Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: YYYYYYibo/full_vanilla_dpo_iter_1
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: two_agent_1_rdpo_iter_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. -->
+
+# two_agent_1_rdpo_iter_2
+
+This model is a fine-tuned version of [YYYYYYibo/full_vanilla_dpo_iter_1](https://huggingface.co/YYYYYYibo/full_vanilla_dpo_iter_1) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 5
+- gradient_accumulation_steps: 13
+- total_train_batch_size: 130
+- total_eval_batch_size: 10
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.687004194540136,
+    "train_runtime": 23329.5349,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.857,
+    "train_steps_per_second": 0.007
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b993db584c8d1aeccf495de810931d74c5bc1654b4c073012920b6ca62390654
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9520e8dd2eda1073efc0c9f24448a729d1f00b24f16347247a7129306a7a0c74
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1ab2a7201f13771780963a478823c656945794a3a0d7455ea171969a392cc5
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.687004194540136,
+    "train_runtime": 23329.5349,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.857,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,318 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9945,
+  "eval_steps": 500,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 14.745374712777657,
+      "learning_rate": 3.125e-08,
+      "logits/chosen": -1.480354905128479,
+      "logits/rejected": -1.5607078075408936,
+      "logps/chosen": -113.47530364990234,
+      "logps/pi_response": -223.8134002685547,
+      "logps/ref_response": -223.8134002685547,
+      "logps/rejected": -112.02357482910156,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "eta": 0.0009999999310821295,
+      "grad_norm": 13.943252568407653,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -1.861205816268921,
+      "logits/rejected": -1.8467286825180054,
+      "logps/chosen": -159.73291015625,
+      "logps/pi_response": -273.9164733886719,
+      "logps/ref_response": -273.0810852050781,
+      "logps/rejected": -158.10842895507812,
+      "loss": 0.693,
+      "rewards/accuracies": 0.46581196784973145,
+      "rewards/chosen": -0.0030446185264736414,
+      "rewards/margins": 0.0008683722116984427,
+      "rewards/rejected": -0.003912990912795067,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 14.636770074330482,
+      "learning_rate": 4.989490450759331e-07,
+      "logits/chosen": -1.6749669313430786,
+      "logits/rejected": -1.6249001026153564,
+      "logps/chosen": -181.44686889648438,
+      "logps/pi_response": -299.26806640625,
+      "logps/ref_response": -269.5531921386719,
+      "logps/rejected": -184.55027770996094,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5461538434028625,
+      "rewards/chosen": -0.15622131526470184,
+      "rewards/margins": 0.010419250465929508,
+      "rewards/rejected": -0.16664059460163116,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 18.84883262757341,
+      "learning_rate": 4.872270441827174e-07,
+      "logits/chosen": -1.5554673671722412,
+      "logits/rejected": -1.4832121133804321,
+      "logps/chosen": -187.2523956298828,
+      "logps/pi_response": -331.72064208984375,
+      "logps/ref_response": -270.0771484375,
+      "logps/rejected": -184.25772094726562,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4961538314819336,
+      "rewards/chosen": -0.3374003469944,
+      "rewards/margins": 0.01481544878333807,
+      "rewards/rejected": -0.35221579670906067,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 19.234325247102298,
+      "learning_rate": 4.6308512113530063e-07,
+      "logits/chosen": -1.6449016332626343,
+      "logits/rejected": -1.708786129951477,
+      "logps/chosen": -188.21363830566406,
+      "logps/pi_response": -333.604736328125,
+      "logps/ref_response": -275.1395263671875,
+      "logps/rejected": -197.63232421875,
+      "loss": 0.6861,
+      "rewards/accuracies": 0.5269230604171753,
+      "rewards/chosen": -0.23007477819919586,
+      "rewards/margins": 0.013713112100958824,
+      "rewards/rejected": -0.24378788471221924,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 17.138306112556428,
+      "learning_rate": 4.277872161641681e-07,
+      "logits/chosen": -1.726422667503357,
+      "logits/rejected": -1.659047245979309,
+      "logps/chosen": -173.61680603027344,
+      "logps/pi_response": -315.35235595703125,
+      "logps/ref_response": -265.1530456542969,
+      "logps/rejected": -175.0764617919922,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.5461538434028625,
+      "rewards/chosen": -0.1452452391386032,
+      "rewards/margins": 0.029706543311476707,
+      "rewards/rejected": -0.17495179176330566,
+      "step": 50
+    },
+    {
+      "epoch": 0.39,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 15.457021507203054,
+      "learning_rate": 3.8318133624280046e-07,
+      "logits/chosen": -1.712626338005066,
