Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: transformers
+model_name: model_tuned
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for model_tuned
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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="VedaantJain/model_tuned", 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/vedaantj/ft-llm/runs/083810)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.2
+- Transformers: 4.46.3
+- Pytorch: 2.1.2+cu118
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+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}}
+}
+```

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.985645933014354,
+    "total_flos": 9149727375360.0,
+    "train_loss": 0.5307981822735224,
+    "train_runtime": 3368.0081,
+    "train_samples": 5060,
+    "train_samples_per_second": 1.115,
+    "train_steps_per_second": 0.093
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9c0ec47315587eb34dba5cd70d3b39b30b09d78dfaa552bc1f5bb2c0e3107d
+size 4972489328

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f479150a15a9c19f7567422a44c4e4f3d6ff3167f5199c0d2f6adb837c6b2e68
+size 2669692552

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.985645933014354,
+    "total_flos": 9149727375360.0,
+    "train_loss": 0.5307981822735224,
+    "train_runtime": 3368.0081,
+    "train_samples": 5060,
+    "train_samples_per_second": 1.115,
+    "train_steps_per_second": 0.093
+}

trainer_state.json

@@ -0,0 +1,507 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.985645933014354,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009569377990430622,
+      "grad_norm": 2.0939094431170635,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0265,
+      "step": 1
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "grad_norm": 1.2308584432431018,
+      "learning_rate": 3.125e-06,
+      "loss": 1.0462,
+      "step": 5
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 0.8192528176324341,
+      "learning_rate": 6.25e-06,
+      "loss": 0.9416,
+      "step": 10
+    },
+    {
+      "epoch": 0.14354066985645933,
+      "grad_norm": 0.5587998098246274,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.8065,
+      "step": 15
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 0.3008165110686449,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6851,
+      "step": 20
+    },
+    {
+      "epoch": 0.23923444976076555,
+      "grad_norm": 0.20347128493031447,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.6537,
+      "step": 25
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 0.17128021850811456,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6333,
+      "step": 30
+    },
+    {
+      "epoch": 0.3349282296650718,
+      "grad_norm": 0.16652191969621177,
+      "learning_rate": 1.9994335583335336e-05,
+      "loss": 0.6149,
+      "step": 35
+    },
+    {
+      "epoch": 0.3827751196172249,
+      "grad_norm": 0.14198363233390676,
+      "learning_rate": 1.9959742939952393e-05,
+      "loss": 0.6082,
+      "step": 40
+    },
+    {
+      "epoch": 0.430622009569378,
+      "grad_norm": 0.21713283105061185,
+      "learning_rate": 1.9893813260530368e-05,
+      "loss": 0.5895,
+      "step": 45
+    },
+    {
+      "epoch": 0.4784688995215311,
+      "grad_norm": 0.13924953869885492,
+      "learning_rate": 1.9796753984232357e-05,
+      "loss": 0.5561,
+      "step": 50
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.13684768549424628,
+      "learning_rate": 1.9668870495450064e-05,
+      "loss": 0.569,
+      "step": 55
+    },
+    {
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.13894406081826732,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.5712,
+      "step": 60
+    },
+    {
+      "epoch": 0.6220095693779905,
+      "grad_norm": 0.14374947839898614,
+      "learning_rate": 1.9322336073880143e-05,
+      "loss": 0.5702,
+      "step": 65
+    },
+    {
+      "epoch": 0.6698564593301436,
+      "grad_norm": 0.14479528353076987,
+      "learning_rate": 1.9104775466588162e-05,
+      "loss": 0.5664,
+      "step": 70
+    },
+    {
+      "epoch": 0.7177033492822966,
+      "grad_norm": 0.14766483692101193,
+      "learning_rate": 1.88585678672358e-05,
+      "loss": 0.5477,
+      "step": 75
+    },
+    {
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.15525222782036766,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 0.5383,
+      "step": 80
+    },
+    {
+      "epoch": 0.8133971291866029,
+      "grad_norm": 0.14420000030755972,
