Model save

.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 +1,82 @@
+---
+license: gemma
+base_model: tanliboy/zephyr-gemma-2-9b-sft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-gemma-2-9b-dpo-2
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tanliboy/huggingface/runs/igf2ndcz)
+# zephyr-gemma-2-9b-dpo-2
+
+This model is a fine-tuned version of [tanliboy/zephyr-gemma-2-9b-sft](https://huggingface.co/tanliboy/zephyr-gemma-2-9b-sft) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5276
+- Rewards/chosen: -0.6043
+- Rewards/rejected: -1.2270
+- Rewards/accuracies: 0.6960
+- Rewards/margins: 0.6227
+- Logps/rejected: -407.1073
+- Logps/chosen: -374.7531
+- Logits/rejected: -14.2849
+- Logits/chosen: -14.1010
+
+## 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: 2e-07
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6677        | 0.1047 | 100  | 0.6651          | 0.0269         | -0.0301          | 0.6440             | 0.0570          | -287.4193      | -311.6301    | -9.5213         | -9.2788       |
+| 0.5915        | 0.2094 | 200  | 0.5920          | -0.3361        | -0.6472          | 0.6880             | 0.3110          | -349.1276      | -347.9349    | -11.9562        | -11.6561      |
+| 0.5723        | 0.3141 | 300  | 0.5674          | -0.3955        | -0.7898          | 0.6880             | 0.3943          | -363.3917      | -353.8749    | -12.6873        | -12.4526      |
+| 0.5622        | 0.4187 | 400  | 0.5468          | -0.5688        | -1.0827          | 0.6800             | 0.5139          | -392.6759      | -371.2007    | -14.2367        | -13.9401      |
+| 0.5441        | 0.5234 | 500  | 0.5363          | -0.6274        | -1.2091          | 0.6680             | 0.5817          | -405.3189      | -377.0607    | -14.3976        | -14.1308      |
+| 0.5125        | 0.6281 | 600  | 0.5344          | -0.5757        | -1.1705          | 0.6840             | 0.5948          | -401.4605      | -371.8937    | -14.3713        | -14.1120      |
+| 0.5158        | 0.7328 | 700  | 0.5316          | -0.6220        | -1.2328          | 0.6760             | 0.6108          | -407.6867      | -376.5182    | -14.2832        | -14.1010      |
+| 0.5133        | 0.8375 | 800  | 0.5278          | -0.6258        | -1.2452          | 0.6800             | 0.6193          | -408.9254      | -376.9043    | -14.2747        | -14.0908      |
+| 0.5098        | 0.9422 | 900  | 0.5276          | -0.6043        | -1.2270          | 0.6960             | 0.6227          | -407.1073      | -374.7531    | -14.2849        | -14.1010      |
+
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9997382884061764,
+    "total_flos": 0.0,
+    "train_loss": 0.560625178402007,
+    "train_runtime": 12630.0326,
+    "train_samples": 61134,
+    "train_samples_per_second": 4.84,
+    "train_steps_per_second": 0.076
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "tanliboy/zephyr-gemma-2-9b-sft",
+  "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": "4.43.1",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dd223dbcdd9b7a159d28e041c3cff016335f745f59a5b3466e5da8919ee4a2
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96131b3e5e3034f39e10580f4cc68a4df695e0048dde4e9d9d2295951355971b
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d6a5edeaaa5ffe3ff5e8750a8600a09ec2bdd555a199dced4e5d4a95cacada
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ef547d1ba1908a19965b389bfc81c663fa70f29eb43c67c0252b607855d663
+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"
+  }
+}

runs/Jul24_07-13-12_action-graph-trainer/events.out.tfevents.1721805765.action-graph-trainer.576983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41061d003fc957dcaea1f7e144107607b75a526eb27667366243173a029ac41f
+size 79306

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 sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ '<start_of_turn>' + message['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>",
+  "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": 0.9997382884061764,
+    "total_flos": 0.0,
+    "train_loss": 0.560625178402007,
+    "train_runtime": 12630.0326,
+    "train_samples": 61134,
+    "train_samples_per_second": 4.84,
+    "train_steps_per_second": 0.076
+}

trainer_state.json

@@ -0,0 +1,1626 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997382884061764,
+  "eval_steps": 100,
+  "global_step": 955,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010468463752944255,
+      "grad_norm": 7.355008386193469,
+      "learning_rate": 2.083333333333333e-09,
+      "logits/chosen": -7.783219814300537,
+      "logits/rejected": -8.072843551635742,
+      "logps/chosen": -335.8546142578125,
+      "logps/rejected": -277.73626708984375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.010468463752944255,
+      "grad_norm": 6.230445884319703,
+      "learning_rate": 2.0833333333333335e-08,
+      "logits/chosen": -7.981190204620361,
+      "logits/rejected": -8.130318641662598,
+      "logps/chosen": -306.2852783203125,
+      "logps/rejected": -309.1938781738281,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.4722222089767456,
+      "rewards/chosen": 0.0020241288002580404,
+      "rewards/margins": 0.0018345804419368505,
+      "rewards/rejected": 0.000189548620255664,
+      "step": 10
+    },
+    {
+      "epoch": 0.02093692750588851,
+      "grad_norm": 6.688413560820125,
+      "learning_rate": 4.166666666666667e-08,
+      "logits/chosen": -8.508150100708008,
+      "logits/rejected": -8.487831115722656,
+      "logps/chosen": -342.08197021484375,
+      "logps/rejected": -300.66973876953125,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.0012120783794671297,
+      "rewards/margins": -0.0002803016686812043,
+      "rewards/rejected": 0.0014923801645636559,
+      "step": 20
+    },
+    {
+      "epoch": 0.031405391258832765,
+      "grad_norm": 8.288905108120925,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": -7.823553562164307,
+      "logits/rejected": -8.030963897705078,
+      "logps/chosen": -294.57769775390625,
+      "logps/rejected": -290.71209716796875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": 0.001970288809388876,
+      "rewards/margins": 0.0006792033091187477,
+      "rewards/rejected": 0.0012910853838548064,
+      "step": 30
+    },
+    {
+      "epoch": 0.04187385501177702,
+      "grad_norm": 6.7092850577908285,
+      "learning_rate": 8.333333333333334e-08,
+      "logits/chosen": -8.137880325317383,
+      "logits/rejected": -8.182608604431152,
+      "logps/chosen": -302.7641906738281,
+      "logps/rejected": -278.7587890625,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": 0.004604184068739414,
+      "rewards/margins": 0.0005916848895139992,
+      "rewards/rejected": 0.004012499004602432,
+      "step": 40
+    },
+    {
+      "epoch": 0.05234231876472128,
+      "grad_norm": 11.714084906492422,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -8.555654525756836,
+      "logits/rejected": -9.059080123901367,
+      "logps/chosen": -318.3633728027344,
+      "logps/rejected": -257.5683288574219,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.010140976868569851,
+      "rewards/margins": 0.002551380079239607,
+      "rewards/rejected": 0.007589596323668957,
+      "step": 50
+    },
+    {
+      "epoch": 0.06281078251766553,
+      "grad_norm": 6.7230358924676015,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": -8.04963493347168,
+      "logits/rejected": -8.676374435424805,
+      "logps/chosen": -334.97003173828125,
