Release v1

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+datasets:
+- Anthropic/hh-rlhf
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- rlhf
+- alignment
+- simulation
+- computational social science
+---
+
+
+# Model Card for So(cially)-Good LM
+
+![model image](https://agwarbliu.s3.amazonaws.com/logo.png)
+
+![model image](https://agwarbliu.s3.amazonaws.com/model_select_ours.png)
+
+
+**Fast, Effective, and Stable alternative of RLHF!**
+
+**Instead of training an additional reward model that is likely to be gamed, we directly train the model on the social games!** 🕹️ 🎲 🎮
+
+Full details on simulation and training can be found [here](https://github.com/agi-templar/Stable-Alignment).
+
+# Training Procedure
+
+Trained on 8xA100s for 3H. The start checkpoint is the [SFT model](https://huggingface.co/agi-css/hh-rlhf-sft)). We have also released the [better-base model](https://huggingface.co/agi-css/better-base) which is the start checkpoint of SFT.
+
+Here is the training script:
+
+```shell
+torchrun --nproc_per_node=8 --master_port=36646 train_alignment.py \
+    --model_name_or_path /workspace/hhh-sft \
+    --data_path /workspace/sandbox_v1.json \
+    --bf16 True \
+    --output_dir /workspace/output_lm \
+    --num_train_epochs 2 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --evaluation_strategy "no" \
+    --save_strategy "steps" \
+    --save_steps 200 \
+    --save_total_limit 1 \
+    --learning_rate 2e-5 \
+    --weight_decay 0. \
+    --warmup_ratio 0.03 \
+    --lr_scheduler_type "cosine" \
+    --logging_steps 1 \
+    --fsdp "full_shard auto_wrap" \
+    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
+    --tf32 True \
+    --model_max_length 480 \
+    --rating_scale 7 \
+    --margin 1 \
+    --max_flow False \
+    --ratio 0.2 \
+    --num_comp 3
+```
+
+# Bias, Risks, and Limitations
+
+Although this project aims to better align current LMs with social norms, inappropriate content and inherent biases in the training data will still impair the alignment of the model.
+
+SoGood LM should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/media/css_models/new_v8_v7",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1490442efeb2f97da9b86e117a0144512c00c78cabe303031e86bdbd9d922d23
+size 9878008210

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bd1f969dd21cb731fa4f47a49b50814be831b0a7187c4efd7c4a62f09e360e
+size 9894803382

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98292204ce39eb4c55b93a23141558a794f65fdd7f7d0b04574d76ff7a88101
+size 7181008761

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 192,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/media/css_models/new_v8/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1969 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9938461538461538,
+  "global_step": 324,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.9766,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.987,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6e-06,
+      "loss": 2.455,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.4113,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-05,
+      "loss": 2.2854,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.2e-05,
+      "loss": 1.8355,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.4e-05,
+      "loss": 1.916,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.8224,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8e-05,
+      "loss": 1.7426,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2e-05,
+      "loss": 1.7137,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9999499496831964e-05,
+      "loss": 1.7565,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9997998037428528e-05,
+      "loss": 1.5721,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9995495772086735e-05,
+      "loss": 1.6722,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999199295128493e-05,
+      "loss": 1.5741,
+      "step": 14
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.99874899256577e-05,
+      "loss": 1.5782,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.998198714596076e-05,
+      "loss": 1.5812,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9975485163025837e-05,
+      "loss": 1.6109,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.996798462770555e-05,
+      "loss": 1.8711,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.995948629080824e-05,
+      "loss": 1.5257,
+      "step": 19
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.994999100302281e-05,
+      "loss": 1.468,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.993949971483358e-05,
+      "loss": 1.5347,
+      "step": 21
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.992801347642515e-05,
+      "loss": 1.5208,
+      "step": 22
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9915533437577264e-05,
+      "loss": 1.5473,
+      "step": 23
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9902060847549716e-05,
+      "loss": 1.5837,
+      "step": 24
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9887597054957304e-05,
+      "loss": 1.5577,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.987214350763483e-05,
+      "loss": 1.7363,
+      "step": 26
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9855701752492174e-05,
+      "loss": 1.5417,
+      "step": 27
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9838273435359447e-05,
+      "loss": 1.427,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9819860300822227e-05,
+      "loss": 1.6365,
+      "step": 29
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9800464192046956e-05,
+      "loss": 1.6032,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9780087050596407e-05,
