Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+base_model: sam-paech/gutenberg3-orpo-exp02
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- sam-paech/gutenberg3-generalfiction-scifi-fantasy-romance-adventure-dpo
+model-index:
+- name: gemma-2-9b-it-gutenberg3
+  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. -->
+
+# gemma-2-9b-it-gutenberg3
+
+This model is a fine-tuned version of [sam-paech/gutenberg3-orpo-exp02](https://huggingface.co/sam-paech/gutenberg3-orpo-exp02) on the sam-paech/gutenberg3-generalfiction-scifi-fantasy-romance-adventure-dpo dataset.
+It achieves the following results on the evaluation set:
+- Loss: 21.6407
+- Rewards/chosen: -27.5382
+- Rewards/rejected: -10.2163
+- Rewards/accuracies: 0.0
+- Rewards/margins: -17.3219
+- Logps/rejected: -1.0216
+- Logps/chosen: -2.7538
+
+## 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-08
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 5
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 10
+- total_eval_batch_size: 5
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|
+| 21.4429       | 0.7092 | 400  | 21.6407         | -27.5382       | -10.2163         | 0.0                | -17.3219        | -1.0216        | -2.7538      |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.2.0+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 1.0,
+    "eval_logps/chosen": -2.755657434463501,
+    "eval_logps/rejected": -1.0496879816055298,
+    "eval_loss": 21.31629180908203,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": -27.55657386779785,
+    "eval_rewards/margins": -17.059694290161133,
+    "eval_rewards/rejected": -10.496879577636719,
+    "eval_runtime": 4.3483,
+    "eval_samples": 12,
+    "eval_samples_per_second": 2.76,
+    "eval_steps_per_second": 0.69,
+    "total_flos": 0.0,
+    "train_loss": 22.58866818745931,
+    "train_runtime": 4347.6828,
+    "train_samples": 5640,
+    "train_samples_per_second": 1.297,
+    "train_steps_per_second": 0.13
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "sam-paech/gutenberg3-orpo-exp02",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_logps/chosen": -2.755657434463501,
+    "eval_logps/rejected": -1.0496879816055298,
+    "eval_loss": 21.31629180908203,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": -27.55657386779785,
+    "eval_rewards/margins": -17.059694290161133,
+    "eval_rewards/rejected": -10.496879577636719,
+    "eval_runtime": 4.3483,
+    "eval_samples": 12,
+    "eval_samples_per_second": 2.76,
+    "eval_steps_per_second": 0.69
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97086396b3fa562927919650db1d1489eb740a618aad8498950569c164200b26
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7204fb83d1809969a3d00c58fda70f7946d69c160c96907de0e8300f0fe8db27
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aeaabca91b5a12a506c4728e2884e64596a35af11042b0e3869e3efcf7cbce
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567bb26478ca1d5c0aa05367fcac6d03f0b23eb840b9be7def2fba9fc2c40762
+size 3670322200

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_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-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-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.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_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.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_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-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_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 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer_config.json

@@ -0,0 +1,2014 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 22.58866818745931,
+    "train_runtime": 4347.6828,
+    "train_samples": 5640,
+    "train_samples_per_second": 1.297,
+    "train_steps_per_second": 0.13
+}

trainer_state.json

@@ -0,0 +1,1512 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 400,
+  "global_step": 564,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008865248226950355,
+      "grad_norm": 149.09850698280093,
+      "learning_rate": 4.385964912280701e-09,
+      "logps/chosen": -2.8927114009857178,
+      "logps/rejected": -0.7169164419174194,
+      "loss": 25.3611,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.927114486694336,
+      "rewards/margins": -21.757949829101562,
+      "rewards/rejected": -7.169164180755615,
+      "step": 5
+    },
+    {
+      "epoch": 0.01773049645390071,
+      "grad_norm": 133.9237477557748,
+      "learning_rate": 8.771929824561403e-09,
+      "logps/chosen": -2.677772045135498,
+      "logps/rejected": -0.7764161825180054,
+      "loss": 24.583,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.777721405029297,
+      "rewards/margins": -19.013559341430664,
+      "rewards/rejected": -7.764161109924316,
+      "step": 10
+    },
+    {
+      "epoch": 0.026595744680851064,
+      "grad_norm": 152.65228499963413,
+      "learning_rate": 1.3157894736842104e-08,
+      "logps/chosen": -2.491425037384033,
+      "logps/rejected": -0.7799981832504272,
+      "loss": 24.3721,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -24.914249420166016,
+      "rewards/margins": -17.114269256591797,
+      "rewards/rejected": -7.79998254776001,
+      "step": 15
+    },
+    {
+      "epoch": 0.03546099290780142,
+      "grad_norm": 167.82984889261684,
+      "learning_rate": 1.7543859649122805e-08,
+      "logps/chosen": -2.818477153778076,
+      "logps/rejected": -0.8185766935348511,
+      "loss": 24.5782,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.184768676757812,
+      "rewards/margins": -19.999004364013672,
+      "rewards/rejected": -8.185766220092773,
+      "step": 20
+    },
+    {
+      "epoch": 0.044326241134751775,
+      "grad_norm": 158.80212467372465,
+      "learning_rate": 2.1929824561403507e-08,
+      "logps/chosen": -3.06237530708313,
+      "logps/rejected": -0.685140073299408,
+      "loss": 24.7471,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -30.62375259399414,
+      "rewards/margins": -23.77235221862793,
+      "rewards/rejected": -6.851400852203369,
+      "step": 25
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 146.70835684303188,
+      "learning_rate": 2.6315789473684208e-08,
+      "logps/chosen": -2.6460320949554443,
+      "logps/rejected": -0.7569402456283569,
+      "loss": 24.7665,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.4603214263916,
+      "rewards/margins": -18.890918731689453,
+      "rewards/rejected": -7.569401741027832,
+      "step": 30
+    },
+    {
+      "epoch": 0.06205673758865248,
