + "mean_token_accuracy": 0.9720797210931778, + "num_tokens": 1758523.0, + "step": 310 + }, + { + "entropy": 0.08278416823595762, + "epoch": 0.8533333333333334, + "grad_norm": 0.076171875, + "learning_rate": 0.00014775435380384968, + "loss": 0.07689375281333924, + "mean_token_accuracy": 0.9735667318105697, + "num_tokens": 1815080.0, + "step": 320 + }, + { + "entropy": 0.08433555215597152, + "epoch": 0.88, + "grad_norm": 0.0888671875, + "learning_rate": 0.00014592117323556373, + "loss": 0.07733245491981507, + "mean_token_accuracy": 0.973043854534626, + "num_tokens": 1872283.0, + "step": 330 + }, + { + "entropy": 0.0831523710861802, + "epoch": 0.9066666666666666, + "grad_norm": 0.185546875, + "learning_rate": 0.00014408799266727771, + "loss": 0.07743646502494812, + "mean_token_accuracy": 0.9724773317575455, + "num_tokens": 1929120.0, + "step": 340 + }, + { + "entropy": 0.08173599634319544, + "epoch": 0.9333333333333333, + "grad_norm": 0.08447265625, + "learning_rate": 0.00014225481209899176, + "loss": 0.07464101910591125, + "mean_token_accuracy": 0.9732464775443077, + "num_tokens": 1986433.0, + "step": 350 + }, + { + "entropy": 0.08154450561851263, + "epoch": 0.96, + "grad_norm": 0.197265625, + "learning_rate": 0.00014042163153070577, + "loss": 0.07836683988571166, + "mean_token_accuracy": 0.9733009964227677, + "num_tokens": 2043465.0, + "step": 360 + }, + { + "entropy": 0.08830973766744137, + "epoch": 0.9866666666666667, + "grad_norm": 0.0634765625, + "learning_rate": 0.0001385884509624198, + "loss": 0.07805899381637574, + "mean_token_accuracy": 0.9734541475772858, + "num_tokens": 2100933.0, + "step": 370 + }, + { + "entropy": 0.08108338043093681, + "epoch": 1.0133333333333334, + "grad_norm": 0.05859375, + "learning_rate": 0.00013675527039413383, + "loss": 0.07582586407661437, + "mean_token_accuracy": 0.9734946370124817, + "num_tokens": 2157057.0, + "step": 380 + }, + { + "entropy": 0.0781314555555582, + "epoch": 1.04, + "grad_norm": 0.05078125, + "learning_rate": 0.00013492208982584784, + "loss": 0.0714304804801941, + "mean_token_accuracy": 0.975023752450943, + "num_tokens": 2214085.0, + "step": 390 + }, + { + "entropy": 0.07955040819942952, + "epoch": 1.0666666666666667, + "grad_norm": 0.08984375, + "learning_rate": 0.00013308890925756189, + "loss": 0.07331350445747375, + "mean_token_accuracy": 0.9737342849373818, + "num_tokens": 2270765.0, + "step": 400 + }, + { + "entropy": 0.07677881456911564, + "epoch": 1.0933333333333333, + "grad_norm": 0.07177734375, + "learning_rate": 0.0001312557286892759, + "loss": 0.07168130278587341, + "mean_token_accuracy": 0.9739445611834526, + "num_tokens": 2327512.0, + "step": 410 + }, + { + "entropy": 0.07667716387659311, + "epoch": 1.12, + "grad_norm": 0.0771484375, + "learning_rate": 0.00012942254812098992, + "loss": 0.07219807505607605, + "mean_token_accuracy": 0.9742562755942344, + "num_tokens": 2384423.0, + "step": 420 + }, + { + "entropy": 0.07681187009438872, + "epoch": 1.1466666666666667, + "grad_norm": 0.0615234375, + "learning_rate": 0.00012758936755270393, + "loss": 0.07280588746070862, + "mean_token_accuracy": 0.9735747814178467, + "num_tokens": 2441102.0, + "step": 430 + }, + { + "entropy": 0.07602620646357536, + "epoch": 1.1733333333333333, + "grad_norm": 0.06982421875, + "learning_rate": 0.00012575618698441797, + "loss": 0.07293958067893982, + "mean_token_accuracy": 0.9740705206990242, + "num_tokens": 2497642.0, + "step": 440 + }, + { + "entropy": 0.07798876240849495, + "epoch": 1.2, + "grad_norm": 0.07421875, + "learning_rate": 0.000123923006416132, + "loss": 0.07215467095375061, + "mean_token_accuracy": 0.9742186814546585, + "num_tokens": 2554273.0, + "step": 450 + }, + { + "entropy": 0.07671927772462368, + "epoch": 1.2266666666666666, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012208982584784603, + "loss": 0.07254356741905213, + "mean_token_accuracy": 0.9733539551496506, + "num_tokens": 2610932.0, + "step": 460 + }, + { + "entropy": 0.07502734698355198, + "epoch": 1.2533333333333334, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012025664527956005, + "loss": 0.07076438069343567, + "mean_token_accuracy": 0.9745794385671616, + "num_tokens": 2668226.0, + "step": 470 + }, + { + "entropy": 0.07516032289713621, + "epoch": 1.28, + "grad_norm": 0.045654296875, + "learning_rate": 0.00011842346471127406, + "loss": 0.0711740493774414, + "mean_token_accuracy": 0.9735412746667862, + "num_tokens": 2725180.0, + "step": 480 + }, + { + "entropy": 0.07623793687671424, + "epoch": 1.3066666666666666, + "grad_norm": 0.053955078125, + "learning_rate": 0.00011659028414298809, + "loss": 0.07199874520301819, + "mean_token_accuracy": 0.9739259093999862, + "num_tokens": 2782069.0, + "step": 490 + }, + { + "entropy": 0.07468608934432268, + "epoch": 1.3333333333333333, + "grad_norm": 0.046142578125, + "learning_rate": 0.0001147571035747021, + "loss": 0.07050397992134094, + "mean_token_accuracy": 0.9742979735136033, + "num_tokens": 2838772.0, + "step": 500 + }, + { + "entropy": 0.07314184289425611, + "epoch": 1.3599999999999999, + "grad_norm": 0.0732421875, + "learning_rate": 0.00011292392300641615, + "loss": 0.06992406845092773, + "mean_token_accuracy": 0.9748412847518921, + "num_tokens": 2896384.0, + "step": 510 + }, + { + "entropy": 