+      "loss": 1.4046,
+      "step": 31
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9758730916235356e-05,
+      "loss": 1.253,
+      "step": 32
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.973639792672638e-05,
+      "loss": 1.4498,
+      "step": 33
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9713090317615877e-05,
+      "loss": 1.5219,
+      "step": 34
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.968881042201029e-05,
+      "loss": 1.5883,
+      "step": 35
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.966356067034256e-05,
+      "loss": 1.5119,
+      "step": 36
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.963734359012881e-05,
+      "loss": 1.5395,
+      "step": 37
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.96101618057154e-05,
+      "loss": 1.5608,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9582018038016156e-05,
+      "loss": 1.6791,
+      "step": 39
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9552915104240067e-05,
+      "loss": 1.4483,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9522855917609243e-05,
+      "loss": 1.5176,
+      "step": 41
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9491843487067305e-05,
+      "loss": 1.7341,
+      "step": 42
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.945988091697821e-05,
+      "loss": 1.7081,
+      "step": 43
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9426971406815464e-05,
+      "loss": 1.5174,
+      "step": 44
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9393118250841897e-05,
+      "loss": 1.7841,
+      "step": 45
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9358324837779864e-05,
+      "loss": 1.6924,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.932259465047206e-05,
+      "loss": 1.6845,
+      "step": 47
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9285931265532875e-05,
+      "loss": 1.5164,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.924833835299037e-05,
+      "loss": 1.4916,
+      "step": 49
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.920981967591891e-05,
+      "loss": 1.5541,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.917037909006248e-05,
+      "loss": 1.5278,
+      "step": 51
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9130020543448705e-05,
+      "loss": 1.5412,
+      "step": 52
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.908874807599368e-05,
+      "loss": 1.5861,
+      "step": 53
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9046565819097546e-05,
+      "loss": 1.4084,
+      "step": 54
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9003477995230942e-05,
+      "loss": 1.6763,
+      "step": 55
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.895948891751234e-05,
+      "loss": 1.357,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8914602989276294e-05,
+      "loss": 1.5576,
+      "step": 57
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8868824703632658e-05,
+      "loss": 1.551,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.882215864301683e-05,
+      "loss": 1.6156,
+      "step": 59
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8774609478731048e-05,
+      "loss": 1.541,
+      "step": 60
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.872618197047678e-05,
+      "loss": 1.392,
+      "step": 61
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8676880965878293e-05,
+      "loss": 1.427,
+      "step": 62
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.862671139999738e-05,
+      "loss": 1.5492,
+      "step": 63
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.857567829483937e-05,
+      "loss": 1.6885,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8523786758850436e-05,
+      "loss": 1.4042,
+      "step": 65
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.84710419864062e-05,
+      "loss": 1.5082,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8417449257291802e-05,
+      "loss": 1.58,
+      "step": 67
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8363013936173393e-05,
+      "loss": 1.465,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8307741472061097e-05,
+      "loss": 1.4981,
+      "step": 69
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8251637397763597e-05,
+      "loss": 1.6048,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8194707329334277e-05,
+      "loss": 1.5923,
+      "step": 71
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8136956965509064e-05,
+      "loss": 1.5466,
+      "step": 72
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8078392087135957e-05,
+      "loss": 1.5844,
+      "step": 73
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8019018556596402e-05,
+      "loss": 1.4136,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7958842317218413e-05,
+      "loss": 1.5178,
+      "step": 75
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7897869392681685e-05,
+      "loss": 1.3765,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7836105886414596e-05,
+      "loss": 1.8089,
+      "step": 77
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7773557980983264e-05,
+      "loss": 1.3932,
+      "step": 78
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.771023193747264e-05,
+      "loss": 1.539,
+      "step": 79
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7646134094859816e-05,
+      "loss": 1.6678,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7581270869379443e-05,
+      "loss": 1.5492,
+      "step": 81
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7515648753881495e-05,
+      "loss": 1.4473,
+      "step": 82