+      "grad_norm": 155.08422103006285,
+      "learning_rate": 3.070175438596491e-08,
+      "logps/chosen": -2.725968837738037,
+      "logps/rejected": -0.7673903703689575,
+      "loss": 24.0323,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.259693145751953,
+      "rewards/margins": -19.58578872680664,
+      "rewards/rejected": -7.673903465270996,
+      "step": 35
+    },
+    {
+      "epoch": 0.07092198581560284,
+      "grad_norm": 144.68445966753478,
+      "learning_rate": 3.508771929824561e-08,
+      "logps/chosen": -2.8730432987213135,
+      "logps/rejected": -0.7648515105247498,
+      "loss": 24.9421,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.73043441772461,
+      "rewards/margins": -21.081920623779297,
+      "rewards/rejected": -7.648515224456787,
+      "step": 40
+    },
+    {
+      "epoch": 0.0797872340425532,
+      "grad_norm": 136.66852055782576,
+      "learning_rate": 3.947368421052631e-08,
+      "logps/chosen": -2.648432970046997,
+      "logps/rejected": -0.7622749209403992,
+      "loss": 24.9349,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.484333038330078,
+      "rewards/margins": -18.861581802368164,
+      "rewards/rejected": -7.622749328613281,
+      "step": 45
+    },
+    {
+      "epoch": 0.08865248226950355,
+      "grad_norm": 137.8970167243902,
+      "learning_rate": 4.385964912280701e-08,
+      "logps/chosen": -2.7805895805358887,
+      "logps/rejected": -0.7085495591163635,
+      "loss": 23.7959,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.805896759033203,
+      "rewards/margins": -20.72039794921875,
+      "rewards/rejected": -7.085495948791504,
+      "step": 50
+    },
+    {
+      "epoch": 0.0975177304964539,
+      "grad_norm": 144.53363403919823,
+      "learning_rate": 4.8245614035087715e-08,
+      "logps/chosen": -2.7633585929870605,
+      "logps/rejected": -0.766043484210968,
+      "loss": 24.5894,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.63358497619629,
+      "rewards/margins": -19.973148345947266,
+      "rewards/rejected": -7.660434722900391,
+      "step": 55
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 186.10146168517474,
+      "learning_rate": 4.999568059583401e-08,
+      "logps/chosen": -2.605541706085205,
+      "logps/rejected": -0.7882484197616577,
+      "loss": 24.1209,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.0554141998291,
+      "rewards/margins": -18.172931671142578,
+      "rewards/rejected": -7.88248348236084,
+      "step": 60
+    },
+    {
+      "epoch": 0.11524822695035461,
+      "grad_norm": 144.73338067190508,
+      "learning_rate": 4.9969289642076847e-08,
+      "logps/chosen": -2.691685199737549,
+      "logps/rejected": -0.7605332136154175,
+      "loss": 24.5817,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.916851043701172,
+      "rewards/margins": -19.311519622802734,
+      "rewards/rejected": -7.6053314208984375,
+      "step": 65
+    },
+    {
+      "epoch": 0.12411347517730496,
+      "grad_norm": 142.10076756137335,
+      "learning_rate": 4.991893270335525e-08,
+      "logps/chosen": -2.887664318084717,
+      "logps/rejected": -0.7798042297363281,
+      "loss": 25.4368,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.876644134521484,
+      "rewards/margins": -21.078603744506836,
+      "rewards/rejected": -7.798041343688965,
+      "step": 70
+    },
+    {
+      "epoch": 0.13297872340425532,
+      "grad_norm": 136.39554296889824,
+      "learning_rate": 4.9844658113188256e-08,
+      "logps/chosen": -2.554642915725708,
+      "logps/rejected": -0.741515576839447,
+      "loss": 25.032,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.546428680419922,
+      "rewards/margins": -18.131275177001953,
+      "rewards/rejected": -7.41515588760376,
+      "step": 75
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 150.8035431184681,
+      "learning_rate": 4.974653716169812e-08,
+      "logps/chosen": -2.592639923095703,
+      "logps/rejected": -0.7398035526275635,
+      "loss": 24.5209,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.9263973236084,
+      "rewards/margins": -18.528364181518555,
+      "rewards/rejected": -7.398035526275635,
+      "step": 80
+    },
+    {
+      "epoch": 0.15070921985815602,
+      "grad_norm": 131.31880148234296,
+      "learning_rate": 4.962466402718474e-08,
+      "logps/chosen": -2.76173734664917,
+      "logps/rejected": -0.7157766819000244,
+      "loss": 24.4644,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.61737060546875,
+      "rewards/margins": -20.459604263305664,
+      "rewards/rejected": -7.157766819000244,
+      "step": 85
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 134.79926804392827,
+      "learning_rate": 4.9479155685731585e-08,
+      "logps/chosen": -2.651050329208374,
+      "logps/rejected": -0.8522893190383911,
+      "loss": 23.8276,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.510501861572266,
+      "rewards/margins": -17.98760986328125,
+      "rewards/rejected": -8.522892951965332,
+      "step": 90
+    },
+    {
+      "epoch": 0.16843971631205673,
+      "grad_norm": 148.45315521916737,
+      "learning_rate": 4.93101517989299e-08,
+      "logps/chosen": -2.806105136871338,
+      "logps/rejected": -0.8227446675300598,
+      "loss": 24.8131,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.061050415039062,
+      "rewards/margins": -19.833606719970703,
+      "rewards/rejected": -8.227446556091309,
+      "step": 95
+    },
+    {
+      "epoch": 0.1773049645390071,
+      "grad_norm": 143.9707085484871,
+      "learning_rate": 4.91178145798289e-08,
+      "logps/chosen": -2.8190388679504395,
+      "logps/rejected": -0.7673857808113098,
+      "loss": 24.4349,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.19038963317871,
+      "rewards/margins": -20.516530990600586,
+      "rewards/rejected": -7.673857688903809,
+      "step": 100
+    },
+    {
+      "epoch": 0.18617021276595744,
+      "grad_norm": 142.14896402628358,
+      "learning_rate": 4.890232863724074e-08,
+      "logps/chosen": -2.5820021629333496,
+      "logps/rejected": -0.7970396876335144,
+      "loss": 24.1908,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.820018768310547,
+      "rewards/margins": -17.849624633789062,
+      "rewards/rejected": -7.970396518707275,
+      "step": 105
+    },
+    {
+      "epoch": 0.1950354609929078,
+      "grad_norm": 146.1009589129858,
+      "learning_rate": 4.8663900798549555e-08,
+      "logps/chosen": -2.6352057456970215,
+      "logps/rejected": -0.7787631154060364,