0.07735273949801921, + "epoch": 1.3866666666666667, + "grad_norm": 0.042236328125, + "learning_rate": 0.00011109074243813016, + "loss": 0.07089330554008484, + "mean_token_accuracy": 0.973857656121254, + "num_tokens": 2953074.0, + "step": 520 + }, + { + "entropy": 0.07427110467106104, + "epoch": 1.4133333333333333, + "grad_norm": 0.05615234375, + "learning_rate": 0.00010925756186984419, + "loss": 0.07023302912712097, + "mean_token_accuracy": 0.9745061740279197, + "num_tokens": 3009599.0, + "step": 530 + }, + { + "entropy": 0.07496015410870313, + "epoch": 1.44, + "grad_norm": 0.04150390625, + "learning_rate": 0.0001074243813015582, + "loss": 0.07044907808303832, + "mean_token_accuracy": 0.97446711063385, + "num_tokens": 3065550.0, + "step": 540 + }, + { + "entropy": 0.07237969692796468, + "epoch": 1.4666666666666668, + "grad_norm": 0.0537109375, + "learning_rate": 0.00010559120073327222, + "loss": 0.06903309226036072, + "mean_token_accuracy": 0.9751396328210831, + "num_tokens": 3122339.0, + "step": 550 + }, + { + "entropy": 0.07292939173057675, + "epoch": 1.4933333333333334, + "grad_norm": 0.044921875, + "learning_rate": 0.00010375802016498626, + "loss": 0.06951733827590942, + "mean_token_accuracy": 0.9748973533511162, + "num_tokens": 3179284.0, + "step": 560 + }, + { + "entropy": 0.0735103216022253, + "epoch": 1.52, + "grad_norm": 0.0595703125, + "learning_rate": 0.00010192483959670028, + "loss": 0.06886410713195801, + "mean_token_accuracy": 0.9742336764931678, + "num_tokens": 3236634.0, + "step": 570 + }, + { + "entropy": 0.07244595270603896, + "epoch": 1.5466666666666666, + "grad_norm": 0.049072265625, + "learning_rate": 0.0001000916590284143, + "loss": 0.06925945878028869, + "mean_token_accuracy": 0.9746079474687577, + "num_tokens": 3293217.0, + "step": 580 + }, + { + "entropy": 0.0733188034966588, + "epoch": 1.5733333333333333, + "grad_norm": 0.04833984375, + "learning_rate": 9.825847846012832e-05, + "loss": 0.06935187578201293, + "mean_token_accuracy": 0.9748518764972687, + "num_tokens": 3349872.0, + "step": 590 + }, + { + "entropy": 0.07255212999880314, + "epoch": 1.6, + "grad_norm": 0.04736328125, + "learning_rate": 9.642529789184235e-05, + "loss": 0.07008358240127563, + "mean_token_accuracy": 0.9742572873830795, + "num_tokens": 3406930.0, + "step": 600 + }, + { + "entropy": 0.0732356732711196, + "epoch": 1.6266666666666667, + "grad_norm": 0.0498046875, + "learning_rate": 9.459211732355638e-05, + "loss": 0.06836349368095399, + "mean_token_accuracy": 0.9751275479793549, + "num_tokens": 3464439.0, + "step": 610 + }, + { + "entropy": 0.07225457970052958, + "epoch": 1.6533333333333333, + "grad_norm": 0.04443359375, + "learning_rate": 9.27589367552704e-05, + "loss": 0.06948843002319335, + "mean_token_accuracy": 0.9739401176571846, + "num_tokens": 3521325.0, + "step": 620 + }, + { + "entropy": 0.07250613961368799, + "epoch": 1.6800000000000002, + "grad_norm": 0.04931640625, + "learning_rate": 9.092575618698442e-05, + "loss": 0.06941892504692078, + "mean_token_accuracy": 0.9748956650495529, + "num_tokens": 3577996.0, + "step": 630 + }, + { + "entropy": 0.0732794025912881, + "epoch": 1.7066666666666666, + "grad_norm": 0.04736328125, + "learning_rate": 8.909257561869845e-05, + "loss": 0.06896185874938965, + "mean_token_accuracy": 0.9750035509467125, + "num_tokens": 3634811.0, + "step": 640 + }, + { + "entropy": 0.07183574195951223, + "epoch": 1.7333333333333334, + "grad_norm": 0.0498046875, + "learning_rate": 8.725939505041248e-05, + "loss": 0.0701564073562622, + "mean_token_accuracy": 0.9742208927869797, + "num_tokens": 3691017.0, + "step": 650 + }, + { + "entropy": 0.07327579502016306, + "epoch": 1.76, + "grad_norm": 0.07470703125, + "learning_rate": 8.54262144821265e-05, + "loss": 0.06881371140480042, + "mean_token_accuracy": 0.9741959020495414, + "num_tokens": 3747546.0, + "step": 660 + }, + { + "entropy": 0.07111402666196227, + "epoch": 1.7866666666666666, + "grad_norm": 0.05712890625, + "learning_rate": 8.359303391384051e-05, + "loss": 0.06966341137886048, + "mean_token_accuracy": 0.9747162073850631, + "num_tokens": 3804126.0, + "step": 670 + }, + { + "entropy": 0.07224018704146147, + "epoch": 1.8133333333333335, + "grad_norm": 0.04541015625, + "learning_rate": 8.175985334555454e-05, + "loss": 0.06840948462486267, + "mean_token_accuracy": 0.9747431293129921, + "num_tokens": 3861006.0, + "step": 680 + }, + { + "entropy": 0.07255861330777406, + "epoch": 1.8399999999999999, + "grad_norm": 0.045654296875, + "learning_rate": 7.992667277726857e-05, + "loss": 0.06987766623497009, + "mean_token_accuracy": 0.9739771053195, + "num_tokens": 3916797.0, + "step": 690 + }, + { + "entropy": 0.07260533329099417, + "epoch": 1.8666666666666667, + "grad_norm": 0.048583984375, + "learning_rate": 7.809349220898258e-05, + "loss": 0.06835905909538269, + "mean_token_accuracy": 0.9750322937965393, + "num_tokens": 3973197.0, + "step": 700 + }, + { + "entropy": 0.0710109818726778, + "epoch": 1.8933333333333333, + "grad_norm": 0.041748046875, + "learning_rate": 7.626031164069661e-05, + "loss": 0.0677144169807434, + "mean_token_accuracy": 0.9751162648200988, + "num_tokens": 4030212.0, + "step": 710 + }, + { + "entropy": 0.070679662656039, + "epoch": 1.92, + "grad_norm": 0.0458984375, + "learning_rate": 7.442713107241064e-05, + "loss": 