Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+model_name: Qwen-2.5-7B-Simple-RL
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen-2.5-7B-Simple-RL
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="namazifar/Qwen-2.5-7B-Simple-RL", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rlhf-m-d/huggingface/runs/h2hyfw3t) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.05658998479865941,
+    "train_runtime": 6508.7782,
+    "train_samples": 7500,
+    "train_samples_per_second": 1.152,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/checkpoint-fsx/mahdinam-sandbox/nova/1.0/8B-R3-SFT/",
+  "architectures": [
+    "AlexaLlamaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 108,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 109,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 65536,
+  "model_type": "alexallm-v2",
+  "moe_ffn_hidden_size": null,
+  "moe_frequency": 1,
+  "moe_router_activation": "sigmoid",
+  "moe_shared_experts": 0,
+  "moe_topk": 1,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_moe_experts": 1,
+  "num_query_groups": 8,
+  "original_max_position_embeddings": 2048,
+  "pad_token_id": 0,
+  "position_abf_factor": 200,
+  "position_interpolation_factor": 1.0,
+  "residual_dropout": 0.0,
+  "rms_norm_eps": 1e-06,
+  "rope_state": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_flash_attention": true,
+  "use_flash_mlp": false,
+  "vocab_size": 129832,
+  "yarn_scale": 1.0
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 108,
+  "eos_token_id": 109,
+  "pad_token_id": 0,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976c1bacc144ffc22416ce0daa09d70916849bbc94d3eb703035bbf48836e9d5
+size 4997980680

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6518c72c309c31cd139dfc36d297be6eef81176fad68e0bfb60719953f35f09e
+size 4907510240

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be5a7ebba20c7490e9216c2596005808365fac418690276654e2aea62f4ad7f
+size 4999784832

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d6d74180fc7accd3834e432bb4913cd95d92727d9ac2ddef24a80536d46c28
+size 2791714560

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 17696956416
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "▁[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "▁[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f61fedb747d57a6b385c33ec4fd9026eb5b9a6b2c59c92525dc3726284daf5
+size 2281869

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "▁[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "109": {
+      "content": "▁[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "112": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "▁[BOS]",
+  "chat_template": "{% set BEGIN_TOOL_USE_TOKEN = '<tool>' %}{% set END_TOOL_USE_TOKEN = '</tool>' %}{% set IMAGE_RESERVED_TOKEN = '<image>' %}{% set VIDEO_RESERVED_TOKEN = '<video>' %}{% set MEDIA_TOKEN_SEP = '\n' %}{% set DEFAULT_SYSTEM_MSG = 'A chat between a curious User and an artificial intelligence Bot. The Bot gives helpful, detailed, and polite answers to the User\\'s questions.' %}{% set GLOBAL = namespace(TOOL_USE_ORDERED = []) %}{% macro has_system_content_blocks(system) %}{% set result = namespace(value = '') %}{% if system is string %}{% set result.value = 'True' %}{% elif system is iterable and system is not mapping %}{% for item in system %}{% if item is string or 'text' in item or 'image' in item or 'video' in item %}{% set result.value = 'True' %}{% endif %}{% endfor %}{% endif %}{{ result.value }}{% endmacro %}{% macro format_param_schema(param_name, schema, is_required) %}{% if schema is undefined or not schema is mapping %}{{ raise_exception('Invalid json in tool input schema. Expected a valid JSON Schema object for ' ~ param_name ~ ' parameter.') }}{% endif %}{{ '{' }}{% for k,v in schema.items() %}{% if k == \"required\" %}{{ '\"required_properties\": '}}{% else %}{{ '\"'~ k ~ '\": ' }}{% endif %}{{ v | tojson }}{% if not loop.last %}{{ ', ' }}{% elif is_required %}{{ ', \"required\": True' }}{% endif %}{% endfor %}{{ '}' }}{% endmacro %}{% macro format_tool_input_schema(json_schema) %}{% if json_schema is undefined %}{{ '\"arguments\": {}' }}{% else %}{% if not json_schema is mapping %}{{ raise_exception('Invalid json in tool input schema. Expected a valid JSON Schema object.') }}{% endif %}{% for key in json_schema %}{% if not key in ['type', 'properties', 'required'] %}{{ raise_exception('Invalid json in tool input schema. Unexpected key \\'' ~ key ~'\\'. Only [\\'type\\', \\'properties\\', \\'required\\'] are supported.') }}{% endif %}{% endfor %}{% if json_schema['type'] is undefined or json_schema['type'] != 'object' %}{{ raise_exception('Invalid json in tool input schema. Expected key \\'type\\' with value \\'object\\'.') }}{% endif %}{% if json_schema['properties'] is undefined %}{{ '\"arguments\": {}' }}{% else %}{{ '\"arguments\": {' }}{% for k,v in json_schema['properties'].items() %}{{ '\"' ~ k ~ '\": ' }}{% set is_required = true if json_schema['required'] is defined and k in json_schema['required'] %}{{ format_param_schema(k, v, is_required) }}{{ ', ' if not loop.last }}{% endfor %}{{ '}' }}{% endif %}{% endif %}{% endmacro %}{% macro format_tool_def(tool) %}{% set toolDef = tool['toolSpec'] %}{% if toolDef is undefined %}{{ raise_exception('Invalid tool definition. Expected key \\'toolSpec\\' in tool definition.') }}{% endif %}{% if toolDef['name'] is undefined %}{{ raise_exception('Invalid tool specification. Expected key \\'name\\' in tool specification.') }}{% endif %}{% set input_schema = toolDef['inputSchema'] %}{% if input_schema is undefined %}{{ raise_exception('Invalid tool specification. Expected key \\'inputSchema\\' in tool specification.') }}{% endif %}{{ '{\"name\": \"' }}{{ toolDef['name'] }}{{ '\", ' }}{% if toolDef['description'] is defined %}{{ '\"description\": \"' }}{{ toolDef['description'] }}{{ '\", ' }}{% endif %}{{ format_tool_input_schema(input_schema['json']) }}{{ '}' }}{% endmacro %}{% macro format_pythonic_function_params(json_object) %}{% for k,v in json_object.items() %}{{ k }}{{ '=' }}{{ v | tojson }}{{', ' if not loop.last}}{% endfor %}{% endmacro %}{% macro format_tool_use(tool_use_blocks)%}{{ BEGIN_TOOL_USE_TOKEN }}{{ ' [' }}{% for tool_use in tool_use_blocks %}{% set tool_name = tool_use.get('name') %}{% set tool_params = tool_use.get('input') %}{% if not tool_name is defined %}{{ raise_exception('Invalid tool use block. Expected key ''name'' in tool use block.') }}{% endif %}{% if not tool_params is defined %}{{ raise_exception('Invalid tool use block. Expected key ''input'' in tool use block.') }}{% endif %}{{ tool_name }}{{ '(' }}{{ format_pythonic_function_params(tool_params) }}{{ ')' }}{{', ' if not loop.last}}{% endfor %}{{ '] ' }}{{ END_TOOL_USE_TOKEN }}{% endmacro %}{% macro find_tool_name(tool_use_ordered, use_id) %}{% for tool_use in tool_use_ordered %}{% if tool_use['toolUseId'] == use_id %}{{ tool_use['name'] }}{% endif %}{% else %}{{ raise_exception('Invalid tool use id: ' ~ use_id) }}{% endfor %}{% endmacro %}{% macro format_tool_result(tool_result_blocks, tool_use_ordered) %}{% set ordered = namespace(tool_results = []) %}{% for tool_use in tool_use_ordered %}{% for tool_result in tool_result_blocks %}{% if tool_result['toolUseId'] == tool_use['toolUseId'] %}{% set ordered.tool_results = ordered.tool_results + [tool_result] %}{% endif %}{% endfor %}{% endfor %}{% if (ordered.tool_results | length) != (tool_result_blocks | length) %}{{ raise_exception('Invalid tool result blocks. Not every tool result has corresponding tool use.') }}{% endif %}{{ 'Resource: {\"toolResult\": ['}}{% for tool_result in ordered.tool_results %}{{ '{\"tool_name\": \"' }}{{ find_tool_name(tool_use_ordered, tool_result['toolUseId']) }}{{ '\", \"result\": ' }}{% set content = tool_result.get('content') %}{% if content is undefined or content | length == 0 %}{% if tool_result.get('status') == 'error' %}{{ '\"unknown error occured\"' }}{% else %}{{ '\"\"' }}{% endif %}{% else %}{% if content is iterable and content | length == 1 and content[0]['json'] is defined %}{{ content[0]['json'] | tojson }}{% else %}{% if content is iterable and (content | selectattr('json', 'defined') | list | length > 0) %}{{ raise_exception('Invalid tool result content. Expected either single JSON block or array of non-JSON blocks.') }}{% endif %}{% set content_formatted = get_shorthand_content(content) %}{{ '\"' }}{{ content_formatted }}{{ '\"' }}{% endif %}{% endif %}{{ '}' }}{{', ' if not loop.last}}{% endfor %}{{ ']}' }}{% endmacro %}{% macro get_shorthand_content(content) %}{% if content is string %}{{ content | trim }}{% elif content is iterable and content is not mapping %}{% set local=namespace(tool_use_ordered = [], tool_results_ordered = []) %}{% for item in content %}{% if 'text' in item %}{{ item['text'] | trim }}{{' ' if not loop.last}}{% elif 'image' in item %}{{ IMAGE_RESERVED_TOKEN }}{{ MEDIA_TOKEN_SEP }}{% elif 'video' in item %}{{ VIDEO_RESERVED_TOKEN }}{{ MEDIA_TOKEN_SEP }}{% elif 'toolResult' in item %}{% set local.tool_results_ordered = local.tool_results_ordered + [item['toolResult']] %}{% if loop.last or 'toolResult' not in content[loop.index]  %}{{ format_tool_result(local.tool_results_ordered, GLOBAL.TOOL_USE_ORDERED) }}{{' ' if not loop.last}}{% set local.tool_results_ordered = [] %}{% endif %}{% elif 'toolUse' in item %}{% set local.tool_use_ordered = local.tool_use_ordered + [item['toolUse']] %}{% set GLOBAL.TOOL_USE_ORDERED = GLOBAL.TOOL_USE_ORDERED + [item['toolUse']] %}{% if loop.last or 'toolUse' not in content[loop.index]  %}{{ format_tool_use(local.tool_use_ordered) }}{{' ' if not loop.last}}{% set local.tool_use_ordered = [] %}{% endif %}{% endif %}{% endfor %}{% else %}{{ raise_exception('Invalid type for message[''content'']. Expected types are only String and List') }}{% endif %}{% endmacro %}{% macro get_system_prompt_content(system, toolConfig) %}{% if system is defined and has_system_content_blocks(system) == 'True' %}{% set system_msg = DEFAULT_SYSTEM_MSG + ' ' + get_shorthand_content(system) %}{% else %}{% set system_msg = DEFAULT_SYSTEM_MSG %}{% endif %}{{ system_msg }}{% if toolConfig is defined %}{% set toolChoice = toolConfig['toolChoice'] %}{% if toolChoice is defined and ('any' in toolChoice or 'tool' in toolChoice) %}{{ raise_exception('Invalid tool configuration. Only supported toolChoice value is \\'auto\\'.') }}{% endif %}{% set tools_list = toolConfig['tools'] %}{% if tools_list is undefined %}{{ raise_exception('Invalid tool configuration. Expected key \\'tools\\' in tool configuration.') }}{% endif %}{{ ' ' if system_msg[-1] | trim | length > 0 else '' }}{{ 'In this session, the model has access to external functionalities.\n' }}{{ 'To assist the user, you can reply to the user or invoke an action. Only invoke actions if relevant to the user request.\n\n' }}{{ 'The following actions are available:\n' }}{% for tool in tools_list %}{{ '- ' }}{{ format_tool_def(tool) }}{{ '\n' }}{% endfor %}{{ '\nModel Instructions:\n' }}{{ '- To invoke an action, begin with ' }}{{ BEGIN_TOOL_USE_TOKEN }}{{ ' and end with ' }}{{ END_TOOL_USE_TOKEN }}{{ '. Generate Pythonic action calls and place them in an array, e.g., ' }}{{ BEGIN_TOOL_USE_TOKEN }}{{ ' [action1(arg1=val1, ...), action2(arg1=val1)] ' }}{{ END_TOOL_USE_TOKEN }}{{ '.' }}\n{% endif %}{% endmacro %}{% macro validate_roles(messages) %}{% set roles = messages | map(attribute='role') | unique | list %}{% set allowed_roles = ['user', 'bot', 'system', 'assistant'] %}{% if ('bot' in roles and 'assistant' in