+      "learning_rate": 1.8283398029800167e-05,
+      "loss": 0.5509,
+      "step": 85
+    },
+    {
+      "epoch": 0.861244019138756,
+      "grad_norm": 0.14021638409143689,
+      "learning_rate": 1.795624548881781e-05,
+      "loss": 0.5492,
+      "step": 90
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.13897720896535773,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.535,
+      "step": 95
+    },
+    {
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.144999235947906,
+      "learning_rate": 1.7227948638273918e-05,
+      "loss": 0.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.9952153110047847,
+      "eval_loss": 0.5750399827957153,
+      "eval_runtime": 7.9492,
+      "eval_samples_per_second": 17.109,
+      "eval_steps_per_second": 5.787,
+      "step": 104
+    },
+    {
+      "epoch": 1.0047846889952152,
+      "grad_norm": 0.2609579886738764,
+      "learning_rate": 1.682909582004807e-05,
+      "loss": 0.5801,
+      "step": 105
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.14024934432114472,
+      "learning_rate": 1.6408756139850243e-05,
+      "loss": 0.53,
+      "step": 110
+    },
+    {
+      "epoch": 1.1004784688995215,
+      "grad_norm": 0.14458482486273788,
+      "learning_rate": 1.5968252141825038e-05,
+      "loss": 0.5322,
+      "step": 115
+    },
+    {
+      "epoch": 1.1483253588516746,
+      "grad_norm": 0.14629086236317015,
+      "learning_rate": 1.5508969814521026e-05,
+      "loss": 0.5226,
+      "step": 120
+    },
+    {
+      "epoch": 1.1961722488038278,
+      "grad_norm": 0.15275249319420742,
+      "learning_rate": 1.5032354230058004e-05,
+      "loss": 0.5237,
+      "step": 125
+    },
+    {
+      "epoch": 1.244019138755981,
+      "grad_norm": 0.15270769602744638,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.5101,
+      "step": 130
+    },
+    {
+      "epoch": 1.291866028708134,
+      "grad_norm": 0.14854577877982414,
+      "learning_rate": 1.4033171544008053e-05,
+      "loss": 0.5084,
+      "step": 135
+    },
+    {
+      "epoch": 1.339712918660287,
+      "grad_norm": 0.14092662389201455,
+      "learning_rate": 1.3513748240813429e-05,
+      "loss": 0.518,
+      "step": 140
+    },
+    {
+      "epoch": 1.38755980861244,
+      "grad_norm": 0.13607051872752182,
+      "learning_rate": 1.2983269385691562e-05,
+      "loss": 0.5184,
+      "step": 145
+    },
+    {
+      "epoch": 1.4354066985645932,
+      "grad_norm": 0.14966143078522062,
+      "learning_rate": 1.2443404061378941e-05,
+      "loss": 0.5062,
+      "step": 150
+    },
+    {
+      "epoch": 1.4832535885167464,
+      "grad_norm": 0.15381766051199638,
+      "learning_rate": 1.1895850883916786e-05,
+      "loss": 0.5049,
+      "step": 155
+    },
+    {
+      "epoch": 1.5311004784688995,
+      "grad_norm": 0.1654965470842917,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 0.5027,
+      "step": 160
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.15124728351536673,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.4928,
+      "step": 165
+    },
+    {
+      "epoch": 1.6267942583732058,
+      "grad_norm": 0.1445164484047255,
+      "learning_rate": 1.0224380642958052e-05,
+      "loss": 0.4926,
+      "step": 170
+    },
+    {
+      "epoch": 1.674641148325359,
+      "grad_norm": 0.14421144356382473,
+      "learning_rate": 9.663464344122064e-06,
+      "loss": 0.4953,
+      "step": 175
+    },
+    {
+      "epoch": 1.722488038277512,
+      "grad_norm": 0.14068706673794015,
+      "learning_rate": 9.103606910965666e-06,
+      "loss": 0.5027,
+      "step": 180
+    },
+    {
+      "epoch": 1.7703349282296652,
+      "grad_norm": 0.14082548483803073,
+      "learning_rate": 8.546569862100876e-06,
+      "loss": 0.4853,
+      "step": 185
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.14468108210583894,
+      "learning_rate": 7.994105842167274e-06,
+      "loss": 0.498,
+      "step": 190
+    },
+    {
+      "epoch": 1.8660287081339713,
+      "grad_norm": 0.14087947795424693,
+      "learning_rate": 7.447953107363574e-06,
+      "loss": 0.4763,
+      "step": 195
+    },
+    {
+      "epoch": 1.9138755980861244,
+      "grad_norm": 0.13646275065164523,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.4549,
+      "step": 200
+    },
+    {
+      "epoch": 1.9617224880382775,
+      "grad_norm": 0.13978124622450475,
+      "learning_rate": 6.381429823033281e-06,
+      "loss": 0.4876,
+      "step": 205
