Delete auxiliary_decoder

auxiliary_decoder/README.md

@@ -1,21 +0,0 @@
----
-library_name: peft
----
-## Training procedure
-
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-### Framework versions
-
-
-- PEFT 0.4.0

auxiliary_decoder/adapter_config.json

@@ -1,21 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/cpfs01/shared/ADLab/hug_ckpts/vicuna-7b-v1.5",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 16,
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "v_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}

auxiliary_decoder/adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
-size 443

auxiliary_decoder/base/README.md

@@ -1,48 +0,0 @@
----
-inference: false
-license: llama2
----
-
-# Vicuna Model Card
-
-## Model Details
-
-Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
-
-- **Developed by:** [LMSYS](https://lmsys.org/)
-- **Model type:** An auto-regressive language model based on the transformer architecture
-- **License:** Llama 2 Community License Agreement	
-- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
-
-### Model Sources
-
-- **Repository:** https://github.com/lm-sys/FastChat
-- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
-- **Paper:** https://arxiv.org/abs/2306.05685
-- **Demo:** https://chat.lmsys.org/
-
-## Uses
-
-The primary use of Vicuna is research on large language models and chatbots.
-The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
-
-## How to Get Started with the Model
-
-- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
-- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api  
-
-## Training Details
-
-Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning.
-The training data is around 125K conversations collected from ShareGPT.com.
-See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
-
-## Evaluation
-
-![Evaluation Results](https://github.com/lm-sys/lm-sys.github.io/blob/main/public/images/webdata/vicuna_v1.5_eval.png?raw=true)
-
-Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
-
-## Difference between different versions of Vicuna
-
-See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)

auxiliary_decoder/base/config.json

@@ -1,26 +0,0 @@
-{
-  "_name_or_path": "vicuna-7b-v1.5",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
-  "use_cache": true,
-  "vocab_size": 32000
-}

auxiliary_decoder/base/generation_config.json

@@ -1,9 +0,0 @@
-{
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "max_length": 4096,
-  "pad_token_id": 0,
-  "temperature": 0.9,
-  "top_p": 0.6,
-  "transformers_version": "4.31.0"
-}

auxiliary_decoder/base/gitattributes

@@ -1,35 +0,0 @@
-*.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

auxiliary_decoder/base/pytorch_model-00001-of-00002.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4133d2fcc5f31286881ea50806d95b721d016b533036a99dedce3f8fe88520e6
-size 9976634558

auxiliary_decoder/base/pytorch_model-00002-of-00002.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d261d3c35e92d3070d1e61ed821ebfca812a847d2a880757d82728acf005c5ac
-size 3500315539

auxiliary_decoder/base/pytorch_model.bin.index.json

@@ -1,330 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13476839424
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
-  }
-}

auxiliary_decoder/base/special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<unk>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

auxiliary_decoder/base/tokenizer.model

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

auxiliary_decoder/base/tokenizer_config.json

@@ -1,35 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": false,
-  "model_max_length": 4096,
-  "pad_token": null,
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

auxiliary_decoder/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cbcdd53f217ad937d0347e62c442748acb981f5b3e963284f09bd1317f16546f
-size 67216517

auxiliary_decoder/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:99929bd03b48e29ef637de6ede9dd8f967124847190195d30b291479474bd0b6
-size 21687

auxiliary_decoder/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ba9110abd238d877fe40302d3a99ab2a07d0a08a3046bcf8659666a97cf3c4bd
-size 21687

auxiliary_decoder/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c4691041a42ddadbc0735b74ddb085e04a5e4636f3f3a625dff055f67734a886
-size 21687

auxiliary_decoder/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93211ed628a3ffb6234f03a6de1cacf8d171d9c8f5ba068610b72fcf413643e7
-size 21687

auxiliary_decoder/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44ee2aab0f3ad1ccb9a537bac135dd2b5a88a9c5bfb76d04070e78438ba8eb8e
-size 21687

