初始化项目，由ModelHub XC社区提供模型

Model: laion/delphi-9e19-p33m67-coldstart-magpie_lr5e6
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+checkpoint-24107/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft__magpie-delphi_warmup__delphi-9e19-p33m67__delphi-5e-06__delphi-3e18-p33m67-k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft__magpie-delphi_warmup__delphi-9e19-p33m67__delphi-5e-06__delphi-3e18-p33m67-k
+
+This model was trained from scratch on the magpie and the delphi_warmup datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 16
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.00032810419238827194,
+    "achieved_tflops_per_gpu_theoretical": 38.77697049801523,
+    "epoch": 1.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.9718374013900757,
+    "mfu_percent": 0.00010516160012444614,
+    "mfu_percent_theoretical": 12.42851618526129,
+    "total_flos": 163931731302400.0,
+    "train_loss": 0.9905494757236973,
+    "train_runtime": 31227.0719,
+    "train_samples_per_second": 17.79,
+    "train_steps_per_second": 1.112,
+    "valid_targets_mean": 681.9,
+    "valid_targets_min": 279
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}

checkpoint-S24107/chat_template.jinja

@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}

checkpoint-S24107/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1792,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "no_bias": true,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 14,
+  "pad_token_id": 128009,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 128256
+}

checkpoint-S24107/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "pad_token_id": 128009,
+  "transformers_version": "4.57.6"
+}

checkpoint-S24107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71506d17f6087092295a012136f843c37c62b3d50cd27f0e06eb1c62a433d315
+size 2769191992

checkpoint-S24107/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-S24107/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4badeeda359a84c6d9efca84271f5bb44396cb95e215b1864b763c35cc6f6c9
+size 17209844

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1792,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "no_bias": true,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 14,
+  "pad_token_id": 128009,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "pad_token_id": 128009,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b854351b8e7c957771f20bb5424b67425b6828d214ea279bb656c6d0ed58c245
+size 2769191992

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "magpie,delphi_warmup",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "/leonardo_work/AIFAC_5C0_290/bfeuer00/data/delphi-tok-prep/delphi-9e19-p33m67",
+  "dataset_name": "magpie,delphi_warmup",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/delphi-9e19-p33m67-coldstart-magpie_lr5e6/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft__magpie-delphi_warmup__delphi-9e19-p33m67__delphi-5e-06__delphi-3e18-p33m67-k",
+  "traces_location_s3": null
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4badeeda359a84c6d9efca84271f5bb44396cb95e215b1864b763c35cc6f6c9
+size 17209844

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.00032810419238827194,
+    "achieved_tflops_per_gpu_theoretical": 38.77697049801523,
+    "epoch": 1.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.9718374013900757,
+    "mfu_percent": 0.00010516160012444614,
+    "mfu_percent_theoretical": 12.42851618526129,
+    "total_flos": 163931731302400.0,
+    "train_loss": 0.9905494757236973,
+    "train_runtime": 31227.0719,
+    "train_samples_per_second": 17.79,
+    "train_steps_per_second": 1.112,
+    "valid_targets_mean": 681.9,
+    "valid_targets_min": 279
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592ce2a8c5fbb9d8a1060b1e915c3fa583c51ddd2845d202819fa02f2d0cef06
+size 8785

training_logs/all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.00032810419238827194,
+    "achieved_tflops_per_gpu_theoretical": 38.77697049801523,
+    "epoch": 1.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.9718374013900757,
+    "mfu_percent": 0.00010516160012444614,
+    "mfu_percent_theoretical": 12.42851618526129,
+    "total_flos": 163931731302400.0,
+    "train_loss": 0.9905494757236973,
+    "train_runtime": 31227.0719,
+    "train_samples_per_second": 17.79,
+    "train_steps_per_second": 1.112,
+    "valid_targets_mean": 681.9,
+    "valid_targets_min": 279
+}

training_logs/train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.00032810419238827194,
+    "achieved_tflops_per_gpu_theoretical": 38.77697049801523,
+    "epoch": 1.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.9718374013900757,
+    "mfu_percent": 0.00010516160012444614,
+    "mfu_percent_theoretical": 12.42851618526129,
+    "total_flos": 163931731302400.0,
+    "train_loss": 0.9905494757236973,
+    "train_runtime": 31227.0719,
+    "train_samples_per_second": 17.79,
+    "train_steps_per_second": 1.112,
+    "valid_targets_mean": 681.9,
+    "valid_targets_min": 279
+}