Upload folder using huggingface_hub

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- simonycl/Meta-Llama-3-8B-Instruct-metamath-rm-annotate
+model-index:
+- name: llama-3-8b-instruct-metamath-armorm
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-3-8b-instruct-metamath-armorm
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the simonycl/Meta-Llama-3-8B-Instruct-metamath-rm-annotate dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1754
+- Rewards/chosen: -4.0084
+- Rewards/rejected: -10.7133
+- Rewards/accuracies: 0.9260
+- Rewards/margins: 6.7050
+- Logps/rejected: -1190.5024
+- Logps/chosen: -493.8166
+- Logits/rejected: -0.1943
+- Logits/chosen: -0.5449
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.1771        | 0.7881 | 400  | 0.1754          | -4.0084        | -10.7133         | 0.9260             | 6.7050          | -1190.5024     | -493.8166    | -0.1943         | -0.5449       |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9989532664244812,
+    "eval_logits/chosen": -0.559479296207428,
+    "eval_logits/rejected": -0.2016037255525589,
+    "eval_logps/chosen": -501.3774108886719,
+    "eval_logps/rejected": -1203.66748046875,
+    "eval_loss": 0.17328061163425446,
+    "eval_rewards/accuracies": 0.9259999990463257,
+    "eval_rewards/chosen": -4.0839948654174805,
+    "eval_rewards/margins": 6.760995388031006,
+    "eval_rewards/rejected": -10.844988822937012,
+    "eval_runtime": 209.9991,
+    "eval_samples": 1999,
+    "eval_samples_per_second": 9.519,
+    "eval_steps_per_second": 1.19,
+    "total_flos": 0.0,
+    "train_loss": 0.2931108748654172,
+    "train_runtime": 25855.3563,
+    "train_samples": 64961,
+    "train_samples_per_second": 2.512,
+    "train_steps_per_second": 0.02
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9989532664244812,
+    "eval_logits/chosen": -0.559479296207428,
+    "eval_logits/rejected": -0.2016037255525589,
+    "eval_logps/chosen": -501.3774108886719,
+    "eval_logps/rejected": -1203.66748046875,
+    "eval_loss": 0.17328061163425446,
+    "eval_rewards/accuracies": 0.9259999990463257,
+    "eval_rewards/chosen": -4.0839948654174805,
+    "eval_rewards/margins": 6.760995388031006,
+    "eval_rewards/rejected": -10.844988822937012,
+    "eval_runtime": 209.9991,
+    "eval_samples": 1999,
+    "eval_samples_per_second": 9.519,
+    "eval_steps_per_second": 1.19
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec3dd693231bdef1f7aab4f692c35342a8c932853b40c7089b26aeb16d7066c
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eddd366bdb656aa45b6e0356b23dbacaa6949df8d9e57705721116752ae7ec1
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca1e5938d96e9f83b589c0991c3fc9cfbd2d1a1be466242a9ae386f6dea09e2
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab25b134c3af48dc65254f1d9839a51de3732734e6c3dc101b79b4257237a38
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9989532664244812,
+    "total_flos": 0.0,
+    "train_loss": 0.2931108748654172,
+    "train_runtime": 25855.3563,
+    "train_samples": 64961,
+    "train_samples_per_second": 2.512,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,1588 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9989532664244812,
+  "eval_steps": 400,
+  "global_step": 507,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00197032202450588,
+      "grad_norm": 3.5716759707287533,
+      "learning_rate": 9.803921568627451e-09,
+      "logits/chosen": -0.3212517201900482,
+      "logits/rejected": -0.038288265466690063,
+      "logps/chosen": -83.59561920166016,
+      "logps/rejected": -104.97456359863281,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0098516101225294,
+      "grad_norm": 3.762089232305721,
+      "learning_rate": 4.901960784313725e-08,
+      "logits/chosen": -0.32774022221565247,
+      "logits/rejected": -0.058511316776275635,
+      "logps/chosen": -94.72791290283203,
+      "logps/rejected": -115.28005981445312,
+      "loss": 0.6933,
+      "rewards/accuracies": 0.3984375,
+      "rewards/chosen": 0.0006928616785444319,
+      "rewards/margins": 0.00022075558081269264,
+      "rewards/rejected": 0.00047210603952407837,
+      "step": 5
+    },
+    {
+      "epoch": 0.0197032202450588,
+      "grad_norm": 3.861972304946439,
+      "learning_rate": 9.80392156862745e-08,
+      "logits/chosen": -0.4017206132411957,
+      "logits/rejected": -0.05145833641290665,
+      "logps/chosen": -88.12547302246094,
+      "logps/rejected": -117.3188705444336,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.00022920728952158242,
+      "rewards/margins": 0.0002208867372246459,
+      "rewards/rejected": 8.32052046462195e-06,
+      "step": 10
+    },
+    {
+      "epoch": 0.029554830367588204,
+      "grad_norm": 3.4321533097840518,
+      "learning_rate": 1.4705882352941175e-07,
+      "logits/chosen": -0.39205312728881836,
+      "logits/rejected": -0.07538292557001114,
+      "logps/chosen": -91.50929260253906,
+      "logps/rejected": -115.07341003417969,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.00023484870325773954,
+      "rewards/margins": 0.00033765833359211683,
+      "rewards/rejected": -0.0005725071532651782,
+      "step": 15
+    },
+    {
+      "epoch": 0.0394064404901176,
+      "grad_norm": 3.9607360848968187,
+      "learning_rate": 1.96078431372549e-07,
+      "logits/chosen": -0.4966781735420227,
+      "logits/rejected": -0.055919598788022995,
+      "logps/chosen": -89.81816864013672,
+      "logps/rejected": -127.3244857788086,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.0005681807524524629,
+      "rewards/margins": 0.0009713674080558121,
+      "rewards/rejected": -0.001539548160508275,
+      "step": 20
+    },
+    {
+      "epoch": 0.04925805061264701,
+      "grad_norm": 3.5296437552816307,
+      "learning_rate": 2.4509803921568627e-07,
+      "logits/chosen": -0.3703702688217163,
+      "logits/rejected": -0.04695729538798332,
+      "logps/chosen": -89.12193298339844,
+      "logps/rejected": -114.06550598144531,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -0.0009911435190588236,
+      "rewards/margins": 0.0011183301685377955,
+      "rewards/rejected": -0.0021094740368425846,
+      "step": 25
+    },
+    {
+      "epoch": 0.05910966073517641,
+      "grad_norm": 3.853261672366896,
+      "learning_rate": 2.941176470588235e-07,
+      "logits/chosen": -0.4061547815799713,
+      "logits/rejected": -0.022843435406684875,
+      "logps/chosen": -88.47209930419922,
+      "logps/rejected": -119.05744934082031,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.003369951155036688,
+      "rewards/margins": 0.003699511755257845,
+      "rewards/rejected": -0.0070694624446332455,
+      "step": 30
+    },
+    {
+      "epoch": 0.0689612708577058,
+      "grad_norm": 3.3150761566132947,
+      "learning_rate": 3.431372549019608e-07,
+      "logits/chosen": -0.45706015825271606,
+      "logits/rejected": -0.00249934452585876,
+      "logps/chosen": -85.24281311035156,
+      "logps/rejected": -114.63134765625,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.004671358037739992,
+      "rewards/margins": 0.006625416222959757,