+      "logps/rejected": -284.1954040527344,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.0205511637032032,
+      "rewards/margins": 0.006578472442924976,
+      "rewards/rejected": 0.013972689397633076,
+      "step": 60
+    },
+    {
+      "epoch": 0.07327924627060979,
+      "grad_norm": 6.439781455829167,
+      "learning_rate": 1.4583333333333332e-07,
+      "logits/chosen": -8.384071350097656,
+      "logits/rejected": -8.226759910583496,
+      "logps/chosen": -240.31106567382812,
+      "logps/rejected": -258.47332763671875,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.0298004187643528,
+      "rewards/margins": 0.011175071820616722,
+      "rewards/rejected": 0.018625345081090927,
+      "step": 70
+    },
+    {
+      "epoch": 0.08374771002355404,
+      "grad_norm": 6.513071298610303,
+      "learning_rate": 1.6666666666666668e-07,
+      "logits/chosen": -8.502431869506836,
+      "logits/rejected": -9.255155563354492,
+      "logps/chosen": -296.0177307128906,
+      "logps/rejected": -268.50347900390625,
+      "loss": 0.6815,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.04522623121738434,
+      "rewards/margins": 0.025061482563614845,
+      "rewards/rejected": 0.020164750516414642,
+      "step": 80
+    },
+    {
+      "epoch": 0.0942161737764983,
+      "grad_norm": 5.920042917298396,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": -8.7146635055542,
+      "logits/rejected": -8.876623153686523,
+      "logps/chosen": -272.12420654296875,
+      "logps/rejected": -255.40225219726562,
+      "loss": 0.6782,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.06685945391654968,
+      "rewards/margins": 0.04631630331277847,
+      "rewards/rejected": 0.02054314874112606,
+      "step": 90
+    },
+    {
+      "epoch": 0.10468463752944256,
+      "grad_norm": 7.4287436912349065,
+      "learning_rate": 1.9998929970725745e-07,
+      "logits/chosen": -8.944499969482422,
+      "logits/rejected": -8.88210678100586,
+      "logps/chosen": -293.67266845703125,
+      "logps/rejected": -300.55419921875,
+      "loss": 0.6677,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.049799270927906036,
+      "rewards/margins": 0.04667241498827934,
+      "rewards/rejected": 0.003126861061900854,
+      "step": 100
+    },
+    {
+      "epoch": 0.10468463752944256,
+      "eval_logits/chosen": -9.278841972351074,
+      "eval_logits/rejected": -9.52132511138916,
+      "eval_logps/chosen": -311.630126953125,
+      "eval_logps/rejected": -287.41925048828125,
+      "eval_loss": 0.6651390194892883,
+      "eval_rewards/accuracies": 0.6439999938011169,
+      "eval_rewards/chosen": 0.026908237487077713,
+      "eval_rewards/margins": 0.057010453194379807,
+      "eval_rewards/rejected": -0.030102219432592392,
+      "eval_runtime": 151.8713,
+      "eval_samples_per_second": 13.169,
+      "eval_steps_per_second": 0.823,
+      "step": 100
+    },
+    {
+      "epoch": 0.11515310128238682,
+      "grad_norm": 7.059170038910516,
+      "learning_rate": 1.9986894771071702e-07,
+      "logits/chosen": -9.338754653930664,
+      "logits/rejected": -9.311285972595215,
+      "logps/chosen": -288.4460144042969,
+      "logps/rejected": -247.97964477539062,
+      "loss": 0.6636,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.021794503554701805,
+      "rewards/margins": 0.10265706479549408,
+      "rewards/rejected": -0.08086254447698593,
+      "step": 110
+    },
+    {
+      "epoch": 0.12562156503533106,
+      "grad_norm": 8.852936631402919,
+      "learning_rate": 1.996150298485439e-07,
+      "logits/chosen": -10.604690551757812,
+      "logits/rejected": -10.366097450256348,
+      "logps/chosen": -265.26751708984375,
+      "logps/rejected": -300.37530517578125,
+      "loss": 0.6409,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.0008338313782587647,
+      "rewards/margins": 0.0940166562795639,
+      "rewards/rejected": -0.09485048055648804,
+      "step": 120
+    },
+    {
+      "epoch": 0.1360900287882753,
+      "grad_norm": 15.573650791324633,
+      "learning_rate": 1.9922788571337257e-07,
+      "logits/chosen": -10.188752174377441,
+      "logits/rejected": -10.191640853881836,
+      "logps/chosen": -323.96685791015625,
+      "logps/rejected": -297.19439697265625,
+      "loss": 0.6304,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.006395213305950165,
+      "rewards/margins": 0.13638103008270264,
+      "rewards/rejected": -0.1427762359380722,
+      "step": 130
+    },
+    {
+      "epoch": 0.14655849254121958,
+      "grad_norm": 20.046359115149162,
+      "learning_rate": 1.9870803307616914e-07,
+      "logits/chosen": -10.423749923706055,
+      "logits/rejected": -10.360530853271484,
+      "logps/chosen": -343.8540954589844,
+      "logps/rejected": -346.18634033203125,
+      "loss": 0.6211,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.14697681367397308,
+      "rewards/margins": 0.1654496192932129,
+      "rewards/rejected": -0.3124264180660248,
+      "step": 140
+    },
+    {
+      "epoch": 0.15702695629416383,
+      "grad_norm": 7.638915011188106,
+      "learning_rate": 1.9805616719375848e-07,
+      "logits/chosen": -10.7134370803833,
+      "logits/rejected": -11.019803047180176,
+      "logps/chosen": -330.085205078125,
+      "logps/rejected": -305.45208740234375,
+      "loss": 0.6196,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.15285547077655792,
+      "rewards/margins": 0.1812134087085724,
+      "rewards/rejected": -0.3340689241886139,
+      "step": 150
+    },
+    {
+      "epoch": 0.16749542004710807,
+      "grad_norm": 12.849690942872602,
+      "learning_rate": 1.972731598789799e-07,
+      "logits/chosen": -9.68244743347168,
+      "logits/rejected": -10.297185897827148,
+      "logps/chosen": -327.29144287109375,
+      "logps/rejected": -285.8588562011719,
+      "loss": 0.6086,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04306762292981148,
+      "rewards/margins": 0.2582402527332306,
+      "rewards/rejected": -0.3013078570365906,
+      "step": 160
+    },
+    {
+      "epoch": 0.17796388380005235,
+      "grad_norm": 32.698955102660705,
+      "learning_rate": 1.9636005833471467e-07,
+      "logits/chosen": -11.027162551879883,
+      "logits/rejected": -11.326080322265625,
+      "logps/chosen": -288.31817626953125,
+      "logps/rejected": -291.74908447265625,
+      "loss": 0.5927,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.3270031809806824,
+      "rewards/margins": 0.15106120705604553,
+      "rewards/rejected": -0.4780643582344055,
+      "step": 170
+    },
+    {
+      "epoch": 0.1884323475529966,
+      "grad_norm": 11.54139813571567,
+      "learning_rate": 1.9531808375334508e-07,
+      "logits/chosen": -10.985331535339355,
+      "logits/rejected": -11.428260803222656,
+      "logps/chosen": -317.88580322265625,
+      "logps/rejected": -319.74444580078125,
+      "loss": 0.5856,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.10588045418262482,
+      "rewards/margins": 0.28938889503479004,
+      "rewards/rejected": -0.39526933431625366,
+      "step": 180
+    },
+    {
+      "epoch": 0.19890081130594087,
+      "grad_norm": 10.803006572264644,
+      "learning_rate": 1.9414862968351785e-07,
+      "logits/chosen": -11.358689308166504,
+      "logits/rejected": -11.146299362182617,
+      "logps/chosen": -284.0877380371094,
+      "logps/rejected": -376.7961120605469,
+      "loss": 0.5878,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.08324204385280609,