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7449274317181304e-05,
+      "loss": 1.5742,
+      "step": 83
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.738215420340205e-05,
+      "loss": 1.3161,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.731429513130964e-05,
+      "loss": 1.4037,
+      "step": 85
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7245703893640188e-05,
+      "loss": 1.602,
+      "step": 86
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.717638735642005e-05,
+      "loss": 1.3847,
+      "step": 87
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7106352458278524e-05,
+      "loss": 1.5577,
+      "step": 88
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7035606209753276e-05,
+      "loss": 1.4845,
+      "step": 89
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.696415569258862e-05,
+      "loss": 1.6808,
+      "step": 90
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6892008059026587e-05,
+      "loss": 1.5455,
+      "step": 91
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6819170531091018e-05,
+      "loss": 1.623,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6745650399864608e-05,
+      "loss": 1.6224,
+      "step": 93
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.667145502475907e-05,
+      "loss": 1.3582,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.659659183277847e-05,
+      "loss": 1.3149,
+      "step": 95
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6521068317775756e-05,
+      "loss": 1.6216,
+      "step": 96
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.644489203970263e-05,
+      "loss": 1.5645,
+      "step": 97
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6368070623852794e-05,
+      "loss": 1.3277,
+      "step": 98
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6290611760098655e-05,
+      "loss": 1.6269,
+      "step": 99
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6212523202121547e-05,
+      "loss": 1.4384,
+      "step": 100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6133812766635603e-05,
+      "loss": 1.4306,
+      "step": 101
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6054488332605282e-05,
+      "loss": 1.4768,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.59745578404567e-05,
+      "loss": 1.8864,
+      "step": 103
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.589402929128276e-05,
+      "loss": 1.3486,
+      "step": 104
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.581291074604226e-05,
+      "loss": 1.613,
+      "step": 105
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.573121032475297e-05,
+      "loss": 1.4764,
+      "step": 106
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.564893620567884e-05,
+      "loss": 1.358,
+      "step": 107
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5566096624511306e-05,
+      "loss": 1.4771,
+      "step": 108
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5482699873544937e-05,
+      "loss": 1.3671,
+      "step": 109
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5398754300847346e-05,
+      "loss": 1.5569,
+      "step": 110
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.531426830942354e-05,
+      "loss": 1.4741,
+      "step": 111
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5229250356374804e-05,
+      "loss": 1.6195,
+      "step": 112
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5143708952052099e-05,
+      "loss": 1.4781,
+      "step": 113
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5057652659204198e-05,
+      "loss": 1.5379,
+      "step": 114
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4971090092120544e-05,
+      "loss": 1.3646,
+      "step": 115
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4884029915768945e-05,
+      "loss": 1.4879,
+      "step": 116
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4796480844928218e-05,
+      "loss": 1.5311,
+      "step": 117
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4708451643315827e-05,
+      "loss": 1.527,
+      "step": 118
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4619951122710624e-05,
+      "loss": 1.4042,
+      "step": 119
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4530988142070802e-05,
+      "loss": 1.4992,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4441571606647089e-05,
+      "loss": 1.6264,
+      "step": 121
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4351710467091337e-05,
+      "loss": 1.6355,
+      "step": 122
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4261413718560549e-05,
+      "loss": 1.5735,
+      "step": 123
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4170690399816469e-05,
+      "loss": 1.5545,
+      "step": 124
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4079549592320782e-05,
+      "loss": 1.3931,
+      "step": 125
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3988000419326073e-05,
+      "loss": 1.5475,
+      "step": 126
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3896052044962558e-05,
+      "loss": 1.4149,
+      "step": 127
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3803713673320773e-05,
+      "loss": 1.7302,
+      "step": 128
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3710994547530225e-05,
+      "loss": 1.5059,
+      "step": 129
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3617903948834155e-05,
+      "loss": 1.5142,
+      "step": 130
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3524451195660472e-05,
+      "loss": 1.6166,
+      "step": 131
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.343064564268899e-05,
+      "loss": 1.4794,
+      "step": 132