+      "rewards/rejected": -0.011296774260699749,
+      "step": 35
+    },
+    {
+      "epoch": 0.0788128809802352,
+      "grad_norm": 3.66028976226441,
+      "learning_rate": 3.92156862745098e-07,
+      "logits/chosen": -0.3261186182498932,
+      "logits/rejected": -0.042820725589990616,
+      "logps/chosen": -92.31107330322266,
+      "logps/rejected": -119.44239807128906,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.011948658153414726,
+      "rewards/margins": 0.011541644111275673,
+      "rewards/rejected": -0.02349030040204525,
+      "step": 40
+    },
+    {
+      "epoch": 0.08866449110276461,
+      "grad_norm": 3.63969403932034,
+      "learning_rate": 4.4117647058823526e-07,
+      "logits/chosen": -0.2984916567802429,
+      "logits/rejected": -0.02350195124745369,
+      "logps/chosen": -92.2959213256836,
+      "logps/rejected": -115.9202880859375,
+      "loss": 0.6836,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.019472572952508926,
+      "rewards/margins": 0.02039313316345215,
+      "rewards/rejected": -0.039865706115961075,
+      "step": 45
+    },
+    {
+      "epoch": 0.09851610122529401,
+      "grad_norm": 4.3604990095665945,
+      "learning_rate": 4.901960784313725e-07,
+      "logits/chosen": -0.38818296790122986,
+      "logits/rejected": 0.04775471240282059,
+      "logps/chosen": -97.75857543945312,
+      "logps/rejected": -131.0858154296875,
+      "loss": 0.6743,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.04315173625946045,
+      "rewards/margins": 0.04073283448815346,
+      "rewards/rejected": -0.0838845744729042,
+      "step": 50
+    },
+    {
+      "epoch": 0.10836771134782341,
+      "grad_norm": 4.880994433768252,
+      "learning_rate": 4.999050767562379e-07,
+      "logits/chosen": -0.2254917174577713,
+      "logits/rejected": 0.084599569439888,
+      "logps/chosen": -96.35099029541016,
+      "logps/rejected": -127.17691802978516,
+      "loss": 0.6614,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.0744641050696373,
+      "rewards/margins": 0.0766611099243164,
+      "rewards/rejected": -0.1511252075433731,
+      "step": 55
+    },
+    {
+      "epoch": 0.11821932147035281,
+      "grad_norm": 4.281283362848375,
+      "learning_rate": 4.99519574616467e-07,
+      "logits/chosen": -0.21917180716991425,
+      "logits/rejected": 0.08296950161457062,
+      "logps/chosen": -107.1852798461914,
+      "logps/rejected": -146.62796020507812,
+      "loss": 0.6427,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.1631706953048706,
+      "rewards/margins": 0.10459752380847931,
+      "rewards/rejected": -0.2677682042121887,
+      "step": 60
+    },
+    {
+      "epoch": 0.12807093159288221,
+      "grad_norm": 5.071139920620645,
+      "learning_rate": 4.988380179235842e-07,
+      "logits/chosen": -0.17159122228622437,
+      "logits/rejected": 0.16882023215293884,
+      "logps/chosen": -118.68798828125,
+      "logps/rejected": -170.29942321777344,
+      "loss": 0.6032,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.3113929331302643,
+      "rewards/margins": 0.2638421654701233,
+      "rewards/rejected": -0.57523512840271,
+      "step": 65
+    },
+    {
+      "epoch": 0.1379225417154116,
+      "grad_norm": 4.727207802562835,
+      "learning_rate": 4.978612153434526e-07,
+      "logits/chosen": -0.0856039747595787,
+      "logits/rejected": 0.19887478649616241,
+      "logps/chosen": -144.53707885742188,
+      "logps/rejected": -214.57565307617188,
+      "loss": 0.5613,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.530223548412323,
+      "rewards/margins": 0.47255739569664,
+      "rewards/rejected": -1.0027809143066406,
+      "step": 70
+    },
+    {
+      "epoch": 0.14777415183794101,
+      "grad_norm": 7.292282133804881,
+      "learning_rate": 4.965903258506806e-07,
+      "logits/chosen": 0.06728411465883255,
+      "logits/rejected": 0.23301705718040466,
+      "logps/chosen": -173.416748046875,
+      "logps/rejected": -265.91815185546875,
+      "loss": 0.5379,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.8527249097824097,
+      "rewards/margins": 0.6946634650230408,
+      "rewards/rejected": -1.5473883152008057,
+      "step": 75
+    },
+    {
+      "epoch": 0.1576257619604704,
+      "grad_norm": 13.282813528426324,
+      "learning_rate": 4.950268573535011e-07,
+      "logits/chosen": 0.0896778553724289,
+      "logits/rejected": 0.3949694037437439,
+      "logps/chosen": -230.47958374023438,
+      "logps/rejected": -472.5071716308594,
+      "loss": 0.4786,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -1.3847647905349731,
+      "rewards/margins": 2.162508487701416,
+      "rewards/rejected": -3.5472731590270996,
+      "step": 80
+    },
+    {
+      "epoch": 0.16747737208299981,
+      "grad_norm": 12.018078193553391,
+      "learning_rate": 4.93172664904641e-07,
+      "logits/chosen": 0.1456315815448761,
+      "logits/rejected": 0.4849046766757965,
+      "logps/chosen": -349.7117614746094,
+      "logps/rejected": -681.907958984375,
+      "loss": 0.5192,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -2.60054087638855,
+      "rewards/margins": 3.0727696418762207,
+      "rewards/rejected": -5.67331075668335,
+      "step": 85
+    },
+    {
+      "epoch": 0.17732898220552923,
+      "grad_norm": 28.167955774457234,
+      "learning_rate": 4.910299485003033e-07,
+      "logits/chosen": 0.02276581898331642,
+      "logits/rejected": 0.4464835524559021,
+      "logps/chosen": -345.51544189453125,
+      "logps/rejected": -743.3292236328125,
+      "loss": 0.5113,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -2.5319464206695557,
+      "rewards/margins": 3.730536937713623,
+      "rewards/rejected": -6.262484073638916,
+      "step": 90
+    },
+    {
+      "epoch": 0.18718059232805861,
+      "grad_norm": 12.139689938268164,
+      "learning_rate": 4.886012504698769e-07,
+      "logits/chosen": -0.002933202777057886,
+      "logits/rejected": 0.43008264899253845,
+      "logps/chosen": -302.9911193847656,
+      "logps/rejected": -684.910888671875,
+      "loss": 0.472,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -2.1746010780334473,
+      "rewards/margins": 3.5995872020721436,
+      "rewards/rejected": -5.774188041687012,
+      "step": 95
+    },
+    {
+      "epoch": 0.19703220245058803,
+      "grad_norm": 12.5544948664378,
+      "learning_rate": 4.858894524594652e-07,
+      "logits/chosen": 0.022834068164229393,
+      "logits/rejected": 0.3701624274253845,
+      "logps/chosen": -289.3520202636719,
+      "logps/rejected": -683.6341552734375,
+      "loss": 0.3991,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -2.0074386596679688,
+      "rewards/margins": 3.6894798278808594,
+      "rewards/rejected": -5.696918964385986,
+      "step": 100
+    },
+    {
+      "epoch": 0.20688381257311741,
+      "grad_norm": 15.065960090058564,
+      "learning_rate": 4.828977720128198e-07,
+      "logits/chosen": 0.0002507031022105366,
+      "logits/rejected": 0.37204107642173767,
+      "logps/chosen": -334.42730712890625,
+      "logps/rejected": -634.4157104492188,