+      "rewards/margins": 0.37117457389831543,
+      "rewards/rejected": -0.4544166624546051,
+      "step": 190
+    },
+    {
+      "epoch": 0.2093692750588851,
+      "grad_norm": 11.193966860687885,
+      "learning_rate": 1.9285326016639624e-07,
+      "logits/chosen": -11.543092727661133,
+      "logits/rejected": -11.964883804321289,
+      "logps/chosen": -355.447998046875,
+      "logps/rejected": -314.7781066894531,
+      "loss": 0.5915,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.1552293449640274,
+      "rewards/margins": 0.35743778944015503,
+      "rewards/rejected": -0.512667179107666,
+      "step": 200
+    },
+    {
+      "epoch": 0.2093692750588851,
+      "eval_logits/chosen": -11.656082153320312,
+      "eval_logits/rejected": -11.956182479858398,
+      "eval_logps/chosen": -347.9349060058594,
+      "eval_logps/rejected": -349.1275939941406,
+      "eval_loss": 0.5919647812843323,
+      "eval_rewards/accuracies": 0.6880000233650208,
+      "eval_rewards/chosen": -0.33613964915275574,
+      "eval_rewards/margins": 0.31104618310928345,
+      "eval_rewards/rejected": -0.6471858620643616,
+      "eval_runtime": 150.3287,
+      "eval_samples_per_second": 13.304,
+      "eval_steps_per_second": 0.832,
+      "step": 200
+    },
+    {
+      "epoch": 0.21983773881182936,
+      "grad_norm": 25.282722057255278,
+      "learning_rate": 1.914337076438937e-07,
+      "logits/chosen": -11.216215133666992,
+      "logits/rejected": -11.796686172485352,
+      "logps/chosen": -339.0605163574219,
+      "logps/rejected": -345.29901123046875,
+      "loss": 0.6089,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.44959211349487305,
+      "rewards/margins": 0.2086714208126068,
+      "rewards/rejected": -0.6582635641098022,
+      "step": 210
+    },
+    {
+      "epoch": 0.23030620256477363,
+      "grad_norm": 14.044802000055538,
+      "learning_rate": 1.898918706416864e-07,
+      "logits/chosen": -11.541923522949219,
+      "logits/rejected": -12.298526763916016,
+      "logps/chosen": -361.52947998046875,
+      "logps/rejected": -334.96905517578125,
+      "loss": 0.5912,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2677989602088928,
+      "rewards/margins": 0.373500794172287,
+      "rewards/rejected": -0.6412997245788574,
+      "step": 220
+    },
+    {
+      "epoch": 0.24077466631771788,
+      "grad_norm": 12.45188359067346,
+      "learning_rate": 1.882298112301034e-07,
+      "logits/chosen": -11.14279556274414,
+      "logits/rejected": -11.60063362121582,
+      "logps/chosen": -281.5401916503906,
+      "logps/rejected": -305.64166259765625,
+      "loss": 0.5863,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.23669323325157166,
+      "rewards/margins": 0.28197115659713745,
+      "rewards/rejected": -0.5186644196510315,
+      "step": 230
+    },
+    {
+      "epoch": 0.2512431300706621,
+      "grad_norm": 17.19152112354873,
+      "learning_rate": 1.8644975226629022e-07,
+      "logits/chosen": -11.584768295288086,
+      "logits/rejected": -11.848301887512207,
+      "logps/chosen": -325.7696838378906,
+      "logps/rejected": -335.9078369140625,
+      "loss": 0.5696,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2423885315656662,
+      "rewards/margins": 0.3221975266933441,
+      "rewards/rejected": -0.5645860433578491,
+      "step": 240
+    },
+    {
+      "epoch": 0.26171159382360637,
+      "grad_norm": 14.325794995366559,
+      "learning_rate": 1.8455407442133465e-07,
+      "logits/chosen": -11.799114227294922,
+      "logits/rejected": -12.152410507202148,
+      "logps/chosen": -329.87677001953125,
+      "logps/rejected": -324.18115234375,
+      "loss": 0.5655,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.24216821789741516,
+      "rewards/margins": 0.43084821105003357,
+      "rewards/rejected": -0.6730164289474487,
+      "step": 250
+    },
+    {
+      "epoch": 0.2721800575765506,
+      "grad_norm": 12.117583595266726,
+      "learning_rate": 1.8254531299633004e-07,
+      "logits/chosen": -12.106219291687012,
+      "logits/rejected": -12.641697883605957,
+      "logps/chosen": -344.15032958984375,
+      "logps/rejected": -348.90673828125,
+      "loss": 0.562,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.2714720666408539,
+      "rewards/margins": 0.39360731840133667,
+      "rewards/rejected": -0.6650794148445129,
+      "step": 260
+    },
+    {
+      "epoch": 0.2826485213294949,
+      "grad_norm": 17.931356253932698,
+      "learning_rate": 1.8042615453163484e-07,
+      "logits/chosen": -12.003366470336914,
+      "logits/rejected": -12.557150840759277,
+      "logps/chosen": -372.60821533203125,
+      "logps/rejected": -349.703125,
+      "loss": 0.5514,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.45285406708717346,
+      "rewards/margins": 0.3556319773197174,
+      "rewards/rejected": -0.8084859848022461,
+      "step": 270
+    },
+    {
+      "epoch": 0.29311698508243916,
+      "grad_norm": 14.078329477472565,
+      "learning_rate": 1.7819943321386296e-07,
+      "logits/chosen": -12.080374717712402,
+      "logits/rejected": -12.487339973449707,
+      "logps/chosen": -364.81134033203125,
+      "logps/rejected": -383.1141052246094,
+      "loss": 0.5755,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.3204973638057709,
+      "rewards/margins": 0.5626034140586853,
+      "rewards/rejected": -0.883100688457489,
+      "step": 280
+    },
+    {
+      "epoch": 0.3035854488353834,
+      "grad_norm": 16.797223533505605,
+      "learning_rate": 1.7586812708541044e-07,
+      "logits/chosen": -12.28768253326416,
+      "logits/rejected": -13.17219066619873,
+      "logps/chosen": -382.7824401855469,
+      "logps/rejected": -368.29449462890625,
+      "loss": 0.5672,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.40373754501342773,
+      "rewards/margins": 0.4520534873008728,
+      "rewards/rejected": -0.8557910919189453,
+      "step": 290
+    },
+    {
+      "epoch": 0.31405391258832765,
+      "grad_norm": 17.74775759360231,
+      "learning_rate": 1.7343535406158772e-07,
+      "logits/chosen": -12.226592063903809,
+      "logits/rejected": -12.483770370483398,
+      "logps/chosen": -300.1335144042969,
+      "logps/rejected": -350.2237854003906,
+      "loss": 0.5723,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.401310533285141,
+      "rewards/margins": 0.4268767833709717,
+      "rewards/rejected": -0.8281872868537903,
+      "step": 300
+    },
+    {
+      "epoch": 0.31405391258832765,
+      "eval_logits/chosen": -12.452622413635254,
+      "eval_logits/rejected": -12.687331199645996,
+      "eval_logps/chosen": -353.8749084472656,
+      "eval_logps/rejected": -363.39166259765625,
+      "eval_loss": 0.5674170851707458,
+      "eval_rewards/accuracies": 0.6880000233650208,
+      "eval_rewards/chosen": -0.39553993940353394,
+      "eval_rewards/margins": 0.39428621530532837,
+      "eval_rewards/rejected": -0.7898260354995728,
+      "eval_runtime": 150.1759,
+      "eval_samples_per_second": 13.318,
+      "eval_steps_per_second": 0.832,
+      "step": 300
+    },
+    {
+      "epoch": 0.3245223763412719,
+      "grad_norm": 21.123290325111288,
+      "learning_rate": 1.709043677606842e-07,
+      "logits/chosen": -13.11596393585205,
+      "logits/rejected": -13.485511779785156,
+      "logps/chosen": -372.96563720703125,
+      "logps/rejected": -374.05731201171875,
+      "loss": 0.5502,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4754568040370941,