+      "loss": 23.47,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.3520565032959,
+      "rewards/margins": -18.564428329467773,
+      "rewards/rejected": -7.787631034851074,
+      "step": 110
+    },
+    {
+      "epoch": 0.20390070921985815,
+      "grad_norm": 140.00337741613868,
+      "learning_rate": 4.84027599111947e-08,
+      "logps/chosen": -2.8055331707000732,
+      "logps/rejected": -0.7519856095314026,
+      "loss": 24.6991,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.055328369140625,
+      "rewards/margins": -20.535472869873047,
+      "rewards/rejected": -7.5198564529418945,
+      "step": 115
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 141.35660015466556,
+      "learning_rate": 4.8119156623018765e-08,
+      "logps/chosen": -2.79301118850708,
+      "logps/rejected": -0.7545806765556335,
+      "loss": 24.7028,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.93011474609375,
+      "rewards/margins": -20.384307861328125,
+      "rewards/rejected": -7.545806884765625,
+      "step": 120
+    },
+    {
+      "epoch": 0.22163120567375885,
+      "grad_norm": 142.6726786477248,
+      "learning_rate": 4.781336314169116e-08,
+      "logps/chosen": -2.820788860321045,
+      "logps/rejected": -0.8155437707901001,
+      "loss": 24.0466,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.207889556884766,
+      "rewards/margins": -20.05245018005371,
+      "rewards/rejected": -8.155437469482422,
+      "step": 125
+    },
+    {
+      "epoch": 0.23049645390070922,
+      "grad_norm": 132.8640819326495,
+      "learning_rate": 4.748567297343817e-08,
+      "logps/chosen": -2.764223575592041,
+      "logps/rejected": -0.7645096182823181,
+      "loss": 24.7092,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.642236709594727,
+      "rewards/margins": -19.997140884399414,
+      "rewards/rejected": -7.6450958251953125,
+      "step": 130
+    },
+    {
+      "epoch": 0.2393617021276596,
+      "grad_norm": 139.96100373862689,
+      "learning_rate": 4.713640064133024e-08,
+      "logps/chosen": -2.7403454780578613,
+      "logps/rejected": -0.745998740196228,
+      "loss": 23.5556,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.403453826904297,
+      "rewards/margins": -19.943464279174805,
+      "rewards/rejected": -7.459986686706543,
+      "step": 135
+    },
+    {
+      "epoch": 0.24822695035460993,
+      "grad_norm": 148.02227270943942,
+      "learning_rate": 4.676588138339698e-08,
+      "logps/chosen": -2.7284622192382812,
+      "logps/rejected": -0.7950869798660278,
+      "loss": 23.8238,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.284622192382812,
+      "rewards/margins": -19.333749771118164,
+      "rewards/rejected": -7.950869560241699,
+      "step": 140
+    },
+    {
+      "epoch": 0.2570921985815603,
+      "grad_norm": 176.18112226614372,
+      "learning_rate": 4.6374470830859435e-08,
+      "logps/chosen": -2.7229888439178467,
+      "logps/rejected": -0.8719980120658875,
+      "loss": 24.1807,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.229888916015625,
+      "rewards/margins": -18.50990867614746,
+      "rewards/rejected": -8.719980239868164,
+      "step": 145
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 135.96118644362534,
+      "learning_rate": 4.596254466678876e-08,
+      "logps/chosen": -2.56044340133667,
+      "logps/rejected": -0.8695181012153625,
+      "loss": 22.9327,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.60443687438965,
+      "rewards/margins": -16.90925407409668,
+      "rewards/rejected": -8.695180892944336,
+      "step": 150
+    },
+    {
+      "epoch": 0.274822695035461,
+      "grad_norm": 132.24528952538998,
+      "learning_rate": 4.5530498265518635e-08,
+      "logps/chosen": -2.813053607940674,
+      "logps/rejected": -0.808445155620575,
+      "loss": 23.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.130535125732422,
+      "rewards/margins": -20.04608726501465,
+      "rewards/rejected": -8.084451675415039,
+      "step": 155
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 127.79059567307556,
+      "learning_rate": 4.507874631315768e-08,
+      "logps/chosen": -2.66123628616333,
+      "logps/rejected": -0.8127639889717102,
+      "loss": 23.47,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.61236000061035,
+      "rewards/margins": -18.48472023010254,
+      "rewards/rejected": -8.127640724182129,
+      "step": 160
+    },
+    {
+      "epoch": 0.2925531914893617,
+      "grad_norm": 129.2315474298329,
+      "learning_rate": 4.460772240956608e-08,
+      "logps/chosen": -2.7900562286376953,
+      "logps/rejected": -0.849897027015686,
+      "loss": 23.8895,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.900564193725586,
+      "rewards/margins": -19.401594161987305,
+      "rewards/rejected": -8.498970985412598,
+      "step": 165
+    },
+    {
+      "epoch": 0.30141843971631205,
+      "grad_norm": 130.10241912996838,
+      "learning_rate": 4.411787865217846e-08,
+      "logps/chosen": -2.605811595916748,
+      "logps/rejected": -0.7789794206619263,
+      "loss": 24.0528,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.0581111907959,
+      "rewards/margins": -18.268321990966797,
+      "rewards/rejected": -7.789793491363525,
+      "step": 170
+    },
+    {
+      "epoch": 0.3102836879432624,
+      "grad_norm": 125.41956154105759,
+      "learning_rate": 4.36096852020724e-08,
+      "logps/chosen": -2.852963924407959,
+      "logps/rejected": -0.8932555913925171,
+      "loss": 24.7971,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.529638290405273,
+      "rewards/margins": -19.59708023071289,
+      "rewards/rejected": -8.932558059692383,
+      "step": 175
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 129.52798142464744,
+      "learning_rate": 4.308362983269915e-08,
+      "logps/chosen": -2.6496150493621826,
+      "logps/rejected": -0.8426092267036438,
+      "loss": 24.0708,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.496150970458984,
+      "rewards/margins": -18.070056915283203,
+      "rewards/rejected": -8.426092147827148,
+      "step": 180
+    },
+    {
+      "epoch": 0.3280141843971631,
+      "grad_norm": 124.39272381055714,
+      "learning_rate": 4.2540217461709714e-08,
+      "logps/chosen": -2.640799045562744,
+      "logps/rejected": -0.7842020988464355,
+      "loss": 23.3526,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.407989501953125,
+      "rewards/margins": -18.565967559814453,
+      "rewards/rejected": -7.8420209884643555,
+      "step": 185
+    },
+    {
+      "epoch": 0.33687943262411346,