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3336496679914982e-05,
+      "loss": 1.3817,
+      "step": 133
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.324201373170929e-05,
+      "loss": 1.448,
+      "step": 134
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3147206255874886e-05,
+      "loss": 1.5142,
+      "step": 135
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3052083742700172e-05,
+      "loss": 1.4328,
+      "step": 136
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2956655714008992e-05,
+      "loss": 1.3995,
+      "step": 137
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.286093172220748e-05,
+      "loss": 1.5674,
+      "step": 138
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2764921349327864e-05,
+      "loss": 1.4618,
+      "step": 139
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2668634206069305e-05,
+      "loss": 1.5822,
+      "step": 140
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.257207993083585e-05,
+      "loss": 1.5195,
+      "step": 141
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2475268188771628e-05,
+      "loss": 1.391,
+      "step": 142
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2378208670793361e-05,
+      "loss": 1.302,
+      "step": 143
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2280911092620298e-05,
+      "loss": 1.4355,
+      "step": 144
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2183385193801655e-05,
+      "loss": 1.5066,
+      "step": 145
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2085640736741708e-05,
+      "loss": 1.3998,
+      "step": 146
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1987687505722532e-05,
+      "loss": 1.5438,
+      "step": 147
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1889535305924619e-05,
+      "loss": 1.4369,
+      "step": 148
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1791193962445358e-05,
+      "loss": 1.3723,
+      "step": 149
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1692673319315541e-05,
+      "loss": 1.319,
+      "step": 150
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1593983238513971e-05,
+      "loss": 1.5461,
+      "step": 151
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1495133598980263e-05,
+      "loss": 1.2542,
+      "step": 152
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1396134295625971e-05,
+      "loss": 1.5088,
+      "step": 153
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1296995238344084e-05,
+      "loss": 1.4485,
+      "step": 154
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1197726351017052e-05,
+      "loss": 1.6495,
+      "step": 155
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1098337570523397e-05,
+      "loss": 1.3967,
+      "step": 156
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0998838845743012e-05,
+      "loss": 1.3436,
+      "step": 157
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.08992401365613e-05,
+      "loss": 1.441,
+      "step": 158
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0799551412872151e-05,
+      "loss": 1.3192,
+      "step": 159
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0699782653579973e-05,
+      "loss": 1.6255,
+      "step": 160
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0599943845600781e-05,
+      "loss": 1.4091,
+      "step": 161
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0500044982862519e-05,
+      "loss": 1.3174,
+      "step": 162
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0400096065304637e-05,
+      "loss": 1.3448,
+      "step": 163
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.0300107097877114e-05,
+      "loss": 1.1215,
+      "step": 164
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0200088089538944e-05,
+      "loss": 1.3024,
+      "step": 165
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0100049052256236e-05,
+      "loss": 1.0719,
+      "step": 166
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1e-05,
+      "loss": 1.4881,
+      "step": 167
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.899950947743767e-06,
+      "loss": 1.3868,
+      "step": 168
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.799911910461059e-06,
+      "loss": 1.176,
+      "step": 169
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.699892902122887e-06,
+      "loss": 1.3391,
+      "step": 170
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.599903934695366e-06,
+      "loss": 1.2758,
+      "step": 171
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.499955017137485e-06,
+      "loss": 1.2091,
+      "step": 172
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.40005615439922e-06,
+      "loss": 1.7195,
+      "step": 173
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.300217346420029e-06,
+      "loss": 1.2776,
+      "step": 174
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.200448587127852e-06,
+      "loss": 1.5049,
+      "step": 175
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.100759863438702e-06,
+      "loss": 1.3742,
+      "step": 176
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.00116115425699e-06,
+      "loss": 1.3311,
+      "step": 177
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.901662429476607e-06,
+      "loss": 1.2521,
+      "step": 178
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.802273648982951e-06,
+      "loss": 1.201,
+      "step": 179
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.703004761655918e-06,
+      "loss": 1.221,
+      "step": 180
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.603865704374032e-06,
+      "loss": 1.1296,
+      "step": 181