+      "rewards/margins": 0.5059635043144226,
+      "rewards/rejected": -0.9814203381538391,
+      "step": 310
+    },
+    {
+      "epoch": 0.33499084009421615,
+      "grad_norm": 21.451163083722758,
+      "learning_rate": 1.6827855315254218e-07,
+      "logits/chosen": -12.301114082336426,
+      "logits/rejected": -11.965790748596191,
+      "logps/chosen": -310.0186462402344,
+      "logps/rejected": -385.1772155761719,
+      "loss": 0.5855,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.6075664758682251,
+      "rewards/margins": 0.4841720461845398,
+      "rewards/rejected": -1.0917384624481201,
+      "step": 320
+    },
+    {
+      "epoch": 0.34545930384716045,
+      "grad_norm": 18.33219470868773,
+      "learning_rate": 1.6556142203145976e-07,
+      "logits/chosen": -12.740918159484863,
+      "logits/rejected": -13.098161697387695,
+      "logps/chosen": -339.1952819824219,
+      "logps/rejected": -363.0919189453125,
+      "loss": 0.5684,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.5905572175979614,
+      "rewards/margins": 0.25887611508369446,
+      "rewards/rejected": -0.8494332432746887,
+      "step": 330
+    },
+    {
+      "epoch": 0.3559277676001047,
+      "grad_norm": 11.900265933520593,
+      "learning_rate": 1.6275660831947723e-07,
+      "logits/chosen": -11.391129493713379,
+      "logits/rejected": -11.80584716796875,
+      "logps/chosen": -294.5928955078125,
+      "logps/rejected": -305.561767578125,
+      "loss": 0.579,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.28244853019714355,
+      "rewards/margins": 0.5087226629257202,
+      "rewards/rejected": -0.7911711931228638,
+      "step": 340
+    },
+    {
+      "epoch": 0.36639623135304894,
+      "grad_norm": 20.453314348602326,
+      "learning_rate": 1.598678632063284e-07,
+      "logits/chosen": -12.832880973815918,
+      "logits/rejected": -13.420519828796387,
+      "logps/chosen": -368.6810302734375,
+      "logps/rejected": -389.3878479003906,
+      "loss": 0.5505,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4756461977958679,
+      "rewards/margins": 0.39826783537864685,
+      "rewards/rejected": -0.8739139437675476,
+      "step": 350
+    },
+    {
+      "epoch": 0.3768646951059932,
+      "grad_norm": 20.124446185453415,
+      "learning_rate": 1.568990501325568e-07,
+      "logits/chosen": -12.703775405883789,
+      "logits/rejected": -12.269942283630371,
+      "logps/chosen": -284.19219970703125,
+      "logps/rejected": -372.7416076660156,
+      "loss": 0.5258,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.4747592806816101,
+      "rewards/margins": 0.43383827805519104,
+      "rewards/rejected": -0.9085975885391235,
+      "step": 360
+    },
+    {
+      "epoch": 0.38733315885893743,
+      "grad_norm": 12.256605456435558,
+      "learning_rate": 1.5385413962250656e-07,
+      "logits/chosen": -13.217790603637695,
+      "logits/rejected": -13.344598770141602,
+      "logps/chosen": -338.6850280761719,
+      "logps/rejected": -376.1455993652344,
+      "loss": 0.545,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.41851702332496643,
+      "rewards/margins": 0.6487592458724976,
+      "rewards/rejected": -1.0672763586044312,
+      "step": 370
+    },
+    {
+      "epoch": 0.39780162261188173,
+      "grad_norm": 23.457846993021622,
+      "learning_rate": 1.507372039740978e-07,
+      "logits/chosen": -13.952138900756836,
+      "logits/rejected": -13.335546493530273,
+      "logps/chosen": -337.4014892578125,
+      "logps/rejected": -424.3997497558594,
+      "loss": 0.5639,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.5712438821792603,
+      "rewards/margins": 0.33642515540122986,
+      "rewards/rejected": -0.907668948173523,
+      "step": 380
+    },
+    {
+      "epoch": 0.408270086364826,
+      "grad_norm": 34.828863133678425,
+      "learning_rate": 1.475524118124892e-07,
+      "logits/chosen": -12.775480270385742,
+      "logits/rejected": -12.927217483520508,
+      "logps/chosen": -327.45843505859375,
+      "logps/rejected": -354.95562744140625,
+      "loss": 0.5512,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.5806573629379272,
+      "rewards/margins": 0.3768925070762634,
+      "rewards/rejected": -0.9575498700141907,
+      "step": 390
+    },
+    {
+      "epoch": 0.4187385501177702,
+      "grad_norm": 40.31423860042707,
+      "learning_rate": 1.4430402251491138e-07,
+      "logits/chosen": -13.684167861938477,
+      "logits/rejected": -13.840978622436523,
+      "logps/chosen": -374.80859375,
+      "logps/rejected": -402.02685546875,
+      "loss": 0.5622,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.6369796395301819,
+      "rewards/margins": 0.2776455581188202,
+      "rewards/rejected": -0.9146251678466797,
+      "step": 400
+    },
+    {
+      "epoch": 0.4187385501177702,
+      "eval_logits/chosen": -13.940086364746094,
+      "eval_logits/rejected": -14.236658096313477,
+      "eval_logps/chosen": -371.2007141113281,
+      "eval_logps/rejected": -392.6759033203125,
+      "eval_loss": 0.5468377470970154,
+      "eval_rewards/accuracies": 0.6800000071525574,
+      "eval_rewards/chosen": -0.5687984228134155,
+      "eval_rewards/margins": 0.5138704180717468,
+      "eval_rewards/rejected": -1.0826687812805176,
+      "eval_runtime": 149.8563,
+      "eval_samples_per_second": 13.346,
+      "eval_steps_per_second": 0.834,
+      "step": 400
+    },
+    {
+      "epoch": 0.42920701387071447,
+      "grad_norm": 16.540681614535696,
+      "learning_rate": 1.4099638051412743e-07,
+      "logits/chosen": -13.835235595703125,
+      "logits/rejected": -13.860295295715332,
+      "logps/chosen": -377.9153747558594,
+      "logps/rejected": -418.71014404296875,
+      "loss": 0.565,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.5656043291091919,
+      "rewards/margins": 0.5640857815742493,
+      "rewards/rejected": -1.129690170288086,
+      "step": 410
+    },
+    {
+      "epoch": 0.4396754776236587,
+      "grad_norm": 21.686061060497405,
+      "learning_rate": 1.3763390948813896e-07,
+      "logits/chosen": -13.40911865234375,
+      "logits/rejected": -13.989703178405762,
+      "logps/chosen": -390.37274169921875,
+      "logps/rejected": -365.4905090332031,
+      "loss": 0.5514,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.7015476226806641,
+      "rewards/margins": 0.3901844918727875,
+      "rewards/rejected": -1.091732144355774,
+      "step": 420
+    },
+    {
+      "epoch": 0.45014394137660296,
+      "grad_norm": 18.49857147965794,
+      "learning_rate": 1.342211064439091e-07,
+      "logits/chosen": -13.539401054382324,
+      "logits/rejected": -13.536432266235352,
+      "logps/chosen": -348.41888427734375,
+      "logps/rejected": -399.24371337890625,
+      "loss": 0.5585,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.8608742952346802,
+      "rewards/margins": 0.3582659065723419,
+      "rewards/rejected": -1.2191402912139893,
+      "step": 430
+    },
+    {
+      "epoch": 0.46061240512954726,
+      "grad_norm": 28.78489077603455,
+      "learning_rate": 1.3076253570301408e-07,
+      "logits/chosen": -13.883230209350586,
+      "logits/rejected": -13.993196487426758,
+      "logps/chosen": -349.2350769042969,
+      "logps/rejected": -374.9832763671875,
+      "loss": 0.5542,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7180451154708862,
+      "rewards/margins": 0.41989952325820923,
+      "rewards/rejected": -1.1379445791244507,
+      "step": 440