+      "grad_norm": 135.5931742125443,
+      "learning_rate": 4.1979969666325505e-08,
+      "logps/chosen": -2.4907784461975098,
+      "logps/rejected": -0.8824084997177124,
+      "loss": 23.1102,
+      "rewards/accuracies": 0.10000000149011612,
+      "rewards/chosen": -24.907785415649414,
+      "rewards/margins": -16.083698272705078,
+      "rewards/rejected": -8.824087142944336,
+      "step": 190
+    },
+    {
+      "epoch": 0.34574468085106386,
+      "grad_norm": 124.78318512461612,
+      "learning_rate": 4.140342418271896e-08,
+      "logps/chosen": -2.566643476486206,
+      "logps/rejected": -0.8403929471969604,
+      "loss": 23.9738,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.666433334350586,
+      "rewards/margins": -17.262508392333984,
+      "rewards/rejected": -8.403928756713867,
+      "step": 195
+    },
+    {
+      "epoch": 0.3546099290780142,
+      "grad_norm": 124.54166567693945,
+      "learning_rate": 4.0811134389884425e-08,
+      "logps/chosen": -2.662815570831299,
+      "logps/rejected": -0.8375980257987976,
+      "loss": 23.2471,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.628154754638672,
+      "rewards/margins": -18.25217628479004,
+      "rewards/rejected": -8.37597942352295,
+      "step": 200
+    },
+    {
+      "epoch": 0.36347517730496454,
+      "grad_norm": 129.10521131399426,
+      "learning_rate": 4.020366877849477e-08,
+      "logps/chosen": -2.899678945541382,
+      "logps/rejected": -0.9157842397689819,
+      "loss": 22.6395,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.99679183959961,
+      "rewards/margins": -19.838947296142578,
+      "rewards/rejected": -9.157841682434082,
+      "step": 205
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 118.9218343714434,
+      "learning_rate": 3.958161040525354e-08,
+      "logps/chosen": -2.7788329124450684,
+      "logps/rejected": -0.7856232523918152,
+      "loss": 24.5067,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.788330078125,
+      "rewards/margins": -19.93209457397461,
+      "rewards/rejected": -7.856232643127441,
+      "step": 210
+    },
+    {
+      "epoch": 0.38120567375886527,
+      "grad_norm": 124.20603604955339,
+      "learning_rate": 3.894555633326642e-08,
+      "logps/chosen": -2.766160011291504,
+      "logps/rejected": -0.8535798192024231,
+      "loss": 23.9262,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.66160011291504,
+      "rewards/margins": -19.125802993774414,
+      "rewards/rejected": -8.535799026489258,
+      "step": 215
+    },
+    {
+      "epoch": 0.3900709219858156,
+      "grad_norm": 122.4047572823285,
+      "learning_rate": 3.829611705896899e-08,
+      "logps/chosen": -2.758810520172119,
+      "logps/rejected": -0.8758818507194519,
+      "loss": 23.0933,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.58810806274414,
+      "rewards/margins": -18.829286575317383,
+      "rewards/rejected": -8.758818626403809,
+      "step": 220
+    },
+    {
+      "epoch": 0.39893617021276595,
+      "grad_norm": 136.57138875427492,
+      "learning_rate": 3.763391592616104e-08,
+      "logps/chosen": -2.629612445831299,
+      "logps/rejected": -0.8354926109313965,
+      "loss": 23.2906,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.296123504638672,
+      "rewards/margins": -17.941198348999023,
+      "rewards/rejected": -8.354926109313965,
+      "step": 225
+    },
+    {
+      "epoch": 0.4078014184397163,
+      "grad_norm": 125.42475135454727,
+      "learning_rate": 3.695958852770963e-08,
+      "logps/chosen": -2.629051685333252,
+      "logps/rejected": -0.8992561101913452,
+      "loss": 23.2326,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.290517807006836,
+      "rewards/margins": -17.297956466674805,
+      "rewards/rejected": -8.992559432983398,
+      "step": 230
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 130.81865526034508,
+      "learning_rate": 3.627378209549536e-08,
+      "logps/chosen": -2.713019847869873,
+      "logps/rejected": -0.9180544018745422,
+      "loss": 23.2666,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.130197525024414,
+      "rewards/margins": -17.94965171813965,
+      "rewards/rejected": -9.180543899536133,
+      "step": 235
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 154.01811109390695,
+      "learning_rate": 3.557715487918728e-08,
+      "logps/chosen": -2.845736265182495,
+      "logps/rejected": -0.8981745839118958,
+      "loss": 22.8914,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.45736312866211,
+      "rewards/margins": -19.475618362426758,
+      "rewards/rejected": -8.981744766235352,
+      "step": 240
+    },
+    {
+      "epoch": 0.43439716312056736,
+      "grad_norm": 124.72008912272919,
+      "learning_rate": 3.487037551444267e-08,
+      "logps/chosen": -2.6402182579040527,
+      "logps/rejected": -0.9148176908493042,
+      "loss": 24.0945,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.40218162536621,
+      "rewards/margins": -17.254005432128906,
+      "rewards/rejected": -9.148177146911621,
+      "step": 245
+    },
+    {
+      "epoch": 0.4432624113475177,
+      "grad_norm": 126.67782694015744,
+      "learning_rate": 3.4154122381138226e-08,
+      "logps/chosen": -2.8172085285186768,
+      "logps/rejected": -0.9476315379142761,
+      "loss": 22.8683,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.17208480834961,
+      "rewards/margins": -18.695770263671875,
+      "rewards/rejected": -9.476313591003418,
+      "step": 250
+    },
+    {
+      "epoch": 0.4521276595744681,
+      "grad_norm": 128.76198121819777,
+      "learning_rate": 3.3429082952248535e-08,
+      "logps/chosen": -2.6602797508239746,
+      "logps/rejected": -0.9177526235580444,
+      "loss": 22.7192,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.602794647216797,
+      "rewards/margins": -17.42526626586914,
+      "rewards/rejected": -9.177526473999023,
+      "step": 255
+    },
+    {
+      "epoch": 0.46099290780141844,
+      "grad_norm": 120.09861391040339,
+      "learning_rate": 3.2695953133996826e-08,
+      "logps/chosen": -2.6814820766448975,
+      "logps/rejected": -0.8409668803215027,
+      "loss": 22.8322,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.8148193359375,
+      "rewards/margins": -18.405153274536133,
+      "rewards/rejected": -8.409668922424316,
+      "step": 260
+    },
+    {
+      "epoch": 0.4698581560283688,
+      "grad_norm": 149.0293076595361,
+      "learning_rate": 3.195543659791132e-08,
+      "logps/chosen": -2.6782455444335938,