auxiliary_decoder/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c3524f72d69da29ddc7e1b7d2020eaf3c17fdb7760b26b572369cd0febad4de
-size 21687

auxiliary_decoder/rng_state_6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aec123ea87d4cc11d173df7c3aee5d70636a30ffaf7da927e3c3bde634702b9d
-size 21687

auxiliary_decoder/rng_state_7.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb9f4d99b6fdf30377370b405acacb904ee76b422c17d47ee47f0e09827fb2af
-size 21687

auxiliary_decoder/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c767e531f5cc92dcf2b7622466a92b93376b191b8847a14de57d9649808db98
-size 627

auxiliary_decoder/trainer_state.json

@@ -1,787 +0,0 @@
-{
-  "best_metric": 0.3883955776691437,
-  "best_model_checkpoint": "exp/vicuna-7b-lora-sft-code_qa_desc_summ_triplet_r_16_alpha_32_8GPUs-0116/checkpoint-1200",
-  "epoch": 4.375569735642662,
-  "eval_steps": 200,
-  "global_step": 1200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.04,
-      "learning_rate": 2.9999999999999997e-05,
-      "loss": 1.4343,
-      "step": 10
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 5.9999999999999995e-05,
-      "loss": 1.4848,
-      "step": 20
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 8.999999999999999e-05,
-      "loss": 1.1941,
-      "step": 30
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00011999999999999999,
-      "loss": 0.8226,
-      "step": 40
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00015,
-      "loss": 0.6671,
-      "step": 50
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00017999999999999998,
-      "loss": 0.5676,
-      "step": 60
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.00020999999999999998,
-      "loss": 0.5655,
-      "step": 70
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00023999999999999998,
-      "loss": 0.5251,
-      "step": 80
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00027,
-      "loss": 0.4845,
-      "step": 90
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.0003,
-      "loss": 0.481,
-      "step": 100
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.0002976377952755905,
-      "loss": 0.4565,
-      "step": 110
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.0002952755905511811,
-      "loss": 0.4625,
-      "step": 120
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00029291338582677163,
-      "loss": 0.4584,
-      "step": 130
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00029055118110236217,
-      "loss": 0.4425,
-      "step": 140
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.0002881889763779527,
-      "loss": 0.4573,
-      "step": 150
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0002858267716535433,
-      "loss": 0.4361,
-      "step": 160
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00028346456692913383,
-      "loss": 0.4396,
-      "step": 170
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00028110236220472436,
-      "loss": 0.4391,
-      "step": 180
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00027874015748031495,
-      "loss": 0.418,
-      "step": 190
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.0002763779527559055,
-      "loss": 0.4469,
-      "step": 200
-    },
-    {
-      "epoch": 0.73,
-      "eval_loss": 0.4269736409187317,
-      "eval_runtime": 19.352,
-      "eval_samples_per_second": 103.348,
-      "eval_steps_per_second": 1.654,
-      "step": 200
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0002740157480314961,