+    },
+    {
+      "epoch": 0.4710808688824915,
+      "grad_norm": 18.20248083655786,
+      "learning_rate": 1.2726282279726786e-07,
+      "logits/chosen": -14.505528450012207,
+      "logits/rejected": -14.693391799926758,
+      "logps/chosen": -330.843017578125,
+      "logps/rejected": -396.43011474609375,
+      "loss": 0.5424,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.5095499157905579,
+      "rewards/margins": 0.6803628206253052,
+      "rewards/rejected": -1.1899127960205078,
+      "step": 450
+    },
+    {
+      "epoch": 0.48154933263543576,
+      "grad_norm": 16.310384829892065,
+      "learning_rate": 1.2372664828248319e-07,
+      "logits/chosen": -14.17590618133545,
+      "logits/rejected": -14.078557014465332,
+      "logps/chosen": -320.20062255859375,
+      "logps/rejected": -423.71160888671875,
+      "loss": 0.5607,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.4220674932003021,
+      "rewards/margins": 0.6703753471374512,
+      "rewards/rejected": -1.0924427509307861,
+      "step": 460
+    },
+    {
+      "epoch": 0.49201779638838,
+      "grad_norm": 19.430025911116154,
+      "learning_rate": 1.2015874147864312e-07,
+      "logits/chosen": -14.247779846191406,
+      "logits/rejected": -14.570295333862305,
+      "logps/chosen": -338.3775939941406,
+      "logps/rejected": -354.2191467285156,
+      "loss": 0.5134,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.4138456881046295,
+      "rewards/margins": 0.44109171628952026,
+      "rewards/rejected": -0.8549374341964722,
+      "step": 470
+    },
+    {
+      "epoch": 0.5024862601413242,
+      "grad_norm": 17.019933271716724,
+      "learning_rate": 1.1656387414485477e-07,
+      "logits/chosen": -13.82238483428955,
+      "logits/rejected": -13.82000732421875,
+      "logps/chosen": -318.55438232421875,
+      "logps/rejected": -383.9975280761719,
+      "loss": 0.5281,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5111416578292847,
+      "rewards/margins": 0.5328122973442078,
+      "rewards/rejected": -1.0439538955688477,
+      "step": 480
+    },
+    {
+      "epoch": 0.5129547238942685,
+      "grad_norm": 28.874755648357077,
+      "learning_rate": 1.1294685409754433e-07,
+      "logits/chosen": -12.982122421264648,
+      "logits/rejected": -14.110940933227539,
+      "logps/chosen": -390.028076171875,
+      "logps/rejected": -422.0865173339844,
+      "loss": 0.5217,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.47721004486083984,
+      "rewards/margins": 0.8017258644104004,
+      "rewards/rejected": -1.2789360284805298,
+      "step": 490
+    },
+    {
+      "epoch": 0.5234231876472127,
+      "grad_norm": 14.310282443089868,
+      "learning_rate": 1.093125187804288e-07,
+      "logits/chosen": -13.757654190063477,
+      "logits/rejected": -13.917083740234375,
+      "logps/chosen": -368.4084777832031,
+      "logps/rejected": -402.80621337890625,
+      "loss": 0.5441,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.6358953714370728,
+      "rewards/margins": 0.5089365243911743,
+      "rewards/rejected": -1.144831895828247,
+      "step": 500
+    },
+    {
+      "epoch": 0.5234231876472127,
+      "eval_logits/chosen": -14.130770683288574,
+      "eval_logits/rejected": -14.397551536560059,
+      "eval_logps/chosen": -377.0606689453125,
+      "eval_logps/rejected": -405.3188781738281,
+      "eval_loss": 0.5362752676010132,
+      "eval_rewards/accuracies": 0.6679999828338623,
+      "eval_rewards/chosen": -0.6273974180221558,
+      "eval_rewards/margins": 0.5817012786865234,
+      "eval_rewards/rejected": -1.2090985774993896,
+      "eval_runtime": 149.9028,
+      "eval_samples_per_second": 13.342,
+      "eval_steps_per_second": 0.834,
+      "step": 500
+    },
+    {
+      "epoch": 0.533891651400157,
+      "grad_norm": 20.201758093145344,
+      "learning_rate": 1.0566572879486386e-07,
+      "logits/chosen": -13.861791610717773,
+      "logits/rejected": -14.239435195922852,
+      "logps/chosen": -357.29888916015625,
+      "logps/rejected": -406.57366943359375,
+      "loss": 0.5252,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.498563289642334,
+      "rewards/margins": 0.7506011724472046,
+      "rewards/rejected": -1.249164342880249,
+      "step": 510
+    },
+    {
+      "epoch": 0.5443601151531012,
+      "grad_norm": 29.36802681742468,
+      "learning_rate": 1.0201136139922029e-07,
+      "logits/chosen": -14.109712600708008,
+      "logits/rejected": -14.186027526855469,
+      "logps/chosen": -353.62469482421875,
+      "logps/rejected": -370.9365234375,
+      "loss": 0.551,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5417202711105347,
+      "rewards/margins": 0.6182612180709839,
+      "rewards/rejected": -1.1599814891815186,
+      "step": 520
+    },
+    {
+      "epoch": 0.5548285789060455,
+      "grad_norm": 20.995271815473735,
+      "learning_rate": 9.835430398598318e-08,
+      "logits/chosen": -14.159637451171875,
+      "logits/rejected": -14.701879501342773,
+      "logps/chosen": -377.4815979003906,
+      "logps/rejected": -436.66632080078125,
+      "loss": 0.5273,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.3921489119529724,
+      "rewards/margins": 0.8064279556274414,
+      "rewards/rejected": -1.1985770463943481,
+      "step": 530
+    },
+    {
+      "epoch": 0.5652970426589898,
+      "grad_norm": 18.50768834323812,
+      "learning_rate": 9.469944754529784e-08,
+      "logits/chosen": -13.86701488494873,
+      "logits/rejected": -14.368024826049805,
+      "logps/chosen": -343.15997314453125,
+      "logps/rejected": -376.8660583496094,
+      "loss": 0.548,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.6364974975585938,
+      "rewards/margins": 0.5513135194778442,
+      "rewards/rejected": -1.187811017036438,
+      "step": 540
+    },
+    {
+      "epoch": 0.575765506411934,
+      "grad_norm": 21.357543363893058,
+      "learning_rate": 9.105168012370371e-08,
+      "logits/chosen": -13.735044479370117,
+      "logits/rejected": -14.701571464538574,
+      "logps/chosen": -379.26495361328125,
+      "logps/rejected": -371.4606628417969,
+      "loss": 0.5351,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.69088214635849,
+      "rewards/margins": 0.4814137816429138,
+      "rewards/rejected": -1.1722959280014038,
+      "step": 550
+    },
+    {
+      "epoch": 0.5862339701648783,
+      "grad_norm": 30.279493020621196,
+      "learning_rate": 8.741588028680564e-08,
+      "logits/chosen": -14.076385498046875,
+      "logits/rejected": -14.322651863098145,
+      "logps/chosen": -354.1212158203125,
+      "logps/rejected": -378.01654052734375,
+      "loss": 0.538,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.604841411113739,
+      "rewards/margins": 0.5136178135871887,
+      "rewards/rejected": -1.1184592247009277,
+      "step": 560
+    },
+    {
+      "epoch": 0.5967024339178225,
+      "grad_norm": 16.735647281024168,
+      "learning_rate": 8.379691059462476e-08,
+      "logits/chosen": -13.99199104309082,
+      "logits/rejected": -14.157026290893555,
+      "logps/chosen": -374.80938720703125,
+      "logps/rejected": -430.4781799316406,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6314277648925781,
+      "rewards/margins": 0.5574957132339478,
+      "rewards/rejected": -1.1889234781265259,
+      "step": 570
+    },
+    {
+      "epoch": 0.6071708976707668,
+      "grad_norm": 34.538667245559054,
+      "learning_rate": 8.019961109835518e-08,