+      "loss": 0.3437,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -2.488405704498291,
+      "rewards/margins": 2.7599520683288574,
+      "rewards/rejected": -5.24835729598999,
+      "step": 105
+    },
+    {
+      "epoch": 0.21673542269564683,
+      "grad_norm": 16.261338022859512,
+      "learning_rate": 4.796297587537285e-07,
+      "logits/chosen": 0.06315435469150543,
+      "logits/rejected": 0.31432074308395386,
+      "logps/chosen": -361.6005859375,
+      "logps/rejected": -765.8851318359375,
+      "loss": 0.3691,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -2.765998363494873,
+      "rewards/margins": 3.7075164318084717,
+      "rewards/rejected": -6.473515510559082,
+      "step": 110
+    },
+    {
+      "epoch": 0.22658703281817621,
+      "grad_norm": 25.84992444184961,
+      "learning_rate": 4.760892901743944e-07,
+      "logits/chosen": -0.04955141246318817,
+      "logits/rejected": 0.3938520848751068,
+      "logps/chosen": -383.02587890625,
+      "logps/rejected": -1007.9422607421875,
+      "loss": 0.3686,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -2.9116337299346924,
+      "rewards/margins": 5.993666648864746,
+      "rewards/rejected": -8.905302047729492,
+      "step": 115
+    },
+    {
+      "epoch": 0.23643864294070563,
+      "grad_norm": 14.695045524114075,
+      "learning_rate": 4.7228056703479626e-07,
+      "logits/chosen": -0.0156477652490139,
+      "logits/rejected": 0.3278658390045166,
+      "logps/chosen": -313.21759033203125,
+      "logps/rejected": -813.0584716796875,
+      "loss": 0.3258,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -2.286334276199341,
+      "rewards/margins": 4.711178779602051,
+      "rewards/rejected": -6.997513771057129,
+      "step": 120
+    },
+    {
+      "epoch": 0.24629025306323502,
+      "grad_norm": 17.553441070067215,
+      "learning_rate": 4.6820810837849535e-07,
+      "logits/chosen": -0.03341873735189438,
+      "logits/rejected": 0.29112133383750916,
+      "logps/chosen": -298.9117736816406,
+      "logps/rejected": -690.4375610351562,
+      "loss": 0.3097,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -2.0853493213653564,
+      "rewards/margins": 3.7220027446746826,
+      "rewards/rejected": -5.807352542877197,
+      "step": 125
+    },
+    {
+      "epoch": 0.25614186318576443,
+      "grad_norm": 17.93982359731177,
+      "learning_rate": 4.63876746170797e-07,
+      "logits/chosen": -0.07315142452716827,
+      "logits/rejected": 0.3109583854675293,
+      "logps/chosen": -350.6395568847656,
+      "logps/rejected": -922.5460205078125,
+      "loss": 0.346,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -2.5479183197021484,
+      "rewards/margins": 5.4567155838012695,
+      "rewards/rejected": -8.004632949829102,
+      "step": 130
+    },
+    {
+      "epoch": 0.2659934733082938,
+      "grad_norm": 18.77430630377733,
+      "learning_rate": 4.592916195656321e-07,
+      "logits/chosen": -0.005010261200368404,
+      "logits/rejected": 0.3036307990550995,
+      "logps/chosen": -343.17071533203125,
+      "logps/rejected": -685.6228637695312,
+      "loss": 0.3096,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -2.525252103805542,
+      "rewards/margins": 3.2307941913604736,
+      "rewards/rejected": -5.756046295166016,
+      "step": 135
+    },
+    {
+      "epoch": 0.2758450834308232,
+      "grad_norm": 20.040463444379917,
+      "learning_rate": 4.544581688079602e-07,
+      "logits/chosen": -0.10011976957321167,
+      "logits/rejected": 0.3146817684173584,
+      "logps/chosen": -363.49627685546875,
+      "logps/rejected": -862.2647705078125,
+      "loss": 0.2748,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -2.7324507236480713,
+      "rewards/margins": 4.728878974914551,
+      "rewards/rejected": -7.461329460144043,
+      "step": 140
+    },
+    {
+      "epoch": 0.28569669355335264,
+      "grad_norm": 15.733141257855737,
+      "learning_rate": 4.493821287789272e-07,
+      "logits/chosen": -0.01995091699063778,
+      "logits/rejected": 0.2867122292518616,
+      "logps/chosen": -357.0852966308594,
+      "logps/rejected": -750.5655517578125,
+      "loss": 0.2801,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -2.5995800495147705,
+      "rewards/margins": 3.7247650623321533,
+      "rewards/rejected": -6.324345111846924,
+      "step": 145
+    },
+    {
+      "epoch": 0.29554830367588203,
+      "grad_norm": 18.06468660298154,
+      "learning_rate": 4.4406952219143934e-07,
+      "logits/chosen": -0.09586485475301743,
+      "logits/rejected": 0.3208523690700531,
+      "logps/chosen": -382.44842529296875,
+      "logps/rejected": -1018.31298828125,
+      "loss": 0.2467,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -2.9517743587493896,
+      "rewards/margins": 6.108856201171875,
+      "rewards/rejected": -9.060629844665527,
+      "step": 150
+    },
+    {
+      "epoch": 0.3053999137984114,
+      "grad_norm": 28.388834396460805,
+      "learning_rate": 4.38526652444224e-07,
+      "logits/chosen": 0.039218030869960785,
+      "logits/rejected": 0.344778835773468,
+      "logps/chosen": -406.8693542480469,
+      "logps/rejected": -999.7625732421875,
+      "loss": 0.2433,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -3.1535558700561523,
+      "rewards/margins": 5.727279186248779,
+      "rewards/rejected": -8.880834579467773,
+      "step": 155
+    },
+    {
+      "epoch": 0.3152515239209408,
+      "grad_norm": 31.660596706563638,
+      "learning_rate": 4.3276009614285824e-07,
+      "logits/chosen": -0.011146520264446735,
+      "logits/rejected": 0.3051149845123291,
+      "logps/chosen": -429.87841796875,
+      "logps/rejected": -1080.335205078125,
+      "loss": 0.3018,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -3.3935635089874268,
+      "rewards/margins": 6.264310836791992,
+      "rewards/rejected": -9.657873153686523,
+      "step": 160
+    },
+    {
+      "epoch": 0.32510313404347024,
+      "grad_norm": 17.68459404217653,
+      "learning_rate": 4.2677669529663686e-07,
+      "logits/chosen": -0.13334481418132782,
+      "logits/rejected": 0.3171388804912567,
+      "logps/chosen": -376.96551513671875,
+      "logps/rejected": -1257.188720703125,
+      "loss": 0.2428,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -2.8914573192596436,
+      "rewards/margins": 8.503429412841797,
+      "rewards/rejected": -11.394886016845703,
+      "step": 165
+    },
+    {
+      "epoch": 0.33495474416599963,
+      "grad_norm": 14.689124406865364,
+      "learning_rate": 4.2058354920054043e-07,
+      "logits/chosen": -0.07960227131843567,
+      "logits/rejected": 0.3466973602771759,
+      "logps/chosen": -357.06146240234375,
+      "logps/rejected": -982.9493408203125,
+      "loss": 0.2491,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -2.670814037322998,
+      "rewards/margins": 5.986855506896973,
+      "rewards/rejected": -8.657670021057129,
+      "step": 170
+    },
+    {
+      "epoch": 0.344806354288529,
+      "grad_norm": 28.20545664329798,
+      "learning_rate": 4.141880060119336e-07,
+      "logits/chosen": -0.18827159702777863,