+      "logits/rejected": -1.722040057182312,
+      "logps/chosen": -179.5359649658203,
+      "logps/pi_response": -311.54986572265625,
+      "logps/ref_response": -265.8667907714844,
+      "logps/rejected": -191.751708984375,
+      "loss": 0.6849,
+      "rewards/accuracies": 0.5653846263885498,
+      "rewards/chosen": -0.16358985006809235,
+      "rewards/margins": 0.03767317533493042,
+      "rewards/rejected": -0.20126302540302277,
+      "step": 60
+    },
+    {
+      "epoch": 0.46,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 25.055768196503276,
+      "learning_rate": 3.316028034595861e-07,
+      "logits/chosen": -1.7020467519760132,
+      "logits/rejected": -1.7025904655456543,
+      "logps/chosen": -185.90699768066406,
+      "logps/pi_response": -315.3182067871094,
+      "logps/ref_response": -276.3799743652344,
+      "logps/rejected": -189.57199096679688,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.5076923370361328,
+      "rewards/chosen": -0.18907414376735687,
+      "rewards/margins": -0.0005933608626946807,
+      "rewards/rejected": -0.18848079442977905,
+      "step": 70
+    },
+    {
+      "epoch": 0.52,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 20.33794636752797,
+      "learning_rate": 2.7575199021178855e-07,
+      "logits/chosen": -1.3984944820404053,
+      "logits/rejected": -1.3162914514541626,
+      "logps/chosen": -193.8706817626953,
+      "logps/pi_response": -336.3244323730469,
+      "logps/ref_response": -272.45025634765625,
+      "logps/rejected": -203.4906005859375,
+      "loss": 0.6834,
+      "rewards/accuracies": 0.5692307949066162,
+      "rewards/chosen": -0.31467124819755554,
+      "rewards/margins": 0.06254380196332932,
+      "rewards/rejected": -0.37721511721611023,
+      "step": 80
+    },
+    {
+      "epoch": 0.58,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 17.59187813851558,
+      "learning_rate": 2.1855294234408068e-07,
+      "logits/chosen": -1.2510021924972534,
+      "logits/rejected": -1.2377079725265503,
+      "logps/chosen": -209.71649169921875,
+      "logps/pi_response": -354.3184509277344,
+      "logps/ref_response": -265.3123474121094,
+      "logps/rejected": -218.32000732421875,
+      "loss": 0.686,
+      "rewards/accuracies": 0.5538461804389954,
+      "rewards/chosen": -0.5378236770629883,
+      "rewards/margins": 0.04319743812084198,
+      "rewards/rejected": -0.5810210704803467,
+      "step": 90
+    },
+    {
+      "epoch": 0.65,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 15.830895593862458,
+      "learning_rate": 1.6300029195778453e-07,
+      "logits/chosen": -1.2602006196975708,
+      "logits/rejected": -1.3293911218643188,
+      "logps/chosen": -204.08714294433594,
+      "logps/pi_response": -333.2199401855469,
+      "logps/ref_response": -267.4874572753906,
+      "logps/rejected": -209.34811401367188,
+      "loss": 0.6896,
+      "rewards/accuracies": 0.5269230604171753,
+      "rewards/chosen": -0.438109815120697,
+      "rewards/margins": 0.006122402846813202,
+      "rewards/rejected": -0.44423219561576843,
+      "step": 100
+    },
+    {
+      "epoch": 0.71,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 16.101030751126824,
+      "learning_rate": 1.1200247470632392e-07,
+      "logits/chosen": -1.4597405195236206,
+      "logits/rejected": -1.4979974031448364,
+      "logps/chosen": -195.9895782470703,
+      "logps/pi_response": -342.63812255859375,
+      "logps/ref_response": -289.2621765136719,
+      "logps/rejected": -196.60757446289062,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5307692289352417,
+      "rewards/chosen": -0.37045371532440186,
+      "rewards/margins": 0.006542083341628313,
+      "rewards/rejected": -0.3769958019256592,
+      "step": 110
+    },
+    {
+      "epoch": 0.78,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 14.757730514557847,
+      "learning_rate": 6.822945986946385e-08,
+      "logits/chosen": -1.2902206182479858,
+      "logits/rejected": -1.3999152183532715,
+      "logps/chosen": -195.00039672851562,
+      "logps/pi_response": -312.9175720214844,
+      "logps/ref_response": -265.36669921875,
+      "logps/rejected": -204.87124633789062,
+      "loss": 0.6806,
+      "rewards/accuracies": 0.6153846383094788,
+      "rewards/chosen": -0.32740989327430725,
+      "rewards/margins": 0.04114748165011406,
+      "rewards/rejected": -0.368557333946228,
+      "step": 120
+    },
+    {
+      "epoch": 0.84,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 15.906731544868482,
+      "learning_rate": 3.397296523427806e-08,
+      "logits/chosen": -1.066477656364441,
+      "logits/rejected": -1.102446436882019,
+      "logps/chosen": -194.1769561767578,
+      "logps/pi_response": -325.8312683105469,
+      "logps/ref_response": -258.591552734375,
+      "logps/rejected": -202.23509216308594,
+      "loss": 0.682,
+      "rewards/accuracies": 0.5153846144676208,
+      "rewards/chosen": -0.433013916015625,
+      "rewards/margins": 0.026987465098500252,
+      "rewards/rejected": -0.4600013792514801,
+      