+      "logits/chosen": -14.209541320800781,
+      "logits/rejected": -14.323854446411133,
+      "logps/chosen": -338.95855712890625,
+      "logps/rejected": -397.41888427734375,
+      "loss": 0.5399,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.6777793765068054,
+      "rewards/margins": 0.6259523630142212,
+      "rewards/rejected": -1.3037316799163818,
+      "step": 580
+    },
+    {
+      "epoch": 0.6176393614237111,
+      "grad_norm": 26.479615574042146,
+      "learning_rate": 7.662879286722496e-08,
+      "logits/chosen": -13.325056076049805,
+      "logits/rejected": -13.995033264160156,
+      "logps/chosen": -348.37322998046875,
+      "logps/rejected": -410.867431640625,
+      "loss": 0.5221,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.5271872282028198,
+      "rewards/margins": 0.7677302360534668,
+      "rewards/rejected": -1.2949175834655762,
+      "step": 590
+    },
+    {
+      "epoch": 0.6281078251766553,
+      "grad_norm": 17.223129668752573,
+      "learning_rate": 7.308923155411709e-08,
+      "logits/chosen": -14.02897834777832,
+      "logits/rejected": -14.710617065429688,
+      "logps/chosen": -403.61224365234375,
+      "logps/rejected": -422.0875549316406,
+      "loss": 0.5125,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.579394519329071,
+      "rewards/margins": 0.6035684943199158,
+      "rewards/rejected": -1.1829631328582764,
+      "step": 600
+    },
+    {
+      "epoch": 0.6281078251766553,
+      "eval_logits/chosen": -14.112022399902344,
+      "eval_logits/rejected": -14.37132453918457,
+      "eval_logps/chosen": -371.89373779296875,
+      "eval_logps/rejected": -401.46051025390625,
+      "eval_loss": 0.5344283580780029,
+      "eval_rewards/accuracies": 0.6840000152587891,
+      "eval_rewards/chosen": -0.5757284164428711,
+      "eval_rewards/margins": 0.5947864651679993,
+      "eval_rewards/rejected": -1.1705149412155151,
+      "eval_runtime": 150.2044,
+      "eval_samples_per_second": 13.315,
+      "eval_steps_per_second": 0.832,
+      "step": 600
+    },
+    {
+      "epoch": 0.6385762889295996,
+      "grad_norm": 15.068671602779133,
+      "learning_rate": 6.958566100855715e-08,
+      "logits/chosen": -13.8591890335083,
+      "logits/rejected": -14.538678169250488,
+      "logps/chosen": -354.1308288574219,
+      "logps/rejected": -361.6885070800781,
+      "loss": 0.535,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.481017529964447,
+      "rewards/margins": 0.7814317941665649,
+      "rewards/rejected": -1.2624493837356567,
+      "step": 610
+    },
+    {
+      "epoch": 0.6490447526825438,
+      "grad_norm": 21.07918728015492,
+      "learning_rate": 6.612276694560927e-08,
+      "logits/chosen": -13.915349006652832,
+      "logits/rejected": -14.466160774230957,
+      "logps/chosen": -403.4571228027344,
+      "logps/rejected": -412.64520263671875,
+      "loss": 0.501,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.5299188494682312,
+      "rewards/margins": 0.7413763999938965,
+      "rewards/rejected": -1.271295189857483,
+      "step": 620
+    },
+    {
+      "epoch": 0.6595132164354881,
+      "grad_norm": 19.103702131187973,
+      "learning_rate": 6.270518067914745e-08,
+      "logits/chosen": -13.852685928344727,
+      "logits/rejected": -14.353567123413086,
+      "logps/chosen": -374.9162902832031,
+      "logps/rejected": -387.75860595703125,
+      "loss": 0.5089,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.5707219243049622,
+      "rewards/margins": 0.6046653389930725,
+      "rewards/rejected": -1.1753873825073242,
+      "step": 630
+    },
+    {
+      "epoch": 0.6699816801884323,
+      "grad_norm": 26.795662212357737,
+      "learning_rate": 5.933747292788368e-08,
+      "logits/chosen": -13.633771896362305,
+      "logits/rejected": -13.929837226867676,
+      "logps/chosen": -328.4835205078125,
+      "logps/rejected": -389.5190734863281,
+      "loss": 0.5141,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.6092640161514282,
+      "rewards/margins": 0.7141542434692383,
+      "rewards/rejected": -1.323418378829956,
+      "step": 640
+    },
+    {
+      "epoch": 0.6804501439413766,
+      "grad_norm": 26.384619321462868,
+      "learning_rate": 5.6024147702436975e-08,
+      "logits/chosen": -13.914807319641113,
+      "logits/rejected": -14.317163467407227,
+      "logps/chosen": -386.0091247558594,
+      "logps/rejected": -435.4970703125,
+      "loss": 0.5178,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.7489283680915833,
+      "rewards/margins": 0.6266080141067505,
+      "rewards/rejected": -1.3755362033843994,
+      "step": 650
+    },
+    {
+      "epoch": 0.6909186076943209,
+      "grad_norm": 32.16033561247209,
+      "learning_rate": 5.276963628161832e-08,
+      "logits/chosen": -13.31103229522705,
+      "logits/rejected": -13.394811630249023,
+      "logps/chosen": -323.6170349121094,
+      "logps/rejected": -388.63958740234375,
+      "loss": 0.5084,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.49584946036338806,
+      "rewards/margins": 0.8416509628295898,
+      "rewards/rejected": -1.3375004529953003,
+      "step": 660
+    },
+    {
+      "epoch": 0.7013870714472651,
+      "grad_norm": 24.949872599196897,
+      "learning_rate": 4.95782912859878e-08,
+      "logits/chosen": -13.573728561401367,
+      "logits/rejected": -13.890779495239258,
+      "logps/chosen": -366.00323486328125,
+      "logps/rejected": -416.9151916503906,
+      "loss": 0.5086,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.6050105094909668,
+      "rewards/margins": 0.8032246828079224,
+      "rewards/rejected": -1.4082351922988892,
+      "step": 670
+    },
+    {
+      "epoch": 0.7118555352002094,
+      "grad_norm": 38.50640287081186,
+      "learning_rate": 4.645438085661084e-08,
+      "logits/chosen": -14.350041389465332,
+      "logits/rejected": -14.588415145874023,
+      "logps/chosen": -355.0298156738281,
+      "logps/rejected": -394.2617492675781,
+      "loss": 0.5374,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.6707770824432373,
+      "rewards/margins": 0.42906999588012695,
+      "rewards/rejected": -1.0998470783233643,
+      "step": 680
+    },
+    {
+      "epoch": 0.7223239989531536,
+      "grad_norm": 24.422507206522518,
+      "learning_rate": 4.340208294679745e-08,
+      "logits/chosen": -13.968500137329102,
+      "logits/rejected": -14.3223876953125,
+      "logps/chosen": -341.5804748535156,
+      "logps/rejected": -367.90045166015625,
+      "loss": 0.5023,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.6214663982391357,
+      "rewards/margins": 0.579698383808136,
+      "rewards/rejected": -1.201164722442627,
+      "step": 690
+    },
+    {
+      "epoch": 0.7327924627060979,
+      "grad_norm": 16.46994924986635,
+      "learning_rate": 4.042547973446017e-08,
+      "logits/chosen": -13.902259826660156,
+      "logits/rejected": -14.259056091308594,
+      "logps/chosen": -358.53607177734375,
+      "logps/rejected": -394.62664794921875,
+      "loss": 0.5158,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6609233617782593,
+      "rewards/margins": 0.5934489369392395,
+      "rewards/rejected": -1.2543723583221436,
+      "step": 700
+    },
+    {
+      "epoch": 0.7327924627060979,
+      "eval_logits/chosen": -14.100985527038574,
+      "eval_logits/rejected": -14.28322696685791,
+      "eval_logps/chosen": -376.5181579589844,
+      "eval_logps/rejected": -407.68670654296875,