+      "logits/rejected": 0.38570883870124817,
+      "logps/chosen": -389.2264099121094,
+      "logps/rejected": -1181.1763916015625,
+      "loss": 0.2244,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -2.9719629287719727,
+      "rewards/margins": 7.624617099761963,
+      "rewards/rejected": -10.596578598022461,
+      "step": 175
+    },
+    {
+      "epoch": 0.35465796441105846,
+      "grad_norm": 12.08456783460445,
+      "learning_rate": 4.0759765403198877e-07,
+      "logits/chosen": -0.13706155121326447,
+      "logits/rejected": 0.4062003195285797,
+      "logps/chosen": -423.25146484375,
+      "logps/rejected": -1224.51416015625,
+      "loss": 0.232,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.33508038520813,
+      "rewards/margins": 7.718878269195557,
+      "rewards/rejected": -11.053958892822266,
+      "step": 180
+    },
+    {
+      "epoch": 0.36450957453358784,
+      "grad_norm": 30.49885783500924,
+      "learning_rate": 4.008203127021797e-07,
+      "logits/chosen": -0.0005989119526930153,
+      "logits/rejected": 0.3498828411102295,
+      "logps/chosen": -403.3883361816406,
+      "logps/rejected": -953.5397338867188,
+      "loss": 0.2643,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -3.1402335166931152,
+      "rewards/margins": 5.317870140075684,
+      "rewards/rejected": -8.45810317993164,
+      "step": 185
+    },
+    {
+      "epoch": 0.37436118465611723,
+      "grad_norm": 29.71964505469346,
+      "learning_rate": 3.9386402332652754e-07,
+      "logits/chosen": -0.017243508249521255,
+      "logits/rejected": 0.33652183413505554,
+      "logps/chosen": -424.7886657714844,
+      "logps/rejected": -1082.5128173828125,
+      "loss": 0.2424,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": -3.287282943725586,
+      "rewards/margins": 6.3285932540893555,
+      "rewards/rejected": -9.615876197814941,
+      "step": 190
+    },
+    {
+      "epoch": 0.3842127947786466,
+      "grad_norm": 14.536054861256341,
+      "learning_rate": 3.867370395306068e-07,
+      "logits/chosen": -0.04574277997016907,
+      "logits/rejected": 0.33085018396377563,
+      "logps/chosen": -362.3409423828125,
+      "logps/rejected": -905.4466552734375,
+      "loss": 0.211,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -2.7454867362976074,
+      "rewards/margins": 5.19486141204834,
+      "rewards/rejected": -7.940348148345947,
+      "step": 195
+    },
+    {
+      "epoch": 0.39406440490117606,
+      "grad_norm": 18.660014718976367,
+      "learning_rate": 3.794478174686328e-07,
+      "logits/chosen": -0.09074647724628448,
+      "logits/rejected": 0.32256466150283813,
+      "logps/chosen": -450.3705139160156,
+      "logps/rejected": -1143.722412109375,
+      "loss": 0.212,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -3.554090976715088,
+      "rewards/margins": 6.726245880126953,
+      "rewards/rejected": -10.280336380004883,
+      "step": 200
+    },
+    {
+      "epoch": 0.40391601502370544,
+      "grad_norm": 18.975935428919787,
+      "learning_rate": 3.720050057902495e-07,
+      "logits/chosen": -0.0799940824508667,
+      "logits/rejected": 0.3351805806159973,
+      "logps/chosen": -386.51031494140625,
+      "logps/rejected": -958.2678833007812,
+      "loss": 0.2553,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -3.005650281906128,
+      "rewards/margins": 5.4874162673950195,
+      "rewards/rejected": -8.493066787719727,
+      "step": 205
+    },
+    {
+      "epoch": 0.41376762514623483,
+      "grad_norm": 66.8663924137639,
+      "learning_rate": 3.644174353789204e-07,
+      "logits/chosen": -0.10698902606964111,
+      "logits/rejected": 0.2421867549419403,
+      "logps/chosen": -386.45953369140625,
+      "logps/rejected": -966.5511474609375,
+      "loss": 0.2761,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -2.9330146312713623,
+      "rewards/margins": 5.579468727111816,
+      "rewards/rejected": -8.512483596801758,
+      "step": 210
+    },
+    {
+      "epoch": 0.4236192352687642,
+      "grad_norm": 18.37551072443162,
+      "learning_rate": 3.566941088741009e-07,
+      "logits/chosen": -0.0763053148984909,
+      "logits/rejected": 0.21732866764068604,
+      "logps/chosen": -334.40777587890625,
+      "logps/rejected": -830.93212890625,
+      "loss": 0.2438,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -2.431523561477661,
+      "rewards/margins": 4.755476951599121,
+      "rewards/rejected": -7.187000274658203,
+      "step": 215
+    },
+    {
+      "epoch": 0.43347084539129366,
+      "grad_norm": 15.656018668494433,
+      "learning_rate": 3.488441899896217e-07,
+      "logits/chosen": -0.22899878025054932,
+      "logits/rejected": 0.2557538151741028,
+      "logps/chosen": -333.3045349121094,
+      "logps/rejected": -962.7039794921875,
+      "loss": 0.2581,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -2.4449398517608643,
+      "rewards/margins": 5.98301362991333,
+      "rewards/rejected": -8.427953720092773,
+      "step": 220
+    },
+    {
+      "epoch": 0.44332245551382304,
+      "grad_norm": 15.274925011558063,
+      "learning_rate": 3.408769926409574e-07,
+      "logits/chosen": -0.1309630423784256,
+      "logits/rejected": 0.2810899615287781,
+      "logps/chosen": -340.2420959472656,
+      "logps/rejected": -817.1022338867188,
+      "loss": 0.2229,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -2.5391077995300293,
+      "rewards/margins": 4.515716552734375,
+      "rewards/rejected": -7.0548248291015625,
+      "step": 225
+    },
+    {
+      "epoch": 0.45317406563635243,
+      "grad_norm": 24.739799889204917,
+      "learning_rate": 3.3280196989428263e-07,
+      "logits/chosen": -0.17848137021064758,
+      "logits/rejected": 0.2861637473106384,
+      "logps/chosen": -400.38006591796875,
+      "logps/rejected": -1076.140625,
+      "loss": 0.2279,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.109973907470703,
+      "rewards/margins": 6.459465026855469,
+      "rewards/rejected": -9.569437980651855,
+      "step": 230
+    },
+    {
+      "epoch": 0.4630256757588818,
+      "grad_norm": 37.480675492827054,
+      "learning_rate": 3.2462870275042367e-07,
+      "logits/chosen": -0.04912983253598213,
+      "logits/rejected": 0.3032223582267761,
+      "logps/chosen": -460.38995361328125,
+      "logps/rejected": -1109.3538818359375,
+      "loss": 0.2154,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -3.7713286876678467,
+      "rewards/margins": 6.2886857986450195,
+      "rewards/rejected": -10.060014724731445,
+      "step": 235
+    },
+    {
+      "epoch": 0.47287728588141126,
+      "grad_norm": 22.003582994400087,
+      "learning_rate": 3.1636688877701806e-07,
+      "logits/chosen": -0.06944581121206284,
+      "logits/rejected": 0.2779255509376526,
+      "logps/chosen": -457.49481201171875,
+      "logps/rejected": -1130.4078369140625,
+      "loss": 0.2481,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -3.658263683319092,
+      "rewards/margins": 6.430821418762207,
+      "rewards/rejected": -10.08908462524414,
+      "step": 240
+    },
+    {