roles) or (roles | reject('in', allowed_roles) | list | length > 0) %}{{ raise_exception('Message roles: [' + roles | join(', ') + '] has unexpected role(s)') }}{% endif %}{% endmacro %}{% macro get_prompt() %}{{ validate_roles(messages) }}{% for message in messages %}{% if loop.index == 1 %}{% if message['role'] != 'system' %}{% set SYSTEM_MSG = get_system_prompt_content(system, toolConfig)%}{% elif system is defined %}{{ raise_exception('system field is defined, unexpected system role in messages') }}{% else %}{% set SYSTEM_MSG = get_system_prompt_content(message['content'], toolConfig) %}{% endif %}{{ SYSTEM_MSG }}{{ ' ' if SYSTEM_MSG[-1] | trim | length > 0 else '' }}{% endif %}{% if beliefAugmentation is defined and beliefAugmentation | length != 0 %}{% set BELIEF_AUGMENTATION_SEP = '\n' %}{{get_shorthand_content(beliefAugmentation)}}{{BELIEF_AUGMENTATION_SEP}}{% endif %}{% if message['role'] == 'user' %}{{'User: ' }}{{get_shorthand_content(message['content'])}}{% elif message['role'] == 'bot' or message['role'] == 'assistant' %}{{'Bot: ' }}{{get_shorthand_content(message['content'])}}{{'' if loop.last else ' [EOS]'}}{% elif message['role'] == 'system' and loop.index != 1 %}{{ raise_exception('Unexpected system message in the middle of the messages') }}{% endif %}{{ ' ' if not loop.last and message['role'] != 'system' else '' }}{{ ' Bot:' if loop.last and message['role'] == 'user' else '' }}{% endfor %}{% endmacro %}{% set prompt = get_prompt() %}{{'[BOS] ' + prompt if prompt else prompt}}",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_not_add_bos": false,
+  "do_not_add_eos": true,
+  "eos_token": "▁[EOS]",
+  "escape_sp_char": true,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "newline_tag": "[NEWLINE]",
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "process_newline_and_tabs": false,
+  "sep_token": "</s>",
+  "strip_trail_spaces": false,
+  "tab_tag": "[TAB]",
+  "tokenizer_class": "AlexaLLMTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.05658998479865941,
+    "train_runtime": 6508.7782,
+    "train_samples": 7500,
+    "train_samples_per_second": 1.152,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9893390191897654,
+  "eval_steps": 100,
+  "global_step": 58,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 373.13706970214844,
+      "epoch": 0.08528784648187633,
+      "grad_norm": 2.1630916595458984,
+      "kl": 0.001761174201965332,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0001,
+      "reward": 0.9339286163449287,
+      "reward_std": 0.3458739034831524,
+      "rewards/accuracy_reward": 0.23258929550647736,
+      "rewards/format_reward": 0.7013393118977547,
+      "step": 5
+    },
+    {
+      "completion_length": 357.8872917175293,
+      "epoch": 0.17057569296375266,
+      "grad_norm": 5.1070876121521,
+      "kl": 0.37891845703125,
+      "learning_rate": 2.956412726139078e-06,
+      "loss": 0.0152,
+      "reward": 0.9741071835160255,
+      "reward_std": 0.33634802624583243,
+      "rewards/accuracy_reward": 0.22723215203732253,
+      "rewards/format_reward": 0.7468750372529029,
+      "step": 10
+    },
+    {
+      "completion_length": 348.8261344909668,
+      "epoch": 0.255863539445629,
+      "grad_norm": 5.793032169342041,
+      "kl": 0.804296875,
+      "learning_rate": 2.7836719084521715e-06,
+      "loss": 0.0322,
+      "reward": 1.0337054029107093,
+      "reward_std": 0.33858824484050276,
+      "rewards/accuracy_reward": 0.24732144214212895,
+      "rewards/format_reward": 0.7863839656114578,
+      "step": 15
+    },
+    {
+      "completion_length": 346.17434616088866,
+      "epoch": 0.3411513859275053,
+      "grad_norm": 1.532250165939331,
+      "kl": 0.85458984375,
+      "learning_rate": 2.4946839873611927e-06,
+      "loss": 0.0342,
+      "reward": 1.0790179044008255,