+      "eval_loss": 0.5316002368927002,
+      "eval_rewards/accuracies": 0.6759999990463257,
+      "eval_rewards/chosen": -0.6219725012779236,
+      "eval_rewards/margins": 0.610804557800293,
+      "eval_rewards/rejected": -1.2327771186828613,
+      "eval_runtime": 149.412,
+      "eval_samples_per_second": 13.386,
+      "eval_steps_per_second": 0.837,
+      "step": 700
+    },
+    {
+      "epoch": 0.7432609264590422,
+      "grad_norm": 21.302516106563797,
+      "learning_rate": 3.7528552162562855e-08,
+      "logits/chosen": -14.20964527130127,
+      "logits/rejected": -14.762395858764648,
+      "logps/chosen": -352.42864990234375,
+      "logps/rejected": -357.80755615234375,
+      "loss": 0.5624,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6552818417549133,
+      "rewards/margins": 0.563475489616394,
+      "rewards/rejected": -1.2187573909759521,
+      "step": 710
+    },
+    {
+      "epoch": 0.7537293902119864,
+      "grad_norm": 21.028434452167787,
+      "learning_rate": 3.471517461496253e-08,
+      "logits/chosen": -13.895108222961426,
+      "logits/rejected": -14.63810920715332,
+      "logps/chosen": -447.4383850097656,
+      "logps/rejected": -481.58978271484375,
+      "loss": 0.5124,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.5006210207939148,
+      "rewards/margins": 0.9197198152542114,
+      "rewards/rejected": -1.420340895652771,
+      "step": 720
+    },
+    {
+      "epoch": 0.7641978539649307,
+      "grad_norm": 14.730020567879517,
+      "learning_rate": 3.198910973476393e-08,
+      "logits/chosen": -13.825230598449707,
+      "logits/rejected": -14.049738883972168,
+      "logps/chosen": -334.89404296875,
+      "logps/rejected": -387.7596740722656,
+      "loss": 0.5295,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.5604512691497803,
+      "rewards/margins": 0.7153105735778809,
+      "rewards/rejected": -1.2757618427276611,
+      "step": 730
+    },
+    {
+      "epoch": 0.7746663177178749,
+      "grad_norm": 24.660611283550825,
+      "learning_rate": 2.935400339211841e-08,
+      "logits/chosen": -13.387316703796387,
+      "logits/rejected": -14.199974060058594,
+      "logps/chosen": -387.7333068847656,
+      "logps/rejected": -383.7166748046875,
+      "loss": 0.5282,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6691089868545532,
+      "rewards/margins": 0.6580344438552856,
+      "rewards/rejected": -1.3271434307098389,
+      "step": 740
+    },
+    {
+      "epoch": 0.7851347814708192,
+      "grad_norm": 13.767843648079221,
+      "learning_rate": 2.6813379808195357e-08,
+      "logits/chosen": -14.288251876831055,
+      "logits/rejected": -14.359420776367188,
+      "logps/chosen": -339.8260498046875,
+      "logps/rejected": -450.6610412597656,
+      "loss": 0.509,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.5569700598716736,
+      "rewards/margins": 0.9691677093505859,
+      "rewards/rejected": -1.5261377096176147,
+      "step": 750
+    },
+    {
+      "epoch": 0.7956032452237635,
+      "grad_norm": 25.07672836114235,
+      "learning_rate": 2.4370636841848924e-08,
+      "logits/chosen": -13.93481159210205,
+      "logits/rejected": -14.752789497375488,
+      "logps/chosen": -405.8631286621094,
+      "logps/rejected": -400.44769287109375,
+      "loss": 0.5268,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.7553908228874207,
+      "rewards/margins": 0.6457816958427429,
+      "rewards/rejected": -1.401172399520874,
+      "step": 760
+    },
+    {
+      "epoch": 0.8060717089767077,
+      "grad_norm": 23.918260657300134,
+      "learning_rate": 2.202904144528295e-08,
+      "logits/chosen": -14.572360038757324,
+      "logits/rejected": -14.208137512207031,
+      "logps/chosen": -367.49468994140625,
+      "logps/rejected": -460.3101501464844,
+      "loss": 0.5074,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.5758759379386902,
+      "rewards/margins": 0.6287983655929565,
+      "rewards/rejected": -1.204674243927002,
+      "step": 770
+    },
+    {
+      "epoch": 0.816540172729652,
+      "grad_norm": 17.468797083009278,
+      "learning_rate": 1.9791725294791928e-08,
+      "logits/chosen": -13.938896179199219,
+      "logits/rejected": -14.410066604614258,
+      "logps/chosen": -356.8143615722656,
+      "logps/rejected": -365.7565612792969,
+      "loss": 0.5266,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4405798017978668,
+      "rewards/margins": 0.6074010133743286,
+      "rewards/rejected": -1.047980785369873,
+      "step": 780
+    },
+    {
+      "epoch": 0.8270086364825961,
+      "grad_norm": 25.443458513615624,
+      "learning_rate": 1.766168060242159e-08,
+      "logits/chosen": -14.38599681854248,
+      "logits/rejected": -14.689620971679688,
+      "logps/chosen": -313.2379455566406,
+      "logps/rejected": -354.0423889160156,
+      "loss": 0.5395,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.5758354663848877,
+      "rewards/margins": 0.5628177523612976,
+      "rewards/rejected": -1.1386531591415405,
+      "step": 790
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "grad_norm": 16.137468651826794,
+      "learning_rate": 1.564175611415055e-08,
+      "logits/chosen": -13.394170761108398,
+      "logits/rejected": -13.763336181640625,
+      "logps/chosen": -310.41693115234375,
+      "logps/rejected": -387.755615234375,
+      "loss": 0.5133,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.5183297991752625,
+      "rewards/margins": 0.797841489315033,
+      "rewards/rejected": -1.316171407699585,
+      "step": 800
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "eval_logits/chosen": -14.09082317352295,
+      "eval_logits/rejected": -14.274714469909668,
+      "eval_logps/chosen": -376.9043273925781,
+      "eval_logps/rejected": -408.9254150390625,
+      "eval_loss": 0.527787446975708,
+      "eval_rewards/accuracies": 0.6800000071525574,
+      "eval_rewards/chosen": -0.6258336901664734,
+      "eval_rewards/margins": 0.6193299293518066,
+      "eval_rewards/rejected": -1.2451636791229248,
+      "eval_runtime": 149.3494,
+      "eval_samples_per_second": 13.391,
+      "eval_steps_per_second": 0.837,
+      "step": 800
+    },
+    {
+      "epoch": 0.8479455639884846,
+      "grad_norm": 22.038018685540855,
+      "learning_rate": 1.3734653299944831e-08,
+      "logits/chosen": -13.653346061706543,
+      "logits/rejected": -14.236944198608398,
+      "logps/chosen": -420.22412109375,
+      "logps/rejected": -421.231201171875,
+      "loss": 0.532,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.6482435464859009,
+      "rewards/margins": 0.6211605072021484,
+      "rewards/rejected": -1.2694040536880493,
+      "step": 810
+    },
+    {
+      "epoch": 0.8584140277414289,
+      "grad_norm": 25.08502183374406,
+      "learning_rate": 1.1942922740781558e-08,
+      "logits/chosen": -13.920855522155762,
+      "logits/rejected": -14.378143310546875,
+      "logps/chosen": -371.789794921875,
+      "logps/rejected": -409.6880798339844,
+      "loss": 0.5193,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6346549987792969,
+      "rewards/margins": 0.6358563303947449,
+      "rewards/rejected": -1.270511269569397,
+      "step": 820
+    },
+    {
+      "epoch": 0.8688824914943732,
+      "grad_norm": 16.83996659028827,
+      "learning_rate": 1.0268960717472741e-08,
+      "logits/chosen": -14.19860553741455,
+      "logits/rejected": -14.166885375976562,
+      "logps/chosen": -347.3482971191406,
+      "logps/rejected": -415.2900390625,