0.0661697268486023, + "mean_token_accuracy": 0.9755514889955521, + "num_tokens": 4087699.0, + "step": 720 + }, + { + "entropy": 0.0694987777620554, + "epoch": 1.9466666666666668, + "grad_norm": 0.115234375, + "learning_rate": 7.259395050412467e-05, + "loss": 0.06822068691253662, + "mean_token_accuracy": 0.97522524446249, + "num_tokens": 4144740.0, + "step": 730 + }, + { + "entropy": 0.07208629371598363, + "epoch": 1.9733333333333334, + "grad_norm": 0.04443359375, + "learning_rate": 7.076076993583868e-05, + "loss": 0.06933082938194275, + "mean_token_accuracy": 0.9743774682283401, + "num_tokens": 4201289.0, + "step": 740 + }, + { + "entropy": 0.07209395840764046, + "epoch": 2.0, + "grad_norm": 0.04833984375, + "learning_rate": 6.89275893675527e-05, + "loss": 0.06815703511238098, + "mean_token_accuracy": 0.974660362303257, + "num_tokens": 4257958.0, + "step": 750 + }, + { + "entropy": 0.07068475261330605, + "epoch": 2.026666666666667, + "grad_norm": 0.042236328125, + "learning_rate": 6.709440879926673e-05, + "loss": 0.0669311225414276, + "mean_token_accuracy": 0.9747605755925178, + "num_tokens": 4314723.0, + "step": 760 + }, + { + "entropy": 0.06951902080327273, + "epoch": 2.0533333333333332, + "grad_norm": 0.0419921875, + "learning_rate": 6.526122823098076e-05, + "loss": 0.0668017327785492, + "mean_token_accuracy": 0.9751198858022689, + "num_tokens": 4371457.0, + "step": 770 + }, + { + "entropy": 0.07024376196786761, + "epoch": 2.08, + "grad_norm": 0.047607421875, + "learning_rate": 6.342804766269478e-05, + "loss": 0.06699610352516175, + "mean_token_accuracy": 0.9748657032847404, + "num_tokens": 4427543.0, + "step": 780 + }, + { + "entropy": 0.06954137068241835, + "epoch": 2.1066666666666665, + "grad_norm": 0.043212890625, + "learning_rate": 6.15948670944088e-05, + "loss": 0.06581668257713318, + "mean_token_accuracy": 0.9755794301629066, + "num_tokens": 4484853.0, + "step": 790 + }, + { + "entropy": 0.06969003304839134, + "epoch": 2.1333333333333333, + "grad_norm": 0.05859375, + "learning_rate": 5.976168652612283e-05, + "loss": 0.06605738401412964, + "mean_token_accuracy": 0.9751082003116608, + "num_tokens": 4540895.0, + "step": 800 + }, + { + "entropy": 0.07048749346286058, + "epoch": 2.16, + "grad_norm": 0.04931640625, + "learning_rate": 5.792850595783685e-05, + "loss": 0.06759686470031738, + "mean_token_accuracy": 0.9748542428016662, + "num_tokens": 4597531.0, + "step": 810 + }, + { + "entropy": 0.0699356870725751, + "epoch": 2.1866666666666665, + "grad_norm": 0.0498046875, + "learning_rate": 5.6095325389550866e-05, + "loss": 0.06627315282821655, + "mean_token_accuracy": 0.9759758025407791, + "num_tokens": 4654517.0, + "step": 820 + }, + { + "entropy": 0.06981293484568596, + "epoch": 2.2133333333333334, + "grad_norm": 0.04833984375, + "learning_rate": 5.4262144821264894e-05, + "loss": 0.06639997959136963, + "mean_token_accuracy": 0.9752195671200752, + "num_tokens": 4711508.0, + "step": 830 + }, + { + "entropy": 0.06960875494405627, + "epoch": 2.24, + "grad_norm": 0.04736328125, + "learning_rate": 5.2428964252978916e-05, + "loss": 0.06645302176475525, + "mean_token_accuracy": 0.9757942840456962, + "num_tokens": 4768589.0, + "step": 840 + }, + { + "entropy": 0.06928735189139842, + "epoch": 2.2666666666666666, + "grad_norm": 0.06005859375, + "learning_rate": 5.0595783684692945e-05, + "loss": 0.06615262627601623, + "mean_token_accuracy": 0.975421866774559, + "num_tokens": 4825447.0, + "step": 850 + }, + { + "entropy": 0.0701323315501213, + "epoch": 2.2933333333333334, + "grad_norm": 0.043701171875, + "learning_rate": 4.876260311640697e-05, + "loss": 0.06594157218933105, + "mean_token_accuracy": 0.9752340018749237, + "num_tokens": 4882324.0, + "step": 860 + }, + { + "entropy": 0.06790421595796943, + "epoch": 2.32, + "grad_norm": 0.0439453125, + "learning_rate": 4.6929422548120995e-05, + "loss": 0.06551963090896606, + "mean_token_accuracy": 0.9751909494400024, + "num_tokens": 4939254.0, + "step": 870 + }, + { + "entropy": 0.07054078914225101, + "epoch": 2.3466666666666667, + "grad_norm": 0.051025390625, + "learning_rate": 4.509624197983501e-05, + "loss": 0.06690743565559387, + "mean_token_accuracy": 0.9751562505960465, + "num_tokens": 4995524.0, + "step": 880 + }, + { + "entropy": 0.06957337409257888, + "epoch": 2.3733333333333335, + "grad_norm": 0.049560546875, + "learning_rate": 4.326306141154904e-05, + "loss": 0.06609007120132446, + "mean_token_accuracy": 0.9754323452711106, + "num_tokens": 5052578.0, + "step": 890 + }, + { + "entropy": 0.07044977657496929, + "epoch": 2.4, + "grad_norm": 0.0517578125, + "learning_rate": 4.142988084326306e-05, + "loss": 0.06621668338775635, + "mean_token_accuracy": 0.9750386416912079, + "num_tokens": 5108922.0, + "step": 900 + }, + { + "entropy": 0.06792065436020493, + "epoch": 2.4266666666666667, + "grad_norm": 0.046875, + "learning_rate": 3.959670027497709e-05, + "loss": 0.06501899361610412, + "mean_token_accuracy": 0.9760412231087685, + "num_tokens": 5166394.0, + "step": 910 + }, + { + "entropy": 0.06912549249827862, + "epoch": 2.453333333333333, + "grad_norm": 0.046142578125, + "learning_rate": 3.776351970669111e-05, + "loss": 0.06575977206230163, + "mean_token_accuracy": 0.975604172050953, + "num_tokens": 5223123.0, + "step": 920 + }, + { + "entropy": 0.06817780192941428, + "epoch": 2.48, + "grad_norm": 0.0439453125, + "learning_rate": 3.593033913840513e-05, + "loss": 0.06491979956626892, + "mean_token_accuracy": 0.9758375898003578, + "num_tokens": 5280867.0, + "step": 930 + }, + { + "entropy": 0.06880640015006065, + "epoch": 2.506666666666667, + "grad_norm": 0.050048828125, + "learning_rate": 3.409715857011916e-05, + "loss": 0.0658724844455719, + "mean_token_accuracy": 0.9759016156196594, + "num_tokens": 5337629.0, + "step": 940 + }, + { + "entropy": 0.06923360927030445, + "epoch": 2.533333333333333, + "grad_norm": 0.055908203125, + "learning_rate": 3.2263978001833184e-05, + "loss": 0.06607494950294494, + "mean_token_accuracy": 0.9753221690654754, + "num_tokens": 5394318.0, + "step": 950 + }, + { + "entropy": 0.06904373681172729, + "epoch": 2.56, + "grad_norm": 0.04541015625, + "learning_rate": 3.0430797433547202e-05, + "loss": 0.06557352542877197, + "mean_token_accuracy": 0.9759575456380845, + "num_tokens": 5450413.0, + "step": 960 + }, + { + "entropy": 0.06914114560931921, + "epoch": 2.586666666666667, + "grad_norm": 0.046875, + "learning_rate": 2.8597616865261228e-05, + "loss": 0.06594338417053222, + "mean_token_accuracy": 0.9751049831509591, + "num_tokens": 5507306.0, + "step": 970 + }, + { + "entropy": 0.0688713699579239, + "epoch": 2.6133333333333333, + "grad_norm": 0.052001953125, + "learning_rate": 2.6764436296975253e-05, + "loss": 0.06489255428314208, + "mean_token_accuracy": 0.9756928265094758, + "num_tokens": 5564241.0, + "step": 980 + }, + { + "entropy": 0.0688857214525342, + "epoch": 2.64, + "grad_norm": 0.053466796875, + "learning_rate": 2.4931255728689275e-05, + "loss": 0.06557077169418335, + "mean_token_accuracy": 0.9758043006062508, + "num_tokens": 5620870.0, + "step": 990 + }, + { + "entropy": 0.06913622673600912, + "epoch": 2.6666666666666665, + "grad_norm": 0.060302734375, + "learning_rate": 2.30980751604033e-05, + "loss": 0.06396430134773254, + "mean_token_accuracy": 0.9762534514069557, + "num_tokens": 5677975.0, + "step": 1000 + }, + { + "entropy": 0.06967059737071395, + "epoch": 2.6933333333333334, + "grad_norm": 0.0556640625, + "learning_rate": 2.1264894592117325e-05, + "loss": 0.0658549726009369, + "mean_token_accuracy": 0.9755063205957413, + "num_tokens": 5734406.0, + "step": 1010 + }, + { + "entropy": 0.06996878925710917, + "epoch": 2.7199999999999998, + "grad_norm": 0.047607421875, + "learning_rate": 1.943171402383135e-05, + "loss": 0.06624419689178467, + "mean_token_accuracy": 0.9752198234200478, + "num_tokens": 5790588.0, + "step": 1020 + }, + { + "entropy": 0.06913588438183069, + "epoch": 2.7466666666666666, + "grad_norm": 0.051513671875, + "learning_rate": 1.7598533455545372e-05, + "loss": 0.06566822528839111, + "mean_token_accuracy": 0.975077997148037, + "num_tokens": 5846871.0, + "step": 1030 + }, + { + "entropy": 0.07049406385049224, + "epoch": 2.7733333333333334, + "grad_norm": 0.0498046875, + "learning_rate": 1.5765352887259398e-05, + "loss": 0.06581954956054688, + "mean_token_accuracy": 0.9753255605697632, + "num_tokens": 5902888.0, + "step": 1040 + }, + { + "entropy": 0.06881497353315354, + "epoch": 2.8, + "grad_norm": 0.04443359375, + "learning_rate": 1.393217231897342e-05, + "loss": 0.06458759903907776, + "mean_token_accuracy": 0.9755938291549683, + "num_tokens": 5960106.0, + "step": 1050 + }, + { + "entropy": 0.06842826995998622, + "epoch": 2.8266666666666667, + "grad_norm": 0.046630859375, + "learning_rate": 1.2098991750687445e-05, + "loss": 0.06443418264389038, + "mean_token_accuracy": 0.9758713901042938, + "num_tokens": 6016963.0, + "step": 1060 + }, + { + "entropy": 0.06925875274464488, + "epoch": 2.8533333333333335, + "grad_norm": 0.05078125, + "learning_rate": 1.0265811182401468e-05, + "loss": 0.06562719345092774, + "mean_token_accuracy": 0.9754008457064629, + "num_tokens": 6073215.0, + "step": 1070 + }, + { + "entropy": 0.06846961556002498, + "epoch": 2.88, + "grad_norm": 0.05224609375, + "learning_rate": 8.43263061411549e-06, + "loss": 0.06463822722434998, + "mean_token_accuracy": 0.9759333416819572, + "num_tokens": 6130427.0, + "step": 1080 + }, + { + "entropy": 0.06969590932130813, + "epoch": 2.9066666666666667, + "grad_norm": 0.055908203125, + "learning_rate": 6.599450045829514e-06, + "loss": 0.06606504321098328, + "mean_token_accuracy": 0.9749638319015503, + "num_tokens": 6186584.0, + "step": 1090 + }, + { + "entropy": 0.06768293902277947, + "epoch": 2.9333333333333336, + "grad_norm": 0.0478515625, + "learning_rate": 4.766269477543538e-06, + "loss": 0.06344886422157288, + "mean_token_accuracy": 0.9760955572128296, + "num_tokens": 6244713.0, + "step": 1100 + }, + { + "entropy": 0.06839841092005372, + "epoch": 2.96, + "grad_norm": 0.0546875, + "learning_rate": 2.933088909257562e-06, + "loss": 0.06508639454841614, + "mean_token_accuracy": 0.9756930440664291, + "num_tokens": 6301263.0, + "step": 1110 + }, + { + "entropy": 0.06823750771582127, + "epoch": 2.986666666666667, + "grad_norm": 0.04833984375, + "learning_rate": 1.0999083409715858e-06, + "loss": 0.06445437669754028, + "mean_token_accuracy": 0.9759095475077629, + "num_tokens": 6358358.0, + "step": 1120 + } + ], + "logging_steps": 10, + "max_steps": 