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.504866401019738e-06,
+      "loss": 1.2867,
+      "step": 182
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.406016761486034e-06,
+      "loss": 1.2172,
+      "step": 183
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.30732668068446e-06,
+      "loss": 1.3546,
+      "step": 184
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.208806037554645e-06,
+      "loss": 1.3152,
+      "step": 185
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.110464694075383e-06,
+      "loss": 1.2396,
+      "step": 186
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.012312494277473e-06,
+      "loss": 1.2363,
+      "step": 187
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.914359263258295e-06,
+      "loss": 1.269,
+      "step": 188
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.816614806198347e-06,
+      "loss": 1.117,
+      "step": 189
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.719088907379705e-06,
+      "loss": 1.052,
+      "step": 190
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.621791329206643e-06,
+      "loss": 1.1074,
+      "step": 191
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.524731811228374e-06,
+      "loss": 1.1173,
+      "step": 192
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.427920069164154e-06,
+      "loss": 1.4199,
+      "step": 193
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.331365793930698e-06,
+      "loss": 1.1899,
+      "step": 194
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.235078650672141e-06,
+      "loss": 1.1529,
+      "step": 195
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.139068277792524e-06,
+      "loss": 1.0999,
+      "step": 196
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.043344285991012e-06,
+      "loss": 1.173,
+      "step": 197
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.947916257299829e-06,
+      "loss": 1.0733,
+      "step": 198
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.8527937441251195e-06,
+      "loss": 1.1061,
+      "step": 199
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.757986268290713e-06,
+      "loss": 1.458,
+      "step": 200
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.663503320085021e-06,
+      "loss": 1.8228,
+      "step": 201
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.569354357311015e-06,
+      "loss": 1.207,
+      "step": 202
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.475548804339529e-06,
+      "loss": 1.2792,
+      "step": 203
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.382096051165847e-06,
+      "loss": 1.1533,
+      "step": 204
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.289005452469778e-06,
+      "loss": 1.0791,
+      "step": 205
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.196286326679231e-06,
+      "loss": 1.266,
+      "step": 206
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.103947955037447e-06,
+      "loss": 1.1793,
+      "step": 207
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.0119995806739316e-06,
+      "loss": 1.2426,
+      "step": 208
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.920450407679219e-06,
+      "loss": 1.2104,
+      "step": 209
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5.829309600183536e-06,
+      "loss": 1.162,
+      "step": 210
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.738586281439455e-06,
+      "loss": 1.2641,
+      "step": 211
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.648289532908666e-06,
+      "loss": 1.7289,
+      "step": 212
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.558428393352914e-06,
+      "loss": 1.1043,
+      "step": 213
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.469011857929202e-06,
+      "loss": 1.1279,
+      "step": 214
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.380048877289381e-06,
+      "loss": 0.9973,
+      "step": 215
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.291548356684177e-06,
+      "loss": 2.1676,
+      "step": 216
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.2035191550717856e-06,
+      "loss": 1.3953,
+      "step": 217
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.115970084231059e-06,
+      "loss": 1.2132,
+      "step": 218
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.028909907879462e-06,
+      "loss": 1.1612,
+      "step": 219
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.942347340795803e-06,
+      "loss": 1.3607,
+      "step": 220
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.856291047947904e-06,
+      "loss": 1.3732,
+      "step": 221
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.7707496436252e-06,
+      "loss": 1.6733,
+      "step": 222
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.685731690576464e-06,
+      "loss": 1.2424,
+      "step": 223
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.601245699152659e-06,
+      "loss": 1.299,
+      "step": 224
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.5173001264550665e-06,
+      "loss": 1.3776,
+      "step": 225
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.4339033754886974e-06,
+      "loss": 1.1441,
+      "step": 226
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.3510637943211656e-06,
+      "loss": 1.4207,
+      "step": 227
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.268789675247029e-06,
+      "loss": 1.4656,
+      "step": 228
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.1870892539577435e-06,
+      "loss": 1.3888,
+      "step": 229
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.105970708717244e-06,
+      "loss": 1.3829,
+      "step": 230