+      "loss": 0.5355,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.5952852368354797,
+      "rewards/margins": 0.6116087436676025,
+      "rewards/rejected": -1.2068939208984375,
+      "step": 830
+    },
+    {
+      "epoch": 0.8793509552473174,
+      "grad_norm": 16.08177687112279,
+      "learning_rate": 8.715006005852143e-09,
+      "logits/chosen": -14.115530014038086,
+      "logits/rejected": -14.573888778686523,
+      "logps/chosen": -362.61724853515625,
+      "logps/rejected": -457.84942626953125,
+      "loss": 0.4976,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.6578099727630615,
+      "rewards/margins": 0.8440145254135132,
+      "rewards/rejected": -1.5018243789672852,
+      "step": 840
+    },
+    {
+      "epoch": 0.8898194190002617,
+      "grad_norm": 39.033655096711556,
+      "learning_rate": 7.2831368826110625e-09,
+      "logits/chosen": -14.004640579223633,
+      "logits/rejected": -14.758051872253418,
+      "logps/chosen": -382.56427001953125,
+      "logps/rejected": -397.9862365722656,
+      "loss": 0.5084,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.5773628354072571,
+      "rewards/margins": 0.7263933420181274,
+      "rewards/rejected": -1.3037563562393188,
+      "step": 850
+    },
+    {
+      "epoch": 0.9002878827532059,
+      "grad_norm": 19.748822633492768,
+      "learning_rate": 5.975268345787455e-09,
+      "logits/chosen": -13.904319763183594,
+      "logits/rejected": -13.906578063964844,
+      "logps/chosen": -398.3722839355469,
+      "logps/rejected": -399.95306396484375,
+      "loss": 0.5106,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.6384676694869995,
+      "rewards/margins": 0.6380214691162109,
+      "rewards/rejected": -1.276489019393921,
+      "step": 860
+    },
+    {
+      "epoch": 0.9107563465061502,
+      "grad_norm": 59.31572753609887,
+      "learning_rate": 4.793149553625786e-09,
+      "logits/chosen": -14.279424667358398,
+      "logits/rejected": -14.221160888671875,
+      "logps/chosen": -333.5687255859375,
+      "logps/rejected": -372.06304931640625,
+      "loss": 0.5295,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.5818564295768738,
+      "rewards/margins": 0.6132394075393677,
+      "rewards/rejected": -1.1950958967208862,
+      "step": 870
+    },
+    {
+      "epoch": 0.9212248102590945,
+      "grad_norm": 13.400208624148753,
+      "learning_rate": 3.7383614852329214e-09,
+      "logits/chosen": -14.04296588897705,
+      "logits/rejected": -14.601972579956055,
+      "logps/chosen": -374.31024169921875,
+      "logps/rejected": -394.02618408203125,
+      "loss": 0.5216,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.5409375429153442,
+      "rewards/margins": 0.7117520570755005,
+      "rewards/rejected": -1.2526895999908447,
+      "step": 880
+    },
+    {
+      "epoch": 0.9316932740120387,
+      "grad_norm": 23.713770091143388,
+      "learning_rate": 2.812314826158746e-09,
+      "logits/chosen": -13.538187026977539,
+      "logits/rejected": -13.821019172668457,
+      "logps/chosen": -342.670654296875,
+      "logps/rejected": -417.42608642578125,
+      "loss": 0.5146,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.5183156728744507,
+      "rewards/margins": 0.8244325518608093,
+      "rewards/rejected": -1.3427482843399048,
+      "step": 890
+    },
+    {
+      "epoch": 0.942161737764983,
+      "grad_norm": 17.247650815291333,
+      "learning_rate": 2.016248081729144e-09,
+      "logits/chosen": -14.117114067077637,
+      "logits/rejected": -14.199200630187988,
+      "logps/chosen": -360.4630126953125,
+      "logps/rejected": -437.9790954589844,
+      "loss": 0.5098,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.5845374464988708,
+      "rewards/margins": 0.8339082598686218,
+      "rewards/rejected": -1.4184458255767822,
+      "step": 900
+    },
+    {
+      "epoch": 0.942161737764983,
+      "eval_logits/chosen": -14.10096263885498,
+      "eval_logits/rejected": -14.284878730773926,
+      "eval_logps/chosen": -374.75311279296875,
+      "eval_logps/rejected": -407.1072998046875,
+      "eval_loss": 0.5276437997817993,
+      "eval_rewards/accuracies": 0.6959999799728394,
+      "eval_rewards/chosen": -0.6043218970298767,
+      "eval_rewards/margins": 0.6226609349250793,
+      "eval_rewards/rejected": -1.2269827127456665,
+      "eval_runtime": 149.3336,
+      "eval_samples_per_second": 13.393,
+      "eval_steps_per_second": 0.837,
+      "step": 900
+    },
+    {
+      "epoch": 0.9526302015179272,
+      "grad_norm": 38.823289395104936,
+      "learning_rate": 1.3512259206550746e-09,
+      "logits/chosen": -13.173808097839355,
+      "logits/rejected": -14.06005573272705,
+      "logps/chosen": -376.40521240234375,
+      "logps/rejected": -369.52972412109375,
+      "loss": 0.5286,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.6154804229736328,
+      "rewards/margins": 0.589421272277832,
+      "rewards/rejected": -1.2049016952514648,
+      "step": 910
+    },
+    {
+      "epoch": 0.9630986652708715,
+      "grad_norm": 32.054517995284215,
+      "learning_rate": 8.181377511324306e-10,
+      "logits/chosen": -14.00465202331543,
+      "logits/rejected": -14.40130615234375,
+      "logps/chosen": -339.0160217285156,
+      "logps/rejected": -404.2559814453125,
+      "loss": 0.5282,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.569662868976593,
+      "rewards/margins": 0.7953134179115295,
+      "rewards/rejected": -1.3649762868881226,
+      "step": 920
+    },
+    {
+      "epoch": 0.9735671290238157,
+      "grad_norm": 24.37374985565681,
+      "learning_rate": 4.1769653133743035e-10,
+      "logits/chosen": -14.06200885772705,
+      "logits/rejected": -14.65931510925293,
+      "logps/chosen": -348.43487548828125,
+      "logps/rejected": -376.7773132324219,
+      "loss": 0.4989,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.5918719172477722,
+      "rewards/margins": 0.6253038644790649,
+      "rewards/rejected": -1.2171757221221924,
+      "step": 930
+    },
+    {
+      "epoch": 0.98403559277676,
+      "grad_norm": 17.872968337546382,
+      "learning_rate": 1.5043781590823313e-10,
+      "logits/chosen": -14.47838020324707,
+      "logits/rejected": -14.449295043945312,
+      "logps/chosen": -370.87957763671875,
+      "logps/rejected": -464.7237243652344,
+      "loss": 0.5148,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.6222177743911743,
+      "rewards/margins": 0.7162548899650574,
+      "rewards/rejected": -1.338472604751587,
+      "step": 940
+    },
+    {
+      "epoch": 0.9945040565297043,
+      "grad_norm": 22.704537546218425,
+      "learning_rate": 1.671903968816224e-11,
+      "logits/chosen": -13.458340644836426,
+      "logits/rejected": -13.864636421203613,
+      "logps/chosen": -367.2121276855469,
+      "logps/rejected": -387.31488037109375,
+      "loss": 0.5191,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6486170887947083,
+      "rewards/margins": 0.6029497385025024,
+      "rewards/rejected": -1.2515666484832764,
+      "step": 950
+    },
+    {
+      "epoch": 0.9997382884061764,
+      "step": 955,
+      "total_flos": 0.0,
+      "train_loss": 0.560625178402007,
+      "train_runtime": 12630.0326,
+      "train_samples_per_second": 4.84,
+      "train_steps_per_second": 0.076
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 955,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15571656f4381d00eb1d2a9ac9ba192287d16a2477fd5527cd82bc888c82d28f
+size 7544