1125, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.9781846035472384e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/adapters/hf_download/newton/checkpoint-1125/training_args.bin b/adapters/hf_download/newton/checkpoint-1125/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8901e185bda1f9aa496576388f82681270b50795 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-1125/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +size 5585 diff --git a/adapters/hf_download/newton/checkpoint-500/README.md b/adapters/hf_download/newton/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..35f6e0e06fbb5355b8afea90d8f546c40fb6d50e --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/README.md @@ -0,0 +1,209 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct +- lora +- sft +- transformers +- trl +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.18.1 \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-500/adapter_config.json b/adapters/hf_download/newton/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a158266c0996f78496250ff985d9b9f2287d17 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "o_proj", + "k_proj", + "v_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/newton/checkpoint-500/adapter_model.safetensors b/adapters/hf_download/newton/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3017b4ed6d43535bd0d048b844fb9f8339603d36 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e3fa39229c6ec9a3ae3953299dd1633da0fe90c86d1cbd81f4670401ecc4d6 +size 27297544 diff --git a/adapters/hf_download/newton/checkpoint-500/chat_template.jinja b/adapters/hf_download/newton/checkpoint-500/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/adapters/hf_download/newton/checkpoint-500/optimizer.pt b/adapters/hf_download/newton/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..521dde7d40faeb83f5b8679ef0e9e5e5ec86c986 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02efb59f2ff28dda0a4a4530d4c7f101cf666c78420719d9db581857205db1e +size 54745547 diff --git a/adapters/hf_download/newton/checkpoint-500/rng_state.pth b/adapters/hf_download/newton/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4944420efde84f268d279cb7b895d2909afda3fc --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06ed9055f2879d20734525b54e3185ffbd4df450c6774c39d8caa49df8499ed +size 14645 diff --git a/adapters/hf_download/newton/checkpoint-500/scheduler.pt b/adapters/hf_download/newton/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8e61a4c2e2da9554ec4a24bd9949d51a90aad1d --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f2b5fa48c7f09e4487186c3527dd0cb37a3de8892b16ebca696ce3df604cb5 +size 1465 diff --git a/adapters/hf_download/newton/checkpoint-500/tokenizer.json b/adapters/hf_download/newton/checkpoint-500/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/newton/checkpoint-500/tokenizer_config.json b/adapters/hf_download/newton/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/newton/checkpoint-500/trainer_state.json b/adapters/hf_download/newton/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..44b699a99affa0a5c28ecc181604bddbb2188e47 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/trainer_state.json @@ -0,0 +1,534 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3333333333333333, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 2.6570239067077637, + "epoch": 0.02666666666666667, + "grad_norm": 0.287109375, + "learning_rate": 5.294117647058824e-05, + "loss": 2.800247573852539, + "mean_token_accuracy": 0.4749053567647934, + "num_tokens": 56906.0, + "step": 10 + }, + { + "entropy": 2.2495410323143004, + "epoch": 0.05333333333333334, + "grad_norm": 0.265625, + "learning_rate": 0.00011176470588235294, + "loss": 2.4327199935913084, + "mean_token_accuracy": 0.5111239477992058, + "num_tokens": 113827.0, + "step": 20 + }, + { + "entropy": 1.8682004392147065, + "epoch": 0.08, + "grad_norm": 0.306640625, + "learning_rate": 0.00017058823529411766, + "loss": 1.789840316772461, + "mean_token_accuracy": 0.599884121119976, + "num_tokens": 170403.0, + "step": 30 + }, + { + "entropy": 1.2546741724014283, + "epoch": 0.10666666666666667, + "grad_norm": 0.306640625, + "learning_rate": 0.00019908340971585702, + "loss": 1.2151795387268067, + "mean_token_accuracy": 0.7106126025319099, + "num_tokens": 227456.0, + "step": 40 + }, + { + "entropy": 0.8836664661765099, + "epoch": 0.13333333333333333, + "grad_norm": 0.28515625, + "learning_rate": 0.00019725022914757106, + "loss": 0.8311976432800293, + "mean_token_accuracy": 0.7977700293064117, + "num_tokens": 284368.0, + "step": 50 + }, + { + "entropy": 0.6855858579277992, + "epoch": 0.16, + "grad_norm": 0.314453125, + "learning_rate": 0.00019541704857928507, + "loss": 0.6242359638214111, + "mean_token_accuracy": 0.847702169418335, + "num_tokens": 341357.0, + "step": 60 + }, + { + "entropy": 0.4690785683691502, + "epoch": 0.18666666666666668, + "grad_norm": 0.248046875, + "learning_rate": 0.00019358386801099912, + "loss": 0.40251870155334474, + "mean_token_accuracy": 0.9024116918444633, + "num_tokens": 398280.0, + "step": 70 + }, + { + "entropy": 0.34345744624733926, + "epoch": 0.21333333333333335, + "grad_norm": 0.27734375, + "learning_rate": 0.0001917506874427131, + "loss": 0.28333656787872313, + "mean_token_accuracy": 0.9320006996393204, + "num_tokens": 455232.0, + "step": 80 + }, + { + "entropy": 0.25451925955712795, + "epoch": 0.24, + "grad_norm": 0.208984375, + "learning_rate": 0.00018991750687442712, + "loss": 0.21085577011108397, + "mean_token_accuracy": 0.949009683728218, + "num_tokens": 511782.0, + "step": 90 + }, + { + "entropy": 0.19814539551734925, + "epoch": 0.26666666666666666, + "grad_norm": 0.296875, + "learning_rate": 0.00018808432630614116, + "loss": 0.1717105984687805, + "mean_token_accuracy": 0.9577329605817795, + "num_tokens": 568641.0, + "step": 100 + }, + { + "entropy": 0.18550167009234428, + "epoch": 0.29333333333333333, + "grad_norm": 0.21875, + "learning_rate": 0.00018625114573785518, + "loss": 0.15982584953308104, + "mean_token_accuracy": 0.9591923207044601, + "num_tokens": 626038.0, + "step": 110 + }, + { + "entropy": 0.16009770445525645, + "epoch": 0.32, + "grad_norm": 0.2109375, + "learning_rate": 0.00018441796516956922, + "loss": 0.12815338373184204, + "mean_token_accuracy": 0.9657398357987403, + "num_tokens": 682880.0, + "step": 120 + }, + { + "entropy": 0.14740683771669866, + "epoch": 0.3466666666666667, + "grad_norm": 0.2431640625, + "learning_rate": 0.00018258478460128323, + "loss": 0.1188442587852478, + "mean_token_accuracy": 0.9664651393890381, + "num_tokens": 739719.0, + "step": 130 + }, + { + "entropy": 0.13307180535048246, + "epoch": 0.37333333333333335, + "grad_norm": 0.1474609375, + "learning_rate": 0.00018075160403299728, + "loss": 0.11054203510284424, + "mean_token_accuracy": 0.9669812738895416, + "num_tokens": 795894.0, + "step": 140 + }, + { + "entropy": 0.12216594349592924, + "epoch": 0.4, + "grad_norm": 0.1240234375, + "learning_rate": 0.0001789184234647113, + "loss": 0.10401068925857544, + "mean_token_accuracy": 0.9683825269341468, + "num_tokens": 852124.0, + "step": 150 + }, + { + "entropy": 0.11619068495929241, + "epoch": 0.4266666666666667, + "grad_norm": 0.12060546875, + "learning_rate": 0.0001770852428964253, + "loss": 0.0976063370704651, + "mean_token_accuracy": 0.9695558726787568, + "num_tokens": 909328.0, + "step": 160 + }, + { + "entropy": 0.10669020470231771, + "epoch": 0.4533333333333333, + "grad_norm": 0.1279296875, + "learning_rate": 0.00017525206232813932, + "loss": 0.09338906407356262, + "mean_token_accuracy": 0.970247569680214, + "num_tokens": 966577.0, + "step": 170 + }, + { + "entropy": 0.10276608634740114, + "epoch": 0.48, + "grad_norm": 0.115234375, + "learning_rate": 0.00017341888175985334, + "loss": 0.09135337471961975, + "mean_token_accuracy": 0.9711026951670647, + "num_tokens": 1022961.0, + "step": 180 + }, + { + "entropy": 0.10297673251479864, + "epoch": 0.5066666666666667, + "grad_norm": 0.11474609375, + "learning_rate": 0.00017158570119156738, + "loss": 0.08887208104133607, + "mean_token_accuracy": 0.9709939315915108, + "num_tokens": 1079479.0, + "step": 190 + }, + { + "entropy": 0.09722564350813627, + "epoch": 0.5333333333333333, + "grad_norm": 0.1044921875, + "learning_rate": 0.0001697525206232814, + "loss": 0.08848196864128113, + "mean_token_accuracy": 0.9712936446070671, + "num_tokens": 1135784.0, + "step": 200 + }, + { + "entropy": 0.09498227294534445, + "epoch": 0.56, + "grad_norm": 0.2236328125, + "learning_rate": 0.00016791934005499544, + "loss": 0.08531092405319214, + "mean_token_accuracy": 0.9717509031295777, + "num_tokens": 1192723.0, + "step": 210 + }, + { + "entropy": 0.09660841915756464, + "epoch": 0.5866666666666667, + "grad_norm": 0.154296875, + "learning_rate": 0.00016608615948670945, + "loss": 0.08432384729385375, + "mean_token_accuracy": 0.9723995119333267, + "num_tokens": 1248974.0, + "step": 220 + }, + { + "entropy": 0.09139632768929004, + "epoch": 0.6133333333333333, + "grad_norm": 0.08203125, + "learning_rate": 0.0001642529789184235, + "loss": 0.08340675234794617, + "mean_token_accuracy": 0.9725200146436691, + "num_tokens": 1306125.0, + "step": 230 + }, + { + "entropy": 0.09041857812553644, + "epoch": 0.64, + "grad_norm": 0.0751953125, + "learning_rate": 0.0001624197983501375, + "loss": 0.08240053057670593, + "mean_token_accuracy": 0.9727400034666062, + "num_tokens": 1362509.0, + "step": 240 + }, + { + "entropy": 0.08917351886630058, + "epoch": 0.6666666666666666, + "grad_norm": 0.11181640625, + "learning_rate": 0.00016058661778185152, + "loss": 0.08038315176963806, + "mean_token_accuracy": 0.9722966447472572, + "num_tokens": 1419155.0, + "step": 250 + }, + { + "entropy": 0.08846015091985464, + "epoch": 0.6933333333333334, + "grad_norm": 0.07421875, + "learning_rate": 0.00015875343721356554, + "loss": 0.08111950755119324, + "mean_token_accuracy": 0.9725704893469811, + "num_tokens": 1475233.0, + "step": 260 + }, + { + "entropy": 0.08615751322358847, + "epoch": 0.72, + "grad_norm": 0.103515625, + "learning_rate": 0.00015692025664527955, + "loss": 0.07856618165969849, + "mean_token_accuracy": 0.9734801158308983, + "num_tokens": 1531666.0, + "step": 270 + }, + { + "entropy": 0.08350808713585138, + "epoch": 0.7466666666666667, + "grad_norm": 0.0869140625, + "learning_rate": 0.0001550870760769936, + "loss": 0.07699183821678161, + "mean_token_accuracy": 0.9737285181879998, + "num_tokens": 1588686.0, + "step": 280 + }, + { + "entropy": 0.08553262427449226, + "epoch": 0.7733333333333333, + "grad_norm": 0.140625, + "learning_rate": 0.0001532538955087076, + "loss": 