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5740731954574585,
+      "eval_runtime": 11.5294,
+      "eval_samples_per_second": 11.796,
+      "eval_steps_per_second": 3.99,
+      "step": 209
+    },
+    {
+      "epoch": 2.0095693779904304,
+      "grad_norm": 0.1395628254838664,
+      "learning_rate": 5.864414950334796e-06,
+      "loss": 0.5258,
+      "step": 210
+    },
+    {
+      "epoch": 2.0574162679425836,
+      "grad_norm": 0.1646035873905585,
+      "learning_rate": 5.360412158221661e-06,
+      "loss": 0.4763,
+      "step": 215
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.1430640678690393,
+      "learning_rate": 4.871007225940939e-06,
+      "loss": 0.4613,
+      "step": 220
+    },
+    {
+      "epoch": 2.15311004784689,
+      "grad_norm": 0.1461980161567961,
+      "learning_rate": 4.397740002471973e-06,
+      "loss": 0.4446,
+      "step": 225
+    },
+    {
+      "epoch": 2.200956937799043,
+      "grad_norm": 0.14316992446211674,
+      "learning_rate": 3.942099561591802e-06,
+      "loss": 0.4654,
+      "step": 230
+    },
+    {
+      "epoch": 2.248803827751196,
+      "grad_norm": 0.16075469053450084,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.4513,
+      "step": 235
+    },
+    {
+      "epoch": 2.2966507177033493,
+      "grad_norm": 0.1555203656237632,
+      "learning_rate": 3.089373510131354e-06,
+      "loss": 0.4645,
+      "step": 240
+    },
+    {
+      "epoch": 2.3444976076555024,
+      "grad_norm": 0.14495139725052797,
+      "learning_rate": 2.694970891187225e-06,
+      "loss": 0.4397,
+      "step": 245
+    },
+    {
+      "epoch": 2.3923444976076556,
+      "grad_norm": 0.14820564306015635,
+      "learning_rate": 2.323552596419889e-06,
+      "loss": 0.4573,
+      "step": 250
+    },
+    {
+      "epoch": 2.4401913875598087,
+      "grad_norm": 0.14625430854110832,
+      "learning_rate": 1.9762872451962214e-06,
+      "loss": 0.4453,
+      "step": 255
+    },
+    {
+      "epoch": 2.488038277511962,
+      "grad_norm": 0.1417828182794398,
+      "learning_rate": 1.6542674627869738e-06,
+      "loss": 0.454,
+      "step": 260
+    },
+    {
+      "epoch": 2.535885167464115,
+      "grad_norm": 0.2347199249792442,
+      "learning_rate": 1.3585064425634542e-06,
+      "loss": 0.4469,
+      "step": 265
+    },
+    {
+      "epoch": 2.583732057416268,
+      "grad_norm": 0.14511063554793874,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.4483,
+      "step": 270
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.14598006035506486,
+      "learning_rate": 8.493974353268019e-07,
+      "loss": 0.459,
+      "step": 275
+    },
+    {
+      "epoch": 2.679425837320574,
+      "grad_norm": 0.15533898050231443,
+      "learning_rate": 6.37651293602628e-07,
+      "loss": 0.4493,
+      "step": 280
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.14147230186128865,
+      "learning_rate": 4.553625646441928e-07,
+      "loss": 0.4344,
+      "step": 285
+    },
+    {
+      "epoch": 2.77511961722488,
+      "grad_norm": 0.1738953363945195,
+      "learning_rate": 3.0310479623313125e-07,
+      "loss": 0.4513,
+      "step": 290
+    },
+    {
+      "epoch": 2.8229665071770333,
+      "grad_norm": 0.15001004355811276,
+      "learning_rate": 1.81357047638816e-07,
+      "loss": 0.4474,
+      "step": 295
+    },
+    {
+      "epoch": 2.8708133971291865,
+      "grad_norm": 0.15435665748487531,
+      "learning_rate": 9.0502382320653e-08,
+      "loss": 0.4543,
+      "step": 300
+    },
+    {
+      "epoch": 2.9186602870813396,
+      "grad_norm": 0.14366671363851222,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.4558,
+      "step": 305
+    },
+    {
+      "epoch": 2.9665071770334928,
+      "grad_norm": 0.1455740191931236,
+      "learning_rate": 2.5176505749346937e-09,
+      "loss": 0.4556,
+      "step": 310
+    },
+    {
+      "epoch": 2.985645933014354,
+      "eval_loss": 0.5831425786018372,
+      "eval_runtime": 13.8937,
+      "eval_samples_per_second": 9.789,
+      "eval_steps_per_second": 3.311,
+      "step": 312
+    },
+    {
+      "epoch": 2.985645933014354,
+      "step": 312,
+      "total_flos": 9149727375360.0,
+      "train_loss": 0.5307981822735224,
+      "train_runtime": 3368.0081,
+      "train_samples_per_second": 1.115,
+      "train_steps_per_second": 0.093
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9149727375360.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc535384880fd37a44458e5a0ed40df06e0cd47adbe05540cc8dc5625583ac8c
+size 7224