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.0254421595433045e-06,
+      "loss": 1.2,
+      "step": 231
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.945511667394719e-06,
+      "loss": 1.2289,
+      "step": 232
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.866187233364402e-06,
+      "loss": 1.1711,
+      "step": 233
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.787476797878459e-06,
+      "loss": 1.5137,
+      "step": 234
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.7093882399013504e-06,
+      "loss": 1.1758,
+      "step": 235
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.6319293761472073e-06,
+      "loss": 1.1653,
+      "step": 236
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.5551079602973735e-06,
+      "loss": 1.404,
+      "step": 237
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.47893168222425e-06,
+      "loss": 1.0932,
+      "step": 238
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.403408167221536e-06,
+      "loss": 1.321,
+      "step": 239
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.3285449752409315e-06,
+      "loss": 1.1774,
+      "step": 240
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.2543496001353968e-06,
+      "loss": 1.166,
+      "step": 241
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.1808294689089856e-06,
+      "loss": 1.239,
+      "step": 242
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.107991940973417e-06,
+      "loss": 1.3065,
+      "step": 243
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.035844307411384e-06,
+      "loss": 1.1926,
+      "step": 244
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.964393790246728e-06,
+      "loss": 1.3487,
+      "step": 245
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.8936475417214795e-06,
+      "loss": 1.1353,
+      "step": 246
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.8236126435799492e-06,
+      "loss": 1.0904,
+      "step": 247
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.754296106359811e-06,
+      "loss": 1.2677,
+      "step": 248
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.6857048686903618e-06,
+      "loss": 1.2408,
+      "step": 249
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.6178457965979543e-06,
+      "loss": 1.4542,
+      "step": 250
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.5507256828186978e-06,
+      "loss": 1.2505,
+      "step": 251
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.484351246118507e-06,
+      "loss": 1.4077,
+      "step": 252
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.4187291306205573e-06,
+      "loss": 1.1162,
+      "step": 253
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.353865905140187e-06,
+      "loss": 1.3291,
+      "step": 254
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.2897680625273623e-06,
+      "loss": 1.1045,
+      "step": 255
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.226442019016739e-06,
+      "loss": 1.1402,
+      "step": 256
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.1638941135854042e-06,
+      "loss": 1.1621,
+      "step": 257
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.1021306073183166e-06,
+      "loss": 1.2284,
+      "step": 258
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.0411576827815904e-06,
+      "loss": 1.0387,
+      "step": 259
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.9809814434036e-06,
+      "loss": 1.1022,
+      "step": 260
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.921607912864042e-06,
+      "loss": 1.2595,
+      "step": 261
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8630430344909378e-06,
+      "loss": 1.1431,
+      "step": 262
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8052926706657226e-06,
+      "loss": 1.2936,
+      "step": 263
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.748362602236403e-06,
+      "loss": 1.4389,
+      "step": 264
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.6922585279389037e-06,
+      "loss": 1.0685,
+      "step": 265
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.63698606382661e-06,
+      "loss": 1.0782,
+      "step": 266
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.5825507427081976e-06,
+      "loss": 1.0724,
+      "step": 267
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.528958013593801e-06,
+      "loss": 0.98,
+      "step": 268
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4762132411495644e-06,
+      "loss": 1.1179,
+      "step": 269
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4243217051606285e-06,
+      "loss": 1.1229,
+      "step": 270
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3732886000026235e-06,
+      "loss": 1.2608,
+      "step": 271
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.3231190341217081e-06,
+      "loss": 1.1365,
+      "step": 272
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.2738180295232206e-06,
+      "loss": 1.7409,
+      "step": 273
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.2253905212689554e-06,
+      "loss": 1.1186,
+      "step": 274
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1778413569831726e-06,
+      "loss": 1.121,
+      "step": 275
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1311752963673438e-06,
+      "loss": 1.1812,
+      "step": 276
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.085397010723709e-06,
+      "loss": 1.3303,
+      "step": 277
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0405110824876619e-06,
+      "loss": 1.1579,
+      "step": 278
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.965220047690626e-07,
+      "loss": 1.4992,
+      "step": 279