+      "epoch": 0.48272889600394064,
+      "grad_norm": 19.971711860289336,
+      "learning_rate": 3.080263306023669e-07,
+      "logits/chosen": -0.1616104543209076,
+      "logits/rejected": 0.34573450684547424,
+      "logps/chosen": -391.7586364746094,
+      "logps/rejected": -1083.7923583984375,
+      "loss": 0.2438,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -2.9816207885742188,
+      "rewards/margins": 6.61486291885376,
+      "rewards/rejected": -9.59648323059082,
+      "step": 245
+    },
+    {
+      "epoch": 0.49258050612647003,
+      "grad_norm": 20.739989859928595,
+      "learning_rate": 2.996169242846328e-07,
+      "logits/chosen": -0.10813699662685394,
+      "logits/rejected": 0.29609256982803345,
+      "logps/chosen": -359.22247314453125,
+      "logps/rejected": -826.0725708007812,
+      "loss": 0.232,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": -2.712796688079834,
+      "rewards/margins": 4.415780544281006,
+      "rewards/rejected": -7.12857723236084,
+      "step": 250
+    },
+    {
+      "epoch": 0.5024321162489994,
+      "grad_norm": 15.885935054871503,
+      "learning_rate": 2.911486475701835e-07,
+      "logits/chosen": -0.03156828135251999,
+      "logits/rejected": 0.31399112939834595,
+      "logps/chosen": -368.3429260253906,
+      "logps/rejected": -904.3817138671875,
+      "loss": 0.2201,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -2.7986695766448975,
+      "rewards/margins": 5.113903045654297,
+      "rewards/rejected": -7.91257381439209,
+      "step": 255
+    },
+    {
+      "epoch": 0.5122837263715289,
+      "grad_norm": 13.862652448604795,
+      "learning_rate": 2.826315480550129e-07,
+      "logits/chosen": -0.1270112544298172,
+      "logits/rejected": 0.2844023108482361,
+      "logps/chosen": -455.08428955078125,
+      "logps/rejected": -1276.5277099609375,
+      "loss": 0.1856,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -3.578526020050049,
+      "rewards/margins": 7.948564052581787,
+      "rewards/rejected": -11.527090072631836,
+      "step": 260
+    },
+    {
+      "epoch": 0.5221353364940583,
+      "grad_norm": 15.467249958009038,
+      "learning_rate": 2.740757312632854e-07,
+      "logits/chosen": -0.024818364530801773,
+      "logits/rejected": 0.3055967092514038,
+      "logps/chosen": -539.1878051757812,
+      "logps/rejected": -1253.35888671875,
+      "loss": 0.1559,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -4.478360176086426,
+      "rewards/margins": 6.895930290222168,
+      "rewards/rejected": -11.374289512634277,
+      "step": 265
+    },
+    {
+      "epoch": 0.5319869466165876,
+      "grad_norm": 31.10009512513367,
+      "learning_rate": 2.654913486571487e-07,
+      "logits/chosen": -0.016552824527025223,
+      "logits/rejected": 0.2749946713447571,
+      "logps/chosen": -542.9583740234375,
+      "logps/rejected": -1228.0316162109375,
+      "loss": 0.1946,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -4.558867931365967,
+      "rewards/margins": 6.6406965255737305,
+      "rewards/rejected": -11.199563980102539,
+      "step": 270
+    },
+    {
+      "epoch": 0.5418385567391171,
+      "grad_norm": 35.608696896720524,
+      "learning_rate": 2.5688858559204053e-07,
+      "logits/chosen": -0.0217227041721344,
+      "logits/rejected": 0.26401954889297485,
+      "logps/chosen": -419.6533203125,
+      "logps/rejected": -1099.44580078125,
+      "loss": 0.2076,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.3262057304382324,
+      "rewards/margins": 6.59003210067749,
+      "rewards/rejected": -9.916236877441406,
+      "step": 275
+    },
+    {
+      "epoch": 0.5516901668616464,
+      "grad_norm": 27.832752199634818,
+      "learning_rate": 2.4827764923178246e-07,
+      "logits/chosen": -0.12257111072540283,
+      "logits/rejected": 0.29142725467681885,
+      "logps/chosen": -459.1546325683594,
+      "logps/rejected": -1211.1357421875,
+      "loss": 0.1744,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.6038970947265625,
+      "rewards/margins": 7.217177391052246,
+      "rewards/rejected": -10.821075439453125,
+      "step": 280
+    },
+    {
+      "epoch": 0.5615417769841758,
+      "grad_norm": 15.457671376745413,
+      "learning_rate": 2.3966875643779667e-07,
+      "logits/chosen": -0.11881209909915924,
+      "logits/rejected": 0.33363258838653564,
+      "logps/chosen": -386.98553466796875,
+      "logps/rejected": -1144.4805908203125,
+      "loss": 0.1671,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -3.0352859497070312,
+      "rewards/margins": 7.268472194671631,
+      "rewards/rejected": -10.30375862121582,
+      "step": 285
+    },
+    {
+      "epoch": 0.5713933871067053,
+      "grad_norm": 25.92471561688761,
+      "learning_rate": 2.3107212164681774e-07,
+      "logits/chosen": -0.03590301424264908,
+      "logits/rejected": 0.24401037395000458,
+      "logps/chosen": -421.0747985839844,
+      "logps/rejected": -1124.1943359375,
+      "loss": 0.2066,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -3.2867560386657715,
+      "rewards/margins": 6.839125156402588,
+      "rewards/rejected": -10.125880241394043,
+      "step": 290
+    },
+    {
+      "epoch": 0.5812449972292346,
+      "grad_norm": 22.04938946555595,
+      "learning_rate": 2.2249794475148019e-07,
+      "logits/chosen": -0.08926409482955933,
+      "logits/rejected": 0.25861090421676636,
+      "logps/chosen": -413.10809326171875,
+      "logps/rejected": -1079.0089111328125,
+      "loss": 0.2153,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -3.26606822013855,
+      "rewards/margins": 6.43063497543335,
+      "rewards/rejected": -9.69670295715332,
+      "step": 295
+    },
+    {
+      "epoch": 0.5910966073517641,
+      "grad_norm": 25.590982898260364,
+      "learning_rate": 2.1395639899816332e-07,
+      "logits/chosen": -0.034001048654317856,
+      "logits/rejected": 0.27375295758247375,
+      "logps/chosen": -390.47186279296875,
+      "logps/rejected": -967.5938720703125,
+      "loss": 0.2016,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -3.02689266204834,
+      "rewards/margins": 5.586910247802734,
+      "rewards/rejected": -8.613802909851074,
+      "step": 300
+    },
+    {
+      "epoch": 0.6009482174742935,
+      "grad_norm": 24.036657960370842,
+      "learning_rate": 2.0545761891645177e-07,
+      "logits/chosen": -0.12775130569934845,
+      "logits/rejected": 0.28666818141937256,
+      "logps/chosen": -412.830322265625,
+      "logps/rejected": -1101.8428955078125,
+      "loss": 0.2017,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -3.237358570098877,
+      "rewards/margins": 6.622969627380371,
+      "rewards/rejected": -9.860328674316406,
+      "step": 305
+    },
+    {
+      "epoch": 0.6107998275968228,
+      "grad_norm": 19.790299372499124,
+      "learning_rate": 1.9701168829453305e-07,
+      "logits/chosen": -0.05270761996507645,
+      "logits/rejected": 0.33277663588523865,
+      "logps/chosen": -404.56707763671875,
+      "logps/rejected": -926.7605590820312,
+      "loss": 0.212,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": -3.1537652015686035,