+      "logps/rejected": -0.988556981086731,
+      "loss": 22.749,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.782455444335938,
+      "rewards/margins": -16.896886825561523,
+      "rewards/rejected": -9.88556957244873,
+      "step": 265
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 120.49824463691422,
+      "learning_rate": 3.120824410542833e-08,
+      "logps/chosen": -2.619314193725586,
+      "logps/rejected": -0.9258754849433899,
+      "loss": 22.1466,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.19314193725586,
+      "rewards/margins": -16.93438720703125,
+      "rewards/rejected": -9.25875473022461,
+      "step": 270
+    },
+    {
+      "epoch": 0.4875886524822695,
+      "grad_norm": 126.28759504359856,
+      "learning_rate": 3.045509282569031e-08,
+      "logps/chosen": -2.569866895675659,
+      "logps/rejected": -0.843720555305481,
+      "loss": 22.4486,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.69866943359375,
+      "rewards/margins": -17.261463165283203,
+      "rewards/rejected": -8.43720531463623,
+      "step": 275
+    },
+    {
+      "epoch": 0.49645390070921985,
+      "grad_norm": 133.61205279748194,
+      "learning_rate": 2.969670564719369e-08,
+      "logps/chosen": -2.705709457397461,
+      "logps/rejected": -0.8904563784599304,
+      "loss": 22.7856,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.057092666625977,
+      "rewards/margins": -18.152530670166016,
+      "rewards/rejected": -8.904562950134277,
+      "step": 280
+    },
+    {
+      "epoch": 0.5053191489361702,
+      "grad_norm": 125.31007604414539,
+      "learning_rate": 2.893381048394715e-08,
+      "logps/chosen": -2.5439467430114746,
+      "logps/rejected": -0.9845563173294067,
+      "loss": 22.3419,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.43946647644043,
+      "rewards/margins": -15.593902587890625,
+      "rewards/rejected": -9.845562934875488,
+      "step": 285
+    },
+    {
+      "epoch": 0.5141843971631206,
+      "grad_norm": 133.3039752253482,
+      "learning_rate": 2.8167139576806304e-08,
+      "logps/chosen": -2.7466816902160645,
+      "logps/rejected": -0.9437241554260254,
+      "loss": 22.5713,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.466812133789062,
+      "rewards/margins": -18.029569625854492,
+      "rewards/rejected": -9.43724250793457,
+      "step": 290
+    },
+    {
+      "epoch": 0.5230496453900709,
+      "grad_norm": 125.8510714937569,
+      "learning_rate": 2.739742879065544e-08,
+      "logps/chosen": -2.6576900482177734,
+      "logps/rejected": -0.9526101350784302,
+      "loss": 22.5247,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.576900482177734,
+      "rewards/margins": -17.050800323486328,
+      "rewards/rejected": -9.526101112365723,
+      "step": 295
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 132.63761511287686,
+      "learning_rate": 2.662541690811082e-08,
+      "logps/chosen": -2.3779425621032715,
+      "logps/rejected": -0.8925439715385437,
+      "loss": 21.2831,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -23.779422760009766,
+      "rewards/margins": -14.853982925415039,
+      "rewards/rejected": -8.925439834594727,
+      "step": 300
+    },
+    {
+      "epoch": 0.5407801418439716,
+      "grad_norm": 136.13215779336474,
+      "learning_rate": 2.585184492042347e-08,
+      "logps/chosen": -2.6994504928588867,
+      "logps/rejected": -0.9614452123641968,
+      "loss": 21.5851,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.9945068359375,
+      "rewards/margins": -17.38005256652832,
+      "rewards/rejected": -9.614453315734863,
+      "step": 305
+    },
+    {
+      "epoch": 0.549645390070922,
+      "grad_norm": 132.02028150495246,
+      "learning_rate": 2.5077455316262147e-08,
+      "logps/chosen": -2.6731841564178467,
+      "logps/rejected": -0.9815571904182434,
+      "loss": 21.7416,
+      "rewards/accuracies": 0.10000000149011612,
+      "rewards/chosen": -26.73184585571289,
+      "rewards/margins": -16.916271209716797,
+      "rewards/rejected": -9.815571784973145,
+      "step": 310
+    },
+    {
+      "epoch": 0.5585106382978723,
+      "grad_norm": 130.67893366658126,
+      "learning_rate": 2.4302991369058958e-08,
+      "logps/chosen": -2.51406192779541,
+      "logps/rejected": -1.0564053058624268,
+      "loss": 20.9766,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.1406192779541,
+      "rewards/margins": -14.576566696166992,
+      "rewards/rejected": -10.564051628112793,
+      "step": 315
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 131.46127648897104,
+      "learning_rate": 2.3529196423601876e-08,
+      "logps/chosen": -2.443092107772827,
+      "logps/rejected": -0.9888316988945007,
+      "loss": 22.5219,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -24.43092155456543,
+      "rewards/margins": -14.54260540008545,
+      "rewards/rejected": -9.888317108154297,
+      "step": 320
+    },
+    {
+      "epoch": 0.5762411347517731,
+      "grad_norm": 134.82856786462523,
+      "learning_rate": 2.27568131825586e-08,
+      "logps/chosen": -2.7351233959198,
+      "logps/rejected": -1.0152182579040527,
+      "loss": 21.4016,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.35123634338379,
+      "rewards/margins": -17.199050903320312,
+      "rewards/rejected": -10.152182579040527,
+      "step": 325
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 138.32340221747404,
+      "learning_rate": 2.1986582993616925e-08,
+      "logps/chosen": -2.5989935398101807,
+      "logps/rejected": -0.9776498079299927,
+      "loss": 21.6639,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.989938735961914,
+      "rewards/margins": -16.213438034057617,
+      "rewards/rejected": -9.776496887207031,
+      "step": 330
+    },
+    {
+      "epoch": 0.5939716312056738,
+      "grad_norm": 144.27555433213394,
+      "learning_rate": 2.121924513792548e-08,
+      "logps/chosen": -2.7326598167419434,
+      "logps/rejected": -0.993288516998291,
+      "loss": 22.0246,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.326595306396484,
+      "rewards/margins": -17.39371109008789,
+      "rewards/rejected": -9.93288516998291,
+      "step": 335
+    },
+    {
+      "epoch": 0.6028368794326241,
+      "grad_norm": 131.66189209302496,
+      "learning_rate": 2.0455536120518093e-08,
+      "logps/chosen": -2.7750537395477295,
+      "logps/rejected": -1.0254470109939575,
+      "loss": 21.3832,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.750534057617188,
+      "rewards/margins": -17.496063232421875,