-      "loss": 0.4149,
-      "step": 210
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00027165354330708656,
-      "loss": 0.428,
-      "step": 220
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00026929133858267715,
-      "loss": 0.4248,
-      "step": 230
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0002669291338582677,
-      "loss": 0.4249,
-      "step": 240
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.0002645669291338582,
-      "loss": 0.4331,
-      "step": 250
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002622047244094488,
-      "loss": 0.4192,
-      "step": 260
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00025984251968503934,
-      "loss": 0.4204,
-      "step": 270
-    },
-    {
-      "epoch": 1.02,
-      "learning_rate": 0.00025748031496062993,
-      "loss": 0.4318,
-      "step": 280
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 0.00025511811023622047,
-      "loss": 0.4229,
-      "step": 290
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 0.000252755905511811,
-      "loss": 0.4214,
-      "step": 300
-    },
-    {
-      "epoch": 1.13,
-      "learning_rate": 0.00025039370078740154,
-      "loss": 0.416,
-      "step": 310
-    },
-    {
-      "epoch": 1.17,
-      "learning_rate": 0.00024803149606299207,
-      "loss": 0.4199,
-      "step": 320
-    },
-    {
-      "epoch": 1.2,
-      "learning_rate": 0.00024566929133858266,
-      "loss": 0.4218,
-      "step": 330
-    },
-    {
-      "epoch": 1.24,
-      "learning_rate": 0.0002433070866141732,
-      "loss": 0.4113,
-      "step": 340
-    },
-    {
-      "epoch": 1.28,
-      "learning_rate": 0.00024094488188976376,
-      "loss": 0.4185,
-      "step": 350
-    },
-    {
-      "epoch": 1.31,
-      "learning_rate": 0.00023858267716535432,
-      "loss": 0.4168,
-      "step": 360
-    },
-    {
-      "epoch": 1.35,
-      "learning_rate": 0.00023622047244094488,
-      "loss": 0.4162,
-      "step": 370
-    },
-    {
-      "epoch": 1.39,
-      "learning_rate": 0.0002338582677165354,
-      "loss": 0.4175,
-      "step": 380
-    },
-    {
-      "epoch": 1.42,
-      "learning_rate": 0.00023149606299212595,
-      "loss": 0.4045,
-      "step": 390
-    },
-    {
-      "epoch": 1.46,
-      "learning_rate": 0.00022913385826771652,
-      "loss": 0.4152,
-      "step": 400
-    },
-    {
-      "epoch": 1.46,
-      "eval_loss": 0.4086858630180359,
-      "eval_runtime": 19.2818,
-      "eval_samples_per_second": 103.725,
-      "eval_steps_per_second": 1.66,
-      "step": 400
-    },
-    {
-      "epoch": 1.49,
-      "learning_rate": 0.00022677165354330705,
-      "loss": 0.415,
-      "step": 410
-    },
-    {
-      "epoch": 1.53,
-      "learning_rate": 0.00022440944881889761,
-      "loss": 0.4091,
-      "step": 420
-    },
-    {
-      "epoch": 1.57,
-      "learning_rate": 0.00022204724409448818,
-      "loss": 0.4132,
-      "step": 430
-    },
-    {
-      "epoch": 1.6,
-      "learning_rate": 0.00021968503937007874,
-      "loss": 0.3985,
-      "step": 440
-    },
-    {
-      "epoch": 1.64,
-      "learning_rate": 0.00021732283464566927,
-      "loss": 0.4056,
-      "step": 450
-    },
-    {
-      "epoch": 1.68,
-      "learning_rate": 0.0002149606299212598,
-      "loss": 0.4005,
-      "step": 460
-    },
-    {
-      "epoch": 1.71,
-      "learning_rate": 0.00021259842519685037,
-      "loss": 0.4059,