+      "rewards/margins": 4.968669414520264,
+      "rewards/rejected": -8.122434616088867,
+      "step": 310
+    },
+    {
+      "epoch": 0.6206514377193523,
+      "grad_norm": 17.87782246688683,
+      "learning_rate": 1.886286282148002e-07,
+      "logits/chosen": -0.11204645782709122,
+      "logits/rejected": 0.2704783082008362,
+      "logps/chosen": -403.6227111816406,
+      "logps/rejected": -1061.3836669921875,
+      "loss": 0.1927,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": -3.127580404281616,
+      "rewards/margins": 6.2875213623046875,
+      "rewards/rejected": -9.415102005004883,
+      "step": 315
+    },
+    {
+      "epoch": 0.6305030478418816,
+      "grad_norm": 27.10992399069352,
+      "learning_rate": 1.8031838516385422e-07,
+      "logits/chosen": -0.08440341055393219,
+      "logits/rejected": 0.25625738501548767,
+      "logps/chosen": -437.379638671875,
+      "logps/rejected": -1074.4217529296875,
+      "loss": 0.1688,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -3.484510898590088,
+      "rewards/margins": 6.127772331237793,
+      "rewards/rejected": -9.612283706665039,
+      "step": 320
+    },
+    {
+      "epoch": 0.640354657964411,
+      "grad_norm": 12.909401120933932,
+      "learning_rate": 1.7209081923101472e-07,
+      "logits/chosen": -0.06193607300519943,
+      "logits/rejected": 0.3263497054576874,
+      "logps/chosen": -516.2418823242188,
+      "logps/rejected": -1247.0174560546875,
+      "loss": 0.1627,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.2533674240112305,
+      "rewards/margins": 7.042716979980469,
+      "rewards/rejected": -11.2960844039917,
+      "step": 325
+    },
+    {
+      "epoch": 0.6502062680869405,
+      "grad_norm": 35.41204414570712,
+      "learning_rate": 1.639556924093404e-07,
+      "logits/chosen": -0.010410224087536335,
+      "logits/rejected": 0.3084774613380432,
+      "logps/chosen": -453.0167541503906,
+      "logps/rejected": -1185.1031494140625,
+      "loss": 0.2336,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -3.6753456592559814,
+      "rewards/margins": 7.103107452392578,
+      "rewards/rejected": -10.778453826904297,
+      "step": 330
+    },
+    {
+      "epoch": 0.6600578782094698,
+      "grad_norm": 32.29394401511057,
+      "learning_rate": 1.5592265701304114e-07,
+      "logits/chosen": -0.06133923679590225,
+      "logits/rejected": 0.30060631036758423,
+      "logps/chosen": -509.570556640625,
+      "logps/rejected": -1296.840576171875,
+      "loss": 0.2047,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -4.143233299255371,
+      "rewards/margins": 7.6532087326049805,
+      "rewards/rejected": -11.796441078186035,
+      "step": 335
+    },
+    {
+      "epoch": 0.6699094883319993,
+      "grad_norm": 19.06755608816914,
+      "learning_rate": 1.4800124422502334e-07,
+      "logits/chosen": -0.13113179802894592,
+      "logits/rejected": 0.3551362454891205,
+      "logps/chosen": -485.8580627441406,
+      "logps/rejected": -1220.618896484375,
+      "loss": 0.161,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.9135050773620605,
+      "rewards/margins": 7.040993690490723,
+      "rewards/rejected": -10.954499244689941,
+      "step": 340
+    },
+    {
+      "epoch": 0.6797610984545287,
+      "grad_norm": 17.97214825711402,
+      "learning_rate": 1.4020085278815743e-07,
+      "logits/chosen": -0.1197463870048523,
+      "logits/rejected": 0.3118087351322174,
+      "logps/chosen": -434.01708984375,
+      "logps/rejected": -1215.2064208984375,
+      "loss": 0.1725,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.464479923248291,
+      "rewards/margins": 7.495555877685547,
+      "rewards/rejected": -10.96003532409668,
+      "step": 345
+    },
+    {
+      "epoch": 0.689612708577058,
+      "grad_norm": 16.18471076432261,
+      "learning_rate": 1.3253073785368545e-07,
+      "logits/chosen": -0.07801360636949539,
+      "logits/rejected": 0.3843817710876465,
+      "logps/chosen": -473.6708068847656,
+      "logps/rejected": -1193.1351318359375,
+      "loss": 0.1581,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.8626322746276855,
+      "rewards/margins": 6.935461521148682,
+      "rewards/rejected": -10.798093795776367,
+      "step": 350
+    },
+    {
+      "epoch": 0.6994643186995875,
+      "grad_norm": 18.873589947018306,
+      "learning_rate": 1.2500000000000005e-07,
+      "logits/chosen": -0.15726527571678162,
+      "logits/rejected": 0.3174017071723938,
+      "logps/chosen": -496.1824645996094,
+      "logps/rejected": -1303.2685546875,
+      "loss": 0.2076,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -4.049750328063965,
+      "rewards/margins": 7.79373836517334,
+      "rewards/rejected": -11.843488693237305,
+      "step": 355
+    },
+    {
+      "epoch": 0.7093159288221169,
+      "grad_norm": 25.90294321402425,
+      "learning_rate": 1.1761757443482285e-07,
+      "logits/chosen": -0.18966642022132874,
+      "logits/rejected": 0.33566808700561523,
+      "logps/chosen": -508.02734375,
+      "logps/rejected": -1315.270751953125,
+      "loss": 0.1702,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -4.183346748352051,
+      "rewards/margins": 7.791243076324463,
+      "rewards/rejected": -11.974591255187988,
+      "step": 360
+    },
+    {
+      "epoch": 0.7191675389446462,
+      "grad_norm": 19.734057903142222,
+      "learning_rate": 1.1039222039359644e-07,
+      "logits/chosen": -0.016150670126080513,
+      "logits/rejected": 0.2711113393306732,
+      "logps/chosen": -483.9044494628906,
+      "logps/rejected": -1184.877685546875,
+      "loss": 0.15,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.9407734870910645,
+      "rewards/margins": 6.8055901527404785,
+      "rewards/rejected": -10.746362686157227,
+      "step": 365
+    },
+    {
+      "epoch": 0.7290191490671757,
+      "grad_norm": 17.28464556004026,
+      "learning_rate": 1.0333251074666608e-07,
+      "logits/chosen": -0.08890758454799652,
+      "logits/rejected": 0.2970595955848694,
+      "logps/chosen": -506.0663146972656,
+      "logps/rejected": -1378.41845703125,
+      "loss": 0.1539,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.186738014221191,
+      "rewards/margins": 8.530009269714355,
+      "rewards/rejected": -12.716747283935547,
+      "step": 370
+    },
+    {
+      "epoch": 0.738870759189705,
+      "grad_norm": 36.630702602073676,
+      "learning_rate": 9.644682182758304e-08,
+      "logits/chosen": -0.028377581387758255,
+      "logits/rejected": 0.33243700861930847,
+      "logps/chosen": -497.2250061035156,
+      "logps/rejected": -1084.590576171875,
+      "loss": 0.2088,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -4.141284942626953,
+      "rewards/margins": 5.657569885253906,
+      "rewards/rejected": -9.79885482788086,
+      "step": 375
+    },
+    {
+      "epoch": 0.7487223693122345,
+      "grad_norm": 19.60457855935293,
+      "learning_rate": 8.974332349459992e-08,
+      "logits/chosen": -0.12894611060619354,
+      "logits/rejected": 0.3579118549823761,
+      "logps/chosen": -531.294921875,