+      "rewards/rejected": -10.254469871520996,
+      "step": 340
+    },
+    {
+      "epoch": 0.6117021276595744,
+      "grad_norm": 133.29472374802276,
+      "learning_rate": 1.969618896340261e-08,
+      "logps/chosen": -2.791393756866455,
+      "logps/rejected": -0.9777949452400208,
+      "loss": 21.8087,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.9139404296875,
+      "rewards/margins": -18.1359920501709,
+      "rewards/rejected": -9.777949333190918,
+      "step": 345
+    },
+    {
+      "epoch": 0.6205673758865248,
+      "grad_norm": 132.7071056456499,
+      "learning_rate": 1.8941932501992915e-08,
+      "logps/chosen": -2.528127670288086,
+      "logps/rejected": -0.9332917928695679,
+      "loss": 22.4318,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.281272888183594,
+      "rewards/margins": -15.948354721069336,
+      "rewards/rejected": -9.332918167114258,
+      "step": 350
+    },
+    {
+      "epoch": 0.6294326241134752,
+      "grad_norm": 133.23550694363342,
+      "learning_rate": 1.8193490685559176e-08,
+      "logps/chosen": -2.6291937828063965,
+      "logps/rejected": -1.0154783725738525,
+      "loss": 21.633,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.291940689086914,
+      "rewards/margins": -16.137157440185547,
+      "rewards/rejected": -10.154783248901367,
+      "step": 355
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 131.9862073113527,
+      "learning_rate": 1.745158188236805e-08,
+      "logps/chosen": -2.7716784477233887,
+      "logps/rejected": -0.9892207980155945,
+      "loss": 21.8071,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.716785430908203,
+      "rewards/margins": -17.824573516845703,
+      "rewards/rejected": -9.89220905303955,
+      "step": 360
+    },
+    {
+      "epoch": 0.6471631205673759,
+      "grad_norm": 133.59469928327707,
+      "learning_rate": 1.6716918190179507e-08,
+      "logps/chosen": -2.824233055114746,
+      "logps/rejected": -1.0325210094451904,
+      "loss": 21.8658,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.24233055114746,
+      "rewards/margins": -17.91712188720703,
+      "rewards/rejected": -10.325210571289062,
+      "step": 365
+    },
+    {
+      "epoch": 0.6560283687943262,
+      "grad_norm": 137.91947812898098,
+      "learning_rate": 1.599020475276227e-08,
+      "logps/chosen": -2.6540284156799316,
+      "logps/rejected": -1.0216987133026123,
+      "loss": 21.8092,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.540287017822266,
+      "rewards/margins": -16.323299407958984,
+      "rewards/rejected": -10.216985702514648,
+      "step": 370
+    },
+    {
+      "epoch": 0.6648936170212766,
+      "grad_norm": 139.4931571924634,
+      "learning_rate": 1.527213908308386e-08,
+      "logps/chosen": -2.6086392402648926,
+      "logps/rejected": -1.0575668811798096,
+      "loss": 21.1347,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.086395263671875,
+      "rewards/margins": -15.510726928710938,
+      "rewards/rejected": -10.575668334960938,
+      "step": 375
+    },
+    {
+      "epoch": 0.6737588652482269,
+      "grad_norm": 140.7825368139536,
+      "learning_rate": 1.45634103938247e-08,
+      "logps/chosen": -2.7265937328338623,
+      "logps/rejected": -1.1351561546325684,
+      "loss": 21.6724,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.265939712524414,
+      "rewards/margins": -15.914377212524414,
+      "rewards/rejected": -11.3515625,
+      "step": 380
+    },
+    {
+      "epoch": 0.6826241134751773,
+      "grad_norm": 155.36198841615501,
+      "learning_rate": 1.3864698935859152e-08,
+      "logps/chosen": -2.785165309906006,
+      "logps/rejected": -1.016316533088684,
+      "loss": 21.7173,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.851654052734375,
+      "rewards/margins": -17.688488006591797,
+      "rewards/rejected": -10.163165092468262,
+      "step": 385
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 142.46678106209737,
+      "learning_rate": 1.3176675345338084e-08,
+      "logps/chosen": -2.720693349838257,
+      "logps/rejected": -1.0303252935409546,
+      "loss": 21.5356,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.206933975219727,
+      "rewards/margins": -16.903682708740234,
+      "rewards/rejected": -10.303252220153809,
+      "step": 390
+    },
+    {
+      "epoch": 0.700354609929078,
+      "grad_norm": 145.09087804013313,
+      "learning_rate": 1.2500000000000004e-08,
+      "logps/chosen": -2.8458621501922607,
+      "logps/rejected": -1.0235410928726196,
+      "loss": 21.0196,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.4586181640625,
+      "rewards/margins": -18.22321128845215,
+      "rewards/rejected": -10.2354097366333,
+      "step": 395
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 141.31236991069352,
+      "learning_rate": 1.1835322385328258e-08,
+      "logps/chosen": -2.525390625,
+      "logps/rejected": -1.0862586498260498,
+      "loss": 21.4429,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.25390625,
+      "rewards/margins": -14.391319274902344,
+      "rewards/rejected": -10.862588882446289,
+      "step": 400
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "eval_logps/chosen": -2.753817319869995,
+      "eval_logps/rejected": -1.0216267108917236,
+      "eval_loss": 21.640687942504883,
+      "eval_rewards/accuracies": 0.0,
+      "eval_rewards/chosen": -27.538171768188477,
+      "eval_rewards/margins": -17.3219051361084,
+      "eval_rewards/rejected": -10.216267585754395,
+      "eval_runtime": 4.3362,
+      "eval_samples_per_second": 2.767,
+      "eval_steps_per_second": 0.692,
+      "step": 400
+    },
+    {
+      "epoch": 0.7180851063829787,
+      "grad_norm": 138.30907528011366,
+      "learning_rate": 1.1183280471162916e-08,
+      "logps/chosen": -2.6900100708007812,
+      "logps/rejected": -1.054898977279663,
+      "loss": 21.6015,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.900100708007812,
+      "rewards/margins": -16.351110458374023,
+      "rewards/rejected": -10.548989295959473,
+      "step": 405
+    },
+    {
+      "epoch": 0.7269503546099291,
+      "grad_norm": 140.60691958793103,
+      "learning_rate": 1.0544500099365513e-08,
+      "logps/chosen": -2.5441603660583496,
+      "logps/rejected": -1.0485824346542358,
+      "loss": 20.2114,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.441608428955078,
+      "rewards/margins": -14.955782890319824,
+      "rewards/rejected": -10.485824584960938,
+      "step": 410
+    },
+    {
+      "epoch": 0.7358156028368794,
+      "grad_norm": 158.54062894661507,