-      "step": 470
-    },
-    {
-      "epoch": 1.75,
-      "learning_rate": 0.0002102362204724409,
-      "loss": 0.409,
-      "step": 480
-    },
-    {
-      "epoch": 1.79,
-      "learning_rate": 0.00020787401574803147,
-      "loss": 0.4031,
-      "step": 490
-    },
-    {
-      "epoch": 1.82,
-      "learning_rate": 0.00020551181102362203,
-      "loss": 0.4097,
-      "step": 500
-    },
-    {
-      "epoch": 1.86,
-      "learning_rate": 0.0002031496062992126,
-      "loss": 0.4017,
-      "step": 510
-    },
-    {
-      "epoch": 1.9,
-      "learning_rate": 0.00020078740157480313,
-      "loss": 0.4026,
-      "step": 520
-    },
-    {
-      "epoch": 1.93,
-      "learning_rate": 0.0001984251968503937,
-      "loss": 0.4106,
-      "step": 530
-    },
-    {
-      "epoch": 1.97,
-      "learning_rate": 0.00019606299212598423,
-      "loss": 0.395,
-      "step": 540
-    },
-    {
-      "epoch": 2.01,
-      "learning_rate": 0.0001937007874015748,
-      "loss": 0.3988,
-      "step": 550
-    },
-    {
-      "epoch": 2.04,
-      "learning_rate": 0.00019133858267716532,
-      "loss": 0.409,
-      "step": 560
-    },
-    {
-      "epoch": 2.08,
-      "learning_rate": 0.00018897637795275589,
-      "loss": 0.3997,
-      "step": 570
-    },
-    {
-      "epoch": 2.11,
-      "learning_rate": 0.00018661417322834645,
-      "loss": 0.4007,
-      "step": 580
-    },
-    {
-      "epoch": 2.15,
-      "learning_rate": 0.000184251968503937,
-      "loss": 0.3905,
-      "step": 590
-    },
-    {
-      "epoch": 2.19,
-      "learning_rate": 0.00018188976377952755,
-      "loss": 0.4005,
-      "step": 600
-    },
-    {
-      "epoch": 2.19,
-      "eval_loss": 0.40032637119293213,
-      "eval_runtime": 19.2818,
-      "eval_samples_per_second": 103.725,
-      "eval_steps_per_second": 1.66,
-      "step": 600
-    },
-    {
-      "epoch": 2.22,
-      "learning_rate": 0.0001795275590551181,
-      "loss": 0.3983,
-      "step": 610
-    },
-    {
-      "epoch": 2.26,
-      "learning_rate": 0.00017716535433070864,
-      "loss": 0.3881,
-      "step": 620
-    },
-    {
-      "epoch": 2.3,
-      "learning_rate": 0.00017480314960629918,
-      "loss": 0.4008,
-      "step": 630
-    },
-    {
-      "epoch": 2.33,
-      "learning_rate": 0.00017244094488188974,
-      "loss": 0.3927,
-      "step": 640
-    },
-    {
-      "epoch": 2.37,
-      "learning_rate": 0.0001700787401574803,
-      "loss": 0.4005,
-      "step": 650
-    },
-    {
-      "epoch": 2.41,
-      "learning_rate": 0.00016771653543307086,
-      "loss": 0.3962,
-      "step": 660
-    },
-    {
-      "epoch": 2.44,
-      "learning_rate": 0.0001653543307086614,
-      "loss": 0.3902,
-      "step": 670
-    },
-    {
-      "epoch": 2.48,
-      "learning_rate": 0.00016299212598425196,
-      "loss": 0.3911,
-      "step": 680
-    },
-    {
-      "epoch": 2.52,
-      "learning_rate": 0.00016062992125984252,
-      "loss": 0.3891,
-      "step": 690
-    },
-    {
-      "epoch": 2.55,
-      "learning_rate": 0.00015826771653543303,
-      "loss": 0.3939,
-      "step": 700
-    },
-    {
-      "epoch": 2.59,
-      "learning_rate": 0.0001559055118110236,
-      "loss": 0.4001,
-      "step": 710
-    },
-    {
-      "epoch": 2.63,
-      "learning_rate": 0.00015354330708661416,
-      "loss": 0.3918,
-      "step": 720
-    },
-    {
-      "epoch": 2.66,
-      "learning_rate": 0.00015118110236220472,