+      "logps/rejected": -1420.1461181640625,
+      "loss": 0.1458,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -4.368771553039551,
+      "rewards/margins": 8.61566162109375,
+      "rewards/rejected": -12.9844331741333,
+      "step": 380
+    },
+    {
+      "epoch": 0.7585739794347639,
+      "grad_norm": 29.529419355283544,
+      "learning_rate": 8.322996943714672e-08,
+      "logits/chosen": -0.06904452294111252,
+      "logits/rejected": 0.36939507722854614,
+      "logps/chosen": -562.360595703125,
+      "logps/rejected": -1273.906494140625,
+      "loss": 0.1889,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": -4.730219841003418,
+      "rewards/margins": 6.892354488372803,
+      "rewards/rejected": -11.622573852539062,
+      "step": 385
+    },
+    {
+      "epoch": 0.7684255895572932,
+      "grad_norm": 25.714176278106745,
+      "learning_rate": 7.691448773879256e-08,
+      "logits/chosen": -0.00646906066685915,
+      "logits/rejected": 0.3322560787200928,
+      "logps/chosen": -528.5617065429688,
+      "logps/rejected": -1186.562744140625,
+      "loss": 0.2079,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -4.438258171081543,
+      "rewards/margins": 6.317309379577637,
+      "rewards/rejected": -10.755566596984863,
+      "step": 390
+    },
+    {
+      "epoch": 0.7782771996798227,
+      "grad_norm": 39.35106926615935,
+      "learning_rate": 7.080437170788722e-08,
+      "logits/chosen": -0.1304526925086975,
+      "logits/rejected": 0.32332247495651245,
+      "logps/chosen": -530.2940063476562,
+      "logps/rejected": -1372.7288818359375,
+      "loss": 0.2187,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.388240337371826,
+      "rewards/margins": 8.19841480255127,
+      "rewards/rejected": -12.586654663085938,
+      "step": 395
+    },
+    {
+      "epoch": 0.7881288098023521,
+      "grad_norm": 21.011298300829583,
+      "learning_rate": 6.490687098676332e-08,
+      "logits/chosen": -0.08302779495716095,
+      "logits/rejected": 0.3107134699821472,
+      "logps/chosen": -521.3302001953125,
+      "logps/rejected": -1200.8095703125,
+      "loss": 0.1771,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": -4.27340841293335,
+      "rewards/margins": 6.554012298583984,
+      "rewards/rejected": -10.827421188354492,
+      "step": 400
+    },
+    {
+      "epoch": 0.7881288098023521,
+      "eval_logits/chosen": -0.5448604226112366,
+      "eval_logits/rejected": -0.19432824850082397,
+      "eval_logps/chosen": -493.8166198730469,
+      "eval_logps/rejected": -1190.50244140625,
+      "eval_loss": 0.17544269561767578,
+      "eval_rewards/accuracies": 0.9259999990463257,
+      "eval_rewards/chosen": -4.008386135101318,
+      "eval_rewards/margins": 6.704952239990234,
+      "eval_rewards/rejected": -10.713338851928711,
+      "eval_runtime": 214.2304,
+      "eval_samples_per_second": 9.331,
+      "eval_steps_per_second": 1.167,
+      "step": 400
+    },
+    {
+      "epoch": 0.7979804199248814,
+      "grad_norm": 37.559098494289486,
+      "learning_rate": 5.9228982950048414e-08,
+      "logits/chosen": -0.11747940629720688,
+      "logits/rejected": 0.3246985077857971,
+      "logps/chosen": -457.470458984375,
+      "logps/rejected": -1168.145263671875,
+      "loss": 0.1866,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.701908826828003,
+      "rewards/margins": 6.846765041351318,
+      "rewards/rejected": -10.548673629760742,
+      "step": 405
+    },
+    {
+      "epoch": 0.8078320300474109,
+      "grad_norm": 18.967931681147036,
+      "learning_rate": 5.3777444402291345e-08,
+      "logits/chosen": -0.0594136044383049,
+      "logits/rejected": 0.3661075234413147,
+      "logps/chosen": -468.72479248046875,
+      "logps/rejected": -1272.2440185546875,
+      "loss": 0.1991,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -3.781808376312256,
+      "rewards/margins": 7.8276567459106445,
+      "rewards/rejected": -11.609464645385742,
+      "step": 410
+    },
+    {
+      "epoch": 0.8176836401699403,
+      "grad_norm": 21.254093408332785,
+      "learning_rate": 4.855872358475546e-08,
+      "logits/chosen": -0.10291663557291031,
+      "logits/rejected": 0.2963753342628479,
+      "logps/chosen": -469.9095764160156,
+      "logps/rejected": -1065.603515625,
+      "loss": 0.1732,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -3.8083081245422363,
+      "rewards/margins": 5.7012176513671875,
+      "rewards/rejected": -9.509527206420898,
+      "step": 415
+    },
+    {
+      "epoch": 0.8275352502924697,
+      "grad_norm": 33.55300123869426,
+      "learning_rate": 4.357901250086107e-08,
+      "logits/chosen": -0.10372807085514069,
+      "logits/rejected": 0.2795334756374359,
+      "logps/chosen": -468.9990234375,
+      "logps/rejected": -1177.652099609375,
+      "loss": 0.1954,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": -3.7628936767578125,
+      "rewards/margins": 6.844532012939453,
+      "rewards/rejected": -10.607426643371582,
+      "step": 420
+    },
+    {
+      "epoch": 0.8373868604149991,
+      "grad_norm": 19.96643515144232,
+      "learning_rate": 3.884421956938377e-08,
+      "logits/chosen": 0.09214131534099579,
+      "logits/rejected": 0.2883525490760803,
+      "logps/chosen": -478.8783264160156,
+      "logps/rejected": -1042.8377685546875,
+      "loss": 0.1974,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -3.875990629196167,
+      "rewards/margins": 5.487939834594727,
+      "rewards/rejected": -9.363931655883789,
+      "step": 425
+    },
+    {
+      "epoch": 0.8472384705375284,
+      "grad_norm": 25.172312180362216,
+      "learning_rate": 3.435996261412591e-08,
+      "logits/chosen": -0.10333506762981415,
+      "logits/rejected": 0.3282162845134735,
+      "logps/chosen": -495.544189453125,
+      "logps/rejected": -1291.604736328125,
+      "loss": 0.1563,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.0302324295043945,
+      "rewards/margins": 7.705834865570068,
+      "rewards/rejected": -11.736066818237305,
+      "step": 430
+    },
+    {
+      "epoch": 0.8570900806600579,
+      "grad_norm": 15.065416122622528,
+      "learning_rate": 3.013156219837776e-08,
+      "logits/chosen": -0.07826174050569534,
+      "logits/rejected": 0.3285934329032898,
+      "logps/chosen": -421.72967529296875,
+      "logps/rejected": -1110.5625,
+      "loss": 0.1732,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -3.3744163513183594,
+      "rewards/margins": 6.624072074890137,
+      "rewards/rejected": -9.99848747253418,
+      "step": 435
+    },
+    {
+      "epoch": 0.8669416907825873,
+      "grad_norm": 26.990693570929402,
+      "learning_rate": 2.6164035312078447e-08,
+      "logits/chosen": -0.03792654722929001,
+      "logits/rejected": 0.30625802278518677,
+      "logps/chosen": -409.1098937988281,
+      "logps/rejected": -896.5735473632812,
+      "loss": 0.1964,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -3.2458598613739014,
+      "rewards/margins": 4.6952667236328125,
+      "rewards/rejected": -7.941126346588135,
+      "step": 440
+    },
+    {