+      "learning_rate": 9.91959438312451e-09,
+      "logps/chosen": -2.586798667907715,
+      "logps/rejected": -1.0556939840316772,
+      "loss": 20.7519,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.867984771728516,
+      "rewards/margins": -15.31104564666748,
+      "rewards/rejected": -10.556941032409668,
+      "step": 415
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 145.7088174939863,
+      "learning_rate": 9.309163118477952e-09,
+      "logps/chosen": -2.7213327884674072,
+      "logps/rejected": -1.10366690158844,
+      "loss": 20.9045,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.213327407836914,
+      "rewards/margins": -16.176658630371094,
+      "rewards/rejected": -11.036666870117188,
+      "step": 420
+    },
+    {
+      "epoch": 0.7535460992907801,
+      "grad_norm": 140.87803118012943,
+      "learning_rate": 8.713792208618095e-09,
+      "logps/chosen": -2.7333548069000244,
+      "logps/rejected": -1.0871623754501343,
+      "loss": 21.3148,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.333545684814453,
+      "rewards/margins": -16.461925506591797,
+      "rewards/rejected": -10.871623039245605,
+      "step": 425
+    },
+    {
+      "epoch": 0.7624113475177305,
+      "grad_norm": 148.2931552966102,
+      "learning_rate": 8.134053101530814e-09,
+      "logps/chosen": -2.6974215507507324,
+      "logps/rejected": -1.0488805770874023,
+      "loss": 22.011,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.974212646484375,
+      "rewards/margins": -16.485408782958984,
+      "rewards/rejected": -10.488804817199707,
+      "step": 430
+    },
+    {
+      "epoch": 0.7712765957446809,
+      "grad_norm": 156.37941932984688,
+      "learning_rate": 7.570502241509161e-09,
+      "logps/chosen": -2.6490612030029297,
+      "logps/rejected": -1.0499160289764404,
+      "loss": 20.7465,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.490612030029297,
+      "rewards/margins": -15.991450309753418,
+      "rewards/rejected": -10.499159812927246,
+      "step": 435
+    },
+    {
+      "epoch": 0.7801418439716312,
+      "grad_norm": 142.1179108847554,
+      "learning_rate": 7.023680535067997e-09,
+      "logps/chosen": -2.540945053100586,
+      "logps/rejected": -1.1362855434417725,
+      "loss": 20.9313,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.40945053100586,
+      "rewards/margins": -14.046595573425293,
+      "rewards/rejected": -11.362855911254883,
+      "step": 440
+    },
+    {
+      "epoch": 0.7890070921985816,
+      "grad_norm": 142.7591601522917,
+      "learning_rate": 6.4941128317718e-09,
+      "logps/chosen": -2.71937894821167,
+      "logps/rejected": -1.0216131210327148,
+      "loss": 21.3747,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.19378662109375,
+      "rewards/margins": -16.977657318115234,
+      "rewards/rejected": -10.216130256652832,
+      "step": 445
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 146.19832437425603,
+      "learning_rate": 5.9823074204745e-09,
+      "logps/chosen": -2.6064822673797607,
+      "logps/rejected": -1.1812522411346436,
+      "loss": 20.7936,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.0648250579834,
+      "rewards/margins": -14.252301216125488,
+      "rewards/rejected": -11.812520980834961,
+      "step": 450
+    },
+    {
+      "epoch": 0.8067375886524822,
+      "grad_norm": 138.88047068502686,
+      "learning_rate": 5.4887555414543344e-09,
+      "logps/chosen": -2.6501286029815674,
+      "logps/rejected": -1.0125081539154053,
+      "loss": 20.8237,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.50128746032715,
+      "rewards/margins": -16.376205444335938,
+      "rewards/rejected": -10.125081062316895,
+      "step": 455
+    },
+    {
+      "epoch": 0.8156028368794326,
+      "grad_norm": 136.88698229561803,
+      "learning_rate": 5.0139309149124755e-09,
+      "logps/chosen": -2.5912132263183594,
+      "logps/rejected": -1.1049864292144775,
+      "loss": 20.3607,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.91213035583496,
+      "rewards/margins": -14.862268447875977,
+      "rewards/rejected": -11.049863815307617,
+      "step": 460
+    },
+    {
+      "epoch": 0.824468085106383,
+      "grad_norm": 150.56544212976812,
+      "learning_rate": 4.558289286287545e-09,
+      "logps/chosen": -2.563302516937256,
+      "logps/rejected": -1.1222257614135742,
+      "loss": 20.5554,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.63302993774414,
+      "rewards/margins": -14.41076946258545,
+      "rewards/rejected": -11.222257614135742,
+      "step": 465
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 151.83025187850424,
+      "learning_rate": 4.122267988822792e-09,
+      "logps/chosen": -2.8155665397644043,
+      "logps/rejected": -1.1182525157928467,
+      "loss": 20.6342,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.15566635131836,
+      "rewards/margins": -16.973140716552734,
+      "rewards/rejected": -11.182525634765625,
+      "step": 470
+    },
+    {
+      "epoch": 0.8421985815602837,
+      "grad_norm": 143.90652908649776,
+      "learning_rate": 3.7062855238055775e-09,
+      "logps/chosen": -2.8534111976623535,
+      "logps/rejected": -1.079416275024414,
+      "loss": 21.6896,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.534109115600586,
+      "rewards/margins": -17.739948272705078,
+      "rewards/rejected": -10.794163703918457,
+      "step": 475
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 146.70532693647684,
+      "learning_rate": 3.310741158882052e-09,
+      "logps/chosen": -2.5945401191711426,
+      "logps/rejected": -1.1171306371688843,
+      "loss": 20.8278,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.945398330688477,
+      "rewards/margins": -14.774093627929688,
+      "rewards/rejected": -11.171305656433105,
+      "step": 480
+    },
+    {
+      "epoch": 0.8599290780141844,
+      "grad_norm": 152.1225967764815,
+      "learning_rate": 2.9360145448327933e-09,
+      "logps/chosen": -2.7132070064544678,
+      "logps/rejected": -1.10798978805542,
+      "loss": 20.2016,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.132068634033203,
+      "rewards/margins": -16.052169799804688,
+      "rewards/rejected": -11.079896926879883,
+      "step": 485
+    },
+    {
+      "epoch": 0.8687943262411347,
+      "grad_norm": 148.4298648799797,
+      "learning_rate": 2.5824653511768905e-09,
+      "logps/chosen": -2.7444825172424316,
+      "logps/rejected": -1.0877773761749268,
+      "loss": 20.6239,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.44482421875,