0.07849866151809692, + "mean_token_accuracy": 0.9727597609162331, + "num_tokens": 1645610.0, + "step": 290 + }, + { + "entropy": 0.08688175324350596, + "epoch": 0.8, + "grad_norm": 0.1318359375, + "learning_rate": 0.00015142071494042165, + "loss": 0.0791881263256073, + "mean_token_accuracy": 0.9728336438536644, + "num_tokens": 1702234.0, + "step": 300 + }, + { + "entropy": 0.08647099416702986, + "epoch": 0.8266666666666667, + "grad_norm": 0.076171875, + "learning_rate": 0.00014958753437213567, + "loss": 0.07916317582130432, + "mean_token_accuracy": 0.9720797210931778, + "num_tokens": 1758523.0, + "step": 310 + }, + { + "entropy": 0.08278416823595762, + "epoch": 0.8533333333333334, + "grad_norm": 0.076171875, + "learning_rate": 0.00014775435380384968, + "loss": 0.07689375281333924, + "mean_token_accuracy": 0.9735667318105697, + "num_tokens": 1815080.0, + "step": 320 + }, + { + "entropy": 0.08433555215597152, + "epoch": 0.88, + "grad_norm": 0.0888671875, + "learning_rate": 0.00014592117323556373, + "loss": 0.07733245491981507, + "mean_token_accuracy": 0.973043854534626, + "num_tokens": 1872283.0, + "step": 330 + }, + { + "entropy": 0.0831523710861802, + "epoch": 0.9066666666666666, + "grad_norm": 0.185546875, + "learning_rate": 0.00014408799266727771, + "loss": 0.07743646502494812, + "mean_token_accuracy": 0.9724773317575455, + "num_tokens": 1929120.0, + "step": 340 + }, + { + "entropy": 0.08173599634319544, + "epoch": 0.9333333333333333, + "grad_norm": 0.08447265625, + "learning_rate": 0.00014225481209899176, + "loss": 0.07464101910591125, + "mean_token_accuracy": 0.9732464775443077, + "num_tokens": 1986433.0, + "step": 350 + }, + { + "entropy": 0.08154450561851263, + "epoch": 0.96, + "grad_norm": 0.197265625, + "learning_rate": 0.00014042163153070577, + "loss": 0.07836683988571166, + "mean_token_accuracy": 0.9733009964227677, + "num_tokens": 2043465.0, + "step": 360 + }, + { + "entropy": 0.08830973766744137, + "epoch": 0.9866666666666667, + "grad_norm": 0.0634765625, + "learning_rate": 0.0001385884509624198, + "loss": 0.07805899381637574, + "mean_token_accuracy": 0.9734541475772858, + "num_tokens": 2100933.0, + "step": 370 + }, + { + "entropy": 0.08108338043093681, + "epoch": 1.0133333333333334, + "grad_norm": 0.05859375, + "learning_rate": 0.00013675527039413383, + "loss": 0.07582586407661437, + "mean_token_accuracy": 0.9734946370124817, + "num_tokens": 2157057.0, + "step": 380 + }, + { + "entropy": 0.0781314555555582, + "epoch": 1.04, + "grad_norm": 0.05078125, + "learning_rate": 0.00013492208982584784, + "loss": 0.0714304804801941, + "mean_token_accuracy": 0.975023752450943, + "num_tokens": 2214085.0, + "step": 390 + }, + { + "entropy": 0.07955040819942952, + "epoch": 1.0666666666666667, + "grad_norm": 0.08984375, + "learning_rate": 0.00013308890925756189, + "loss": 0.07331350445747375, + "mean_token_accuracy": 0.9737342849373818, + "num_tokens": 2270765.0, + "step": 400 + }, + { + "entropy": 0.07677881456911564, + "epoch": 1.0933333333333333, + "grad_norm": 0.07177734375, + "learning_rate": 0.0001312557286892759, + "loss": 0.07168130278587341, + "mean_token_accuracy": 0.9739445611834526, + "num_tokens": 2327512.0, + "step": 410 + }, + { + "entropy": 0.07667716387659311, + "epoch": 1.12, + "grad_norm": 0.0771484375, + "learning_rate": 0.00012942254812098992, + "loss": 0.07219807505607605, + "mean_token_accuracy": 0.9742562755942344, + "num_tokens": 2384423.0, + "step": 420 + }, + { + "entropy": 0.07681187009438872, + "epoch": 1.1466666666666667, + "grad_norm": 0.0615234375, + "learning_rate": 0.00012758936755270393, + "loss": 0.07280588746070862, + "mean_token_accuracy": 0.9735747814178467, + "num_tokens": 2441102.0, + "step": 430 + }, + { + "entropy": 0.07602620646357536, + "epoch": 1.1733333333333333, + "grad_norm": 0.06982421875, + "learning_rate": 0.00012575618698441797, + "loss": 0.07293958067893982, + "mean_token_accuracy": 0.9740705206990242, + "num_tokens": 2497642.0, + "step": 440 + }, + { + "entropy": 0.07798876240849495, + "epoch": 1.2, + "grad_norm": 0.07421875, + "learning_rate": 0.000123923006416132, + "loss": 0.07215467095375061, + "mean_token_accuracy": 0.9742186814546585, + "num_tokens": 2554273.0, + "step": 450 + }, + { + "entropy": 0.07671927772462368, + "epoch": 1.2266666666666666, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012208982584784603, + "loss": 0.07254356741905213, + "mean_token_accuracy": 0.9733539551496506, + "num_tokens": 2610932.0, + "step": 460 + }, + { + "entropy": 0.07502734698355198, + "epoch": 1.2533333333333334, + "grad_norm": 0.05029296875, + "learning_rate": 0.00012025664527956005, + "loss": 0.07076438069343567, + "mean_token_accuracy": 0.9745794385671616, + "num_tokens": 2668226.0, + "step": 470 + }, + { + "entropy": 0.07516032289713621, + "epoch": 1.28, + "grad_norm": 0.045654296875, + "learning_rate": 0.00011842346471127406, + "loss": 0.0711740493774414, + "mean_token_accuracy": 0.9735412746667862, + "num_tokens": 2725180.0, + "step": 480 + }, + { + "entropy": 0.07623793687671424, + "epoch": 1.3066666666666666, + "grad_norm": 0.053955078125, + "learning_rate": 0.00011659028414298809, + "loss": 0.07199874520301819, + "mean_token_accuracy": 0.9739259093999862, + "num_tokens": 2782069.0, + "step": 490 + }, + { + "entropy": 0.07468608934432268, + "epoch": 