-      "loss": 0.3979,
-      "step": 730
-    },
-    {
-      "epoch": 2.7,
-      "learning_rate": 0.00014881889763779525,
-      "loss": 0.3793,
-      "step": 740
-    },
-    {
-      "epoch": 2.73,
-      "learning_rate": 0.00014645669291338582,
-      "loss": 0.3879,
-      "step": 750
-    },
-    {
-      "epoch": 2.77,
-      "learning_rate": 0.00014409448818897635,
-      "loss": 0.3915,
-      "step": 760
-    },
-    {
-      "epoch": 2.81,
-      "learning_rate": 0.00014173228346456691,
-      "loss": 0.3831,
-      "step": 770
-    },
-    {
-      "epoch": 2.84,
-      "learning_rate": 0.00013937007874015748,
-      "loss": 0.3838,
-      "step": 780
-    },
-    {
-      "epoch": 2.88,
-      "learning_rate": 0.00013700787401574804,
-      "loss": 0.3734,
-      "step": 790
-    },
-    {
-      "epoch": 2.92,
-      "learning_rate": 0.00013464566929133857,
-      "loss": 0.3872,
-      "step": 800
-    },
-    {
-      "epoch": 2.92,
-      "eval_loss": 0.3944130539894104,
-      "eval_runtime": 19.2596,
-      "eval_samples_per_second": 103.844,
-      "eval_steps_per_second": 1.662,
-      "step": 800
-    },
-    {
-      "epoch": 2.95,
-      "learning_rate": 0.0001322834645669291,
-      "loss": 0.386,
-      "step": 810
-    },
-    {
-      "epoch": 2.99,
-      "learning_rate": 0.00012992125984251967,
-      "loss": 0.3799,
-      "step": 820
-    },
-    {
-      "epoch": 3.03,
-      "learning_rate": 0.00012755905511811023,
-      "loss": 0.3895,
-      "step": 830
-    },
-    {
-      "epoch": 3.06,
-      "learning_rate": 0.00012519685039370077,
-      "loss": 0.3852,
-      "step": 840
-    },
-    {
-      "epoch": 3.1,
-      "learning_rate": 0.00012283464566929133,
-      "loss": 0.3879,
-      "step": 850
-    },
-    {
-      "epoch": 3.14,
-      "learning_rate": 0.00012047244094488188,
-      "loss": 0.3892,
-      "step": 860
-    },
-    {
-      "epoch": 3.17,
-      "learning_rate": 0.00011811023622047244,
-      "loss": 0.3801,
-      "step": 870
-    },
-    {
-      "epoch": 3.21,
-      "learning_rate": 0.00011574803149606298,
-      "loss": 0.3802,
-      "step": 880
-    },
-    {
-      "epoch": 3.25,
-      "learning_rate": 0.00011338582677165353,
-      "loss": 0.3863,
-      "step": 890
-    },
-    {
-      "epoch": 3.28,
-      "learning_rate": 0.00011102362204724409,
-      "loss": 0.3792,
-      "step": 900
-    },
-    {
-      "epoch": 3.32,
-      "learning_rate": 0.00010866141732283464,
-      "loss": 0.3923,
-      "step": 910
-    },
-    {
-      "epoch": 3.35,
-      "learning_rate": 0.00010629921259842519,
-      "loss": 0.3753,
-      "step": 920
-    },
-    {
-      "epoch": 3.39,
-      "learning_rate": 0.00010393700787401573,
-      "loss": 0.3777,
-      "step": 930
-    },
-    {
-      "epoch": 3.43,
-      "learning_rate": 0.0001015748031496063,
-      "loss": 0.3849,
-      "step": 940
-    },
-    {
-      "epoch": 3.46,
-      "learning_rate": 9.921259842519685e-05,
-      "loss": 0.3775,
-      "step": 950
-    },
-    {
-      "epoch": 3.5,
-      "learning_rate": 9.68503937007874e-05,
-      "loss": 0.3853,
-      "step": 960
-    },
-    {
-      "epoch": 3.54,
-      "learning_rate": 9.448818897637794e-05,
-      "loss": 0.3719,
-      "step": 970
-    },
-    {
-      "epoch": 3.57,
-      "learning_rate": 9.21259842519685e-05,
-      "loss": 0.3779,
-      "step": 980
-    },
-    {
-      "epoch": 3.61,
-      "learning_rate": 8.976377952755905e-05,