+      "rewards/margins": -16.56705093383789,
+      "rewards/rejected": -10.877774238586426,
+      "step": 490
+    },
+    {
+      "epoch": 0.8776595744680851,
+      "grad_norm": 149.3789958144051,
+      "learning_rate": 2.250432920954584e-09,
+      "logps/chosen": -2.625457286834717,
+      "logps/rejected": -1.1413992643356323,
+      "loss": 20.8323,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.25457191467285,
+      "rewards/margins": -14.840580940246582,
+      "rewards/rejected": -11.413991928100586,
+      "step": 495
+    },
+    {
+      "epoch": 0.8865248226950354,
+      "grad_norm": 149.24437602693683,
+      "learning_rate": 1.9402359450194834e-09,
+      "logps/chosen": -2.633744716644287,
+      "logps/rejected": -1.0395913124084473,
+      "loss": 21.1488,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.337448120117188,
+      "rewards/margins": -15.941534042358398,
+      "rewards/rejected": -10.395914077758789,
+      "step": 500
+    },
+    {
+      "epoch": 0.8953900709219859,
+      "grad_norm": 148.69800996723336,
+      "learning_rate": 1.6521721561532642e-09,
+      "logps/chosen": -2.753237724304199,
+      "logps/rejected": -1.091736078262329,
+      "loss": 21.1955,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.53237533569336,
+      "rewards/margins": -16.61501693725586,
+      "rewards/rejected": -10.91736125946045,
+      "step": 505
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 140.23345832085906,
+      "learning_rate": 1.3865180432961975e-09,
+      "logps/chosen": -2.7156546115875244,
+      "logps/rejected": -1.033905029296875,
+      "loss": 20.9517,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.156545639038086,
+      "rewards/margins": -16.8174991607666,
+      "rewards/rejected": -10.33905029296875,
+      "step": 510
+    },
+    {
+      "epoch": 0.9131205673758865,
+      "grad_norm": 135.7495898891431,
+      "learning_rate": 1.1435285861680105e-09,
+      "logps/chosen": -2.6717796325683594,
+      "logps/rejected": -1.1057870388031006,
+      "loss": 20.2493,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.71779441833496,
+      "rewards/margins": -15.65992546081543,
+      "rewards/rejected": -11.057870864868164,
+      "step": 515
+    },
+    {
+      "epoch": 0.9219858156028369,
+      "grad_norm": 146.54140042392083,
+      "learning_rate": 9.234370105336037e-10,
+      "logps/chosen": -2.7197585105895996,
+      "logps/rejected": -1.0512771606445312,
+      "loss": 20.9221,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.197586059570312,
+      "rewards/margins": -16.684812545776367,
+      "rewards/rejected": -10.512772560119629,
+      "step": 520
+    },
+    {
+      "epoch": 0.9308510638297872,
+      "grad_norm": 154.92783543731412,
+      "learning_rate": 7.264545643486997e-10,
+      "logps/chosen": -2.7849745750427246,
+      "logps/rejected": -1.0905792713165283,
+      "loss": 21.5713,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.849742889404297,
+      "rewards/margins": -16.943950653076172,
+      "rewards/rejected": -10.905792236328125,
+      "step": 525
+    },
+    {
+      "epoch": 0.9397163120567376,
+      "grad_norm": 151.56459387858007,
+      "learning_rate": 5.527703150001173e-10,
+      "logps/chosen": -2.8318445682525635,
+      "logps/rejected": -1.042283535003662,
+      "loss": 21.4995,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -28.31844711303711,
+      "rewards/margins": -17.895610809326172,
+      "rewards/rejected": -10.422834396362305,
+      "step": 530
+    },
+    {
+      "epoch": 0.9485815602836879,
+      "grad_norm": 163.48745110663447,
+      "learning_rate": 4.0255096783542995e-10,
+      "logps/chosen": -2.5114052295684814,
+      "logps/rejected": -1.1133381128311157,
+      "loss": 20.1608,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.114055633544922,
+      "rewards/margins": -13.980671882629395,
+      "rewards/rejected": -11.133380889892578,
+      "step": 535
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 149.97953788101626,
+      "learning_rate": 2.759407061560942e-10,
+      "logps/chosen": -2.641373872756958,
+      "logps/rejected": -1.0878345966339111,
+      "loss": 20.6395,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -26.41373634338379,
+      "rewards/margins": -15.535390853881836,
+      "rewards/rejected": -10.878347396850586,
+      "step": 540
+    },
+    {
+      "epoch": 0.9663120567375887,
+      "grad_norm": 146.82377405274374,
+      "learning_rate": 1.7306105282764162e-10,
+      "logps/chosen": -2.7007031440734863,
+      "logps/rejected": -1.1214299201965332,
+      "loss": 21.5189,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -27.007030487060547,
+      "rewards/margins": -15.792730331420898,
+      "rewards/rejected": -11.214300155639648,
+      "step": 545
+    },
+    {
+      "epoch": 0.975177304964539,
+      "grad_norm": 146.05557779309504,
+      "learning_rate": 9.401075363981436e-11,
+      "logps/chosen": -2.5641696453094482,
+      "logps/rejected": -1.0827744007110596,
+      "loss": 20.7057,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.641698837280273,
+      "rewards/margins": -14.813952445983887,
+      "rewards/rejected": -10.827742576599121,
+      "step": 550
+    },
+    {
+      "epoch": 0.9840425531914894,
+      "grad_norm": 141.1483903438878,
+      "learning_rate": 3.886568252850497e-11,
+      "logps/chosen": -2.5521302223205566,
+      "logps/rejected": -1.1713207960128784,
+      "loss": 20.7053,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": -25.521303176879883,
+      "rewards/margins": -13.808095932006836,
+      "rewards/rejected": -11.713208198547363,
+      "step": 555
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 150.04371038548183,
+      "learning_rate": 7.678768750579711e-12,
+      "logps/chosen": -2.5215792655944824,
+      "logps/rejected": -1.0503337383270264,
+      "loss": 20.6892,
+      "rewards/accuracies": 0.10000000149011612,
+      "rewards/chosen": -25.215795516967773,
+      "rewards/margins": -14.712457656860352,
+      "rewards/rejected": -10.503335952758789,
+      "step": 560
+    },
+    {
+      "epoch": 1.0,
+      "step": 564,
+      "total_flos": 0.0,
+      "train_loss": 22.58866818745931,
+      "train_runtime": 4347.6828,
+      "train_samples_per_second": 1.297,
+      "train_steps_per_second": 0.13
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 564,
+  "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 sha256:9bb2dd606cf9ba0bc22e51800fcf10d8ae9e942ca9776779f742768d1e28fb59
+size 7224