+      "epoch": 0.8767933009051166,
+      "grad_norm": 18.262645314073836,
+      "learning_rate": 2.2462089419165776e-08,
+      "logits/chosen": -0.1863568276166916,
+      "logits/rejected": 0.3409372866153717,
+      "logps/chosen": -467.3153381347656,
+      "logps/rejected": -1355.0755615234375,
+      "loss": 0.1532,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -3.7305431365966797,
+      "rewards/margins": 8.520989418029785,
+      "rewards/rejected": -12.251531600952148,
+      "step": 445
+    },
+    {
+      "epoch": 0.8866449110276461,
+      "grad_norm": 16.536933510909858,
+      "learning_rate": 1.9030116872178314e-08,
+      "logits/chosen": -0.10226424038410187,
+      "logits/rejected": 0.3626253008842468,
+      "logps/chosen": -477.93170166015625,
+      "logps/rejected": -1282.739013671875,
+      "loss": 0.1462,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.8922367095947266,
+      "rewards/margins": 7.7512617111206055,
+      "rewards/rejected": -11.643498420715332,
+      "step": 450
+    },
+    {
+      "epoch": 0.8964965211501755,
+      "grad_norm": 10.605383942176456,
+      "learning_rate": 1.5872189700736337e-08,
+      "logits/chosen": -0.14325854182243347,
+      "logits/rejected": 0.3355133831501007,
+      "logps/chosen": -450.6402282714844,
+      "logps/rejected": -1201.0908203125,
+      "loss": 0.1639,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.650237560272217,
+      "rewards/margins": 7.2110915184021,
+      "rewards/rejected": -10.861330032348633,
+      "step": 455
+    },
+    {
+      "epoch": 0.9063481312727049,
+      "grad_norm": 22.268888152026168,
+      "learning_rate": 1.2992054780085692e-08,
+      "logits/chosen": -0.09486164897680283,
+      "logits/rejected": 0.34676122665405273,
+      "logps/chosen": -434.63916015625,
+      "logps/rejected": -1102.545166015625,
+      "loss": 0.1605,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -3.450458526611328,
+      "rewards/margins": 6.4033966064453125,
+      "rewards/rejected": -9.85385513305664,
+      "step": 460
+    },
+    {
+      "epoch": 0.9161997413952343,
+      "grad_norm": 30.068002083238966,
+      "learning_rate": 1.0393129385436823e-08,
+      "logits/chosen": -0.07793921232223511,
+      "logits/rejected": 0.35799723863601685,
+      "logps/chosen": -450.42236328125,
+      "logps/rejected": -1204.390380859375,
+      "loss": 0.1863,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -3.6568875312805176,
+      "rewards/margins": 7.287510871887207,
+      "rewards/rejected": -10.944398880004883,
+      "step": 465
+    },
+    {
+      "epoch": 0.9260513515177636,
+      "grad_norm": 24.896591444655538,
+      "learning_rate": 8.078497137373242e-09,
+      "logits/chosen": -0.03868895769119263,
+      "logits/rejected": 0.34498023986816406,
+      "logps/chosen": -448.8158264160156,
+      "logps/rejected": -1223.0908203125,
+      "loss": 0.1799,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": -3.6430060863494873,
+      "rewards/margins": 7.505183219909668,
+      "rewards/rejected": -11.14819049835205,
+      "step": 470
+    },
+    {
+      "epoch": 0.9359029616402931,
+      "grad_norm": 29.386355030565646,
+      "learning_rate": 6.0509043431410945e-09,
+      "logits/chosen": -0.07840202748775482,
+      "logits/rejected": 0.3709198832511902,
+      "logps/chosen": -503.24237060546875,
+      "logps/rejected": -1247.880859375,
+      "loss": 0.1969,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -4.159943580627441,
+      "rewards/margins": 7.216925144195557,
+      "rewards/rejected": -11.376869201660156,
+      "step": 475
+    },
+    {
+      "epoch": 0.9457545717628225,
+      "grad_norm": 26.49780454490534,
+      "learning_rate": 4.312756738160145e-09,
+      "logits/chosen": -0.07440705597400665,
+      "logits/rejected": 0.28477969765663147,
+      "logps/chosen": -449.20635986328125,
+      "logps/rejected": -1111.6458740234375,
+      "loss": 0.19,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.603930711746216,
+      "rewards/margins": 6.4518842697143555,
+      "rewards/rejected": -10.055814743041992,
+      "step": 480
+    },
+    {
+      "epoch": 0.9556061818853518,
+      "grad_norm": 20.045924933102782,
+      "learning_rate": 2.8661166316229223e-09,
+      "logits/chosen": -0.08851344138383865,
+      "logits/rejected": 0.32577767968177795,
+      "logps/chosen": -488.3605041503906,
+      "logps/rejected": -1200.70751953125,
+      "loss": 0.1585,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -3.9997458457946777,
+      "rewards/margins": 6.837733268737793,
+      "rewards/rejected": -10.837480545043945,
+      "step": 485
+    },
+    {
+      "epoch": 0.9654577920078813,
+      "grad_norm": 21.692842758377346,
+      "learning_rate": 1.7127004595681727e-09,
+      "logits/chosen": 0.09783969819545746,
+      "logits/rejected": 0.29853665828704834,
+      "logps/chosen": -477.9693908691406,
+      "logps/rejected": -1061.865966796875,
+      "loss": 0.1506,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -3.9010696411132812,
+      "rewards/margins": 5.679271697998047,
+      "rewards/rejected": -9.580340385437012,
+      "step": 490
+    },
+    {
+      "epoch": 0.9753094021304107,
+      "grad_norm": 29.610243074061593,
+      "learning_rate": 8.538767483325383e-10,
+      "logits/chosen": 0.014114913530647755,
+      "logits/rejected": 0.3291045129299164,
+      "logps/chosen": -506.1124572753906,
+      "logps/rejected": -1098.880859375,
+      "loss": 0.1765,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -4.2126784324646,
+      "rewards/margins": 5.722815990447998,
+      "rewards/rejected": -9.935495376586914,
+      "step": 495
+    },
+    {
+      "epoch": 0.9851610122529401,
+      "grad_norm": 16.600143003716234,
+      "learning_rate": 2.9066449079634404e-10,
+      "logits/chosen": -0.01632627286016941,
+      "logits/rejected": 0.2808447480201721,
+      "logps/chosen": -494.154296875,
+      "logps/rejected": -1137.5577392578125,
+      "loss": 0.2076,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -4.033506870269775,
+      "rewards/margins": 6.235844612121582,
+      "rewards/rejected": -10.2693510055542,
+      "step": 500
+    },
+    {
+      "epoch": 0.9950126223754695,
+      "grad_norm": 25.20857166646325,
+      "learning_rate": 2.3731937350224273e-11,
+      "logits/chosen": -0.03347567096352577,
+      "logits/rejected": 0.3957715928554535,
+      "logps/chosen": -471.24090576171875,
+      "logps/rejected": -1382.8267822265625,
+      "loss": 0.1625,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -3.8446497917175293,
+      "rewards/margins": 8.762639045715332,
+      "rewards/rejected": -12.607287406921387,
+      "step": 505
+    },
+    {
+      "epoch": 0.9989532664244812,
+      "step": 507,
+      "total_flos": 0.0,
+      "train_loss": 0.2931108748654172,
+      "train_runtime": 25855.3563,
+      "train_samples_per_second": 2.512,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 507,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2c97c9d342a45d099097cab845cfe9c1d71811c972ba17b8167d1e2fb70a9d
+size 7608