+      "reward_std": 0.35572994202375413,
+      "rewards/accuracy_reward": 0.27433036975562575,
+      "rewards/format_reward": 0.8046875387430191,
+      "step": 20
+    },
+    {
+      "completion_length": 347.5040344238281,
+      "epoch": 0.42643923240938164,
+      "grad_norm": 2.3722541332244873,
+      "kl": 1.31669921875,
+      "learning_rate": 2.1156192081791355e-06,
+      "loss": 0.0527,
+      "reward": 1.1087053999304772,
+      "reward_std": 0.35302889049053193,
+      "rewards/accuracy_reward": 0.28437501229345796,
+      "rewards/format_reward": 0.8243303969502449,
+      "step": 25
+    },
+    {
+      "completion_length": 357.7453266143799,
+      "epoch": 0.511727078891258,
+      "grad_norm": 6.4789137840271,
+      "kl": 1.504296875,
+      "learning_rate": 1.6808050203829845e-06,
+      "loss": 0.0602,
+      "reward": 1.078571479022503,
+      "reward_std": 0.38525725305080416,
+      "rewards/accuracy_reward": 0.3113839436322451,
+      "rewards/format_reward": 0.7671875327825546,
+      "step": 30
+    },
+    {
+      "completion_length": 347.7029151916504,
+      "epoch": 0.5970149253731343,
+      "grad_norm": 5.793887615203857,
+      "kl": 1.673046875,
+      "learning_rate": 1.2296174432791415e-06,
+      "loss": 0.0669,
+      "reward": 1.115625049173832,
+      "reward_std": 0.3930562749505043,
+      "rewards/accuracy_reward": 0.31540180221199987,
+      "rewards/format_reward": 0.8002232521772384,
+      "step": 35
+    },
+    {
+      "completion_length": 332.5259094238281,
+      "epoch": 0.6823027718550106,
+      "grad_norm": 10.747057914733887,
+      "kl": 1.9728515625,
+      "learning_rate": 8.029152419343472e-07,
+      "loss": 0.0789,
+      "reward": 1.132366120815277,
+      "reward_std": 0.3926612690091133,
+      "rewards/accuracy_reward": 0.31651787310838697,
+      "rewards/format_reward": 0.8158482581377029,
+      "step": 40
+    },
+    {
+      "completion_length": 345.2725601196289,
+      "epoch": 0.767590618336887,
+      "grad_norm": 5.969154357910156,
+      "kl": 2.1015625,
+      "learning_rate": 4.3933982822017883e-07,
+      "loss": 0.084,
+      "reward": 1.1439732566475869,
+      "reward_std": 0.3879304490983486,
+      "rewards/accuracy_reward": 0.30178572721779345,
+      "rewards/format_reward": 0.842187537252903,
+      "step": 45
+    },
+    {
+      "completion_length": 337.36385345458984,
+      "epoch": 0.8528784648187633,
+      "grad_norm": 5.109945774078369,
+      "kl": 2.0640625,
+      "learning_rate": 1.718159615201853e-07,
+      "loss": 0.0826,
+      "reward": 1.1687500596046447,
+      "reward_std": 0.40620823949575424,
+      "rewards/accuracy_reward": 0.3241071570664644,
+      "rewards/format_reward": 0.8446428969502449,
+      "step": 50
+    },
+    {
+      "completion_length": 335.0609535217285,
+      "epoch": 0.9381663113006397,
+      "grad_norm": 3.530726432800293,
+      "kl": 2.1984375,
+      "learning_rate": 2.4570139579284723e-08,
+      "loss": 0.0879,
+      "reward": 1.1783482611179352,
+      "reward_std": 0.40133031979203226,
+      "rewards/accuracy_reward": 0.33839287236332893,
+      "rewards/format_reward": 0.8399553969502449,
+      "step": 55
+    },
+    {
+      "completion_length": 334.10566838582355,
+      "epoch": 0.9893390191897654,
+      "kl": 2.4319661458333335,
+      "reward": 1.16815481086572,
+      "reward_std": 0.38675514981150627,
+      "rewards/accuracy_reward": 0.35342263368268806,
+      "rewards/format_reward": 0.8147321790456772,
+      "step": 58,
+      "total_flos": 0.0,
+      "train_loss": 0.05658998479865941,
+      "train_runtime": 6508.7782,
+      "train_samples_per_second": 1.152,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 58,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7e0052f80891a794de87751af9a14a72af04db8aed52f35bdd38ec9755bdef
+size 7480