1.3333333333333333, + "grad_norm": 0.046142578125, + "learning_rate": 0.0001147571035747021, + "loss": 0.07050397992134094, + "mean_token_accuracy": 0.9742979735136033, + "num_tokens": 2838772.0, + "step": 500 + } + ], + "logging_steps": 10, + "max_steps": 1125, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.3243190835068928e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/adapters/hf_download/newton/checkpoint-500/training_args.bin b/adapters/hf_download/newton/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8901e185bda1f9aa496576388f82681270b50795 --- /dev/null +++ b/adapters/hf_download/newton/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8755273dccefb3d7fa41448d64a8c28d76451700a997d4cbd5f7ac202a091f77 +size 5585 diff --git a/adapters/hf_download/newton/tokenizer.json b/adapters/hf_download/newton/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/adapters/hf_download/newton/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/adapters/hf_download/newton/tokenizer_config.json b/adapters/hf_download/newton/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0c736827e07464a3cdd67acebb3699bfd0a38d1 --- /dev/null +++ b/adapters/hf_download/newton/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/adapters/hf_download/philosophy/adapter_config.json b/adapters/hf_download/philosophy/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e436105a860fe50b72d2cc8f1e1b7300e6d03116 --- /dev/null +++ b/adapters/hf_download/philosophy/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "o_proj", + "k_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/philosophy/adapter_model.safetensors b/adapters/hf_download/philosophy/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f67f77cb1daba4207d4d69f8b19f7836fdd60e5 --- /dev/null +++ b/adapters/hf_download/philosophy/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1e0fd3925a2d53626c02c09e001d0efdf0e1b122d4b4a93b2fdcbf1132be02 +size 27297544 diff --git a/adapters/hf_download/quantum/adapter_config.json b/adapters/hf_download/quantum/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e436105a860fe50b72d2cc8f1e1b7300e6d03116 --- /dev/null +++ b/adapters/hf_download/quantum/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "o_proj", + "k_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/quantum/adapter_model.safetensors b/adapters/hf_download/quantum/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2f33d7a4264a21bfbb574abdffa54d59972b4d2 --- /dev/null +++ b/adapters/hf_download/quantum/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daba59d3101ca1d0b42077187173d137c7894ff810c91e08e276ae0b3877bab9 +size 27297544 diff --git a/adapters/hf_download/systems_architecture/adapter_config.json b/adapters/hf_download/systems_architecture/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8b2de52cc3e7a37fd794f63fc3ef18381217d301 --- /dev/null +++ b/adapters/hf_download/systems_architecture/adapter_config.json @@ -0,0 +1,43 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.18.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj", + "k_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapters/hf_download/systems_architecture/adapter_model.safetensors b/adapters/hf_download/systems_architecture/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0665f745c9ec39a2459a8dfeb3542ba9cedad74f --- /dev/null +++ b/adapters/hf_download/systems_architecture/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efee471763195d927b69b997ce0241b1da6d5364ba980cdc28a2d3ef1306bc07 +size 27297544 diff --git a/adapters/multi_perspective-lora-f16.gguf b/adapters/multi_perspective-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..14f8241f00285448004a27ef4adada6943781663 --- /dev/null +++ b/adapters/multi_perspective-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f9e62a8250936a65ca5641f8994564fb7d15db4890c03f81462c06f178e04c +size 27281088 diff --git a/adapters/newton-lora-f16.gguf b/adapters/newton-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..5cecf91e7d25ed705d9ab7bcd2fe68f8940d3898 --- /dev/null +++ b/adapters/newton-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9242685ec0cfbbc383237aeced0ee6f14676785a55930358350bccfab1db5a6f +size 27281088 diff --git a/adapters/philosophy-lora-f16.gguf b/adapters/philosophy-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..320de2dd449c0b9bf5d94c35a26a1d0fe623b8b1 --- /dev/null +++ b/adapters/philosophy-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5157c68f663f0477164f5a7b95a5d89cea0966f8e41ebc49e58141abd96b329a +size 27281088 diff --git a/adapters/quantum-lora-f16.gguf b/adapters/quantum-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..9ad22fd8ccd0487505fe24826515659c51d3bac4 --- /dev/null +++ b/adapters/quantum-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3e3bed6d81d7a72011b031150d81ec8911fa7820539db07f8a949f59a290ff +size 27281088 diff --git a/adapters/systems_architecture-lora-f16.gguf b/adapters/systems_architecture-lora-f16.gguf new file mode 100644 index 0000000000000000000000000000000000000000..03aa12a766156a13f3b4df0e7d94ea791d854922 --- /dev/null +++ b/adapters/systems_architecture-lora-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a653d6c97a5c994d39aafa550a22ee6a23ea1b7f054ad81a595822969cd7f857 +size 27281088