-      "loss": 0.3921,
-      "step": 990
-    },
-    {
-      "epoch": 3.65,
-      "learning_rate": 8.740157480314959e-05,
-      "loss": 0.3776,
-      "step": 1000
-    },
-    {
-      "epoch": 3.65,
-      "eval_loss": 0.3908761739730835,
-      "eval_runtime": 19.2678,
-      "eval_samples_per_second": 103.8,
-      "eval_steps_per_second": 1.661,
-      "step": 1000
-    },
-    {
-      "epoch": 3.68,
-      "learning_rate": 8.503937007874015e-05,
-      "loss": 0.3889,
-      "step": 1010
-    },
-    {
-      "epoch": 3.72,
-      "learning_rate": 8.26771653543307e-05,
-      "loss": 0.3819,
-      "step": 1020
-    },
-    {
-      "epoch": 3.76,
-      "learning_rate": 8.031496062992126e-05,
-      "loss": 0.3758,
-      "step": 1030
-    },
-    {
-      "epoch": 3.79,
-      "learning_rate": 7.79527559055118e-05,
-      "loss": 0.3753,
-      "step": 1040
-    },
-    {
-      "epoch": 3.83,
-      "learning_rate": 7.559055118110236e-05,
-      "loss": 0.3737,
-      "step": 1050
-    },
-    {
-      "epoch": 3.87,
-      "learning_rate": 7.322834645669291e-05,
-      "loss": 0.3833,
-      "step": 1060
-    },
-    {
-      "epoch": 3.9,
-      "learning_rate": 7.086614173228346e-05,
-      "loss": 0.3625,
-      "step": 1070
-    },
-    {
-      "epoch": 3.94,
-      "learning_rate": 6.850393700787402e-05,
-      "loss": 0.3809,
-      "step": 1080
-    },
-    {
-      "epoch": 3.97,
-      "learning_rate": 6.614173228346455e-05,
-      "loss": 0.3751,
-      "step": 1090
-    },
-    {
-      "epoch": 4.01,
-      "learning_rate": 6.377952755905512e-05,
-      "loss": 0.3776,
-      "step": 1100
-    },
-    {
-      "epoch": 4.05,
-      "learning_rate": 6.141732283464567e-05,
-      "loss": 0.3748,
-      "step": 1110
-    },
-    {
-      "epoch": 4.08,
-      "learning_rate": 5.905511811023622e-05,
-      "loss": 0.3636,
-      "step": 1120
-    },
-    {
-      "epoch": 4.12,
-      "learning_rate": 5.669291338582676e-05,
-      "loss": 0.372,
-      "step": 1130
-    },
-    {
-      "epoch": 4.16,
-      "learning_rate": 5.433070866141732e-05,
-      "loss": 0.3795,
-      "step": 1140
-    },
-    {
-      "epoch": 4.19,
-      "learning_rate": 5.196850393700787e-05,
-      "loss": 0.3632,
-      "step": 1150
-    },
-    {
-      "epoch": 4.23,
-      "learning_rate": 4.960629921259842e-05,
-      "loss": 0.3806,
-      "step": 1160
-    },
-    {
-      "epoch": 4.27,
-      "learning_rate": 4.724409448818897e-05,
-      "loss": 0.3732,
-      "step": 1170
-    },
-    {
-      "epoch": 4.3,
-      "learning_rate": 4.488188976377953e-05,
-      "loss": 0.3818,
-      "step": 1180
-    },
-    {
-      "epoch": 4.34,
-      "learning_rate": 4.2519685039370076e-05,
-      "loss": 0.3766,
-      "step": 1190
-    },
-    {
-      "epoch": 4.38,
-      "learning_rate": 4.015748031496063e-05,
-      "loss": 0.3587,
-      "step": 1200
-    },
-    {
-      "epoch": 4.38,
-      "eval_loss": 0.3883955776691437,
-      "eval_runtime": 19.3219,
-      "eval_samples_per_second": 103.51,
-      "eval_steps_per_second": 1.656,
-      "step": 1200
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1370,
-  "num_train_epochs": 5,
-  "save_steps": 200,
-  "total_flos": 2.2400975031249142e+18,
-  "trial_name": null,
-  "trial_params": null
-}

auxiliary_decoder/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f06e9a16a0ff4f4a3e1848a5ee5ca4d1a18dde6f70aaad64595a234fd7300b7f
-size 4155