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.534341809024583e-07,
+      "loss": 2.0781,
+      "step": 280
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.112519240063234e-07,
+      "loss": 1.1184,
+      "step": 281
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.699794565512976e-07,
+      "loss": 1.1405,
+      "step": 282
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.296209099375252e-07,
+      "loss": 1.1669,
+      "step": 283
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.901803240810901e-07,
+      "loss": 1.362,
+      "step": 284
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.516616470096317e-07,
+      "loss": 1.2286,
+      "step": 285
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.140687344671282e-07,
+      "loss": 1.0405,
+      "step": 286
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.77405349527942e-07,
+      "loss": 1.2192,
+      "step": 287
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 6.416751622201389e-07,
+      "loss": 1.4261,
+      "step": 288
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.068817491581069e-07,
+      "loss": 1.1794,
+      "step": 289
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5.730285931845381e-07,
+      "loss": 1.2879,
+      "step": 290
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.40119083021794e-07,
+      "loss": 1.0215,
+      "step": 291
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.08156512932696e-07,
+      "loss": 1.1408,
+      "step": 292
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.771440823907603e-07,
+      "loss": 1.4883,
+      "step": 293
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.4708489575993496e-07,
+      "loss": 1.0723,
+      "step": 294
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.1798196198384545e-07,
+      "loss": 1.5278,
+      "step": 295
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.8983819428460414e-07,
+      "loss": 1.4491,
+      "step": 296
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.626564098711904e-07,
+      "loss": 1.2908,
+      "step": 297
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.364393296574453e-07,
+      "loss": 1.2405,
+      "step": 298
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.1118957798970895e-07,
+      "loss": 1.2314,
+      "step": 299
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.8690968238412444e-07,
+      "loss": 1.2061,
+      "step": 300
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.636020732736233e-07,
+      "loss": 1.7261,
+      "step": 301
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.41269083764647e-07,
+      "loss": 1.154,
+      "step": 302
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.1991294940359343e-07,
+      "loss": 1.1905,
+      "step": 303
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9953580795304628e-07,
+      "loss": 1.3603,
+      "step": 304
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8013969917777484e-07,
+      "loss": 1.2766,
+      "step": 305
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.6172656464055748e-07,
+      "loss": 1.0368,
+      "step": 306
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.4429824750782583e-07,
+      "loss": 1.2633,
+      "step": 307
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.278564923651704e-07,
+      "loss": 1.6303,
+      "step": 308
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.1240294504269777e-07,
+      "loss": 1.2937,
+      "step": 309
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.793915245028595e-08,
+      "loss": 1.7401,
+      "step": 310
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.446656242273699e-08,
+      "loss": 1.1894,
+      "step": 311
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.19865235748507e-08,
+      "loss": 1.1576,
+      "step": 312
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.05002851664227e-08,
+      "loss": 1.0123,
+      "step": 313
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.000899697719552e-08,
+      "loss": 1.2243,
+      "step": 314
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.05137091917629e-08,
+      "loss": 1.1567,
+      "step": 315
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.201537229445051e-08,
+      "loss": 1.0936,
+      "step": 316
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.4514836974165458e-08,
+      "loss": 1.2039,
+      "step": 317
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.8012854039244354e-08,
+      "loss": 1.2848,
+      "step": 318
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.2510074342301225e-08,
+      "loss": 2.3523,
+      "step": 319
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.007048715068522e-09,
+      "loss": 1.1037,
+      "step": 320
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.504227913265658e-09,
+      "loss": 1.09,
+      "step": 321
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.0019625714740032e-09,
+      "loss": 1.1748,
+      "step": 322
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.005031680394012e-10,
+      "loss": 0.9517,
+      "step": 323
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0,
+      "loss": 1.4235,
+      "step": 324
+    },
+    {
+      "epoch": 1.99,
+      "step": 324,
+      "total_flos": 4.296843871230362e+16,
+      "train_loss": 1.4149539908509197,
+      "train_runtime": 5540.1348,
+      "train_samples_per_second": 1.877,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "max_steps": 324,
+  "num_train_epochs": 2,
+  "total_flos": 4.296843871230362e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdba535830e0a53dbef31e91bb5fa94ce438be0ae901486d08c11e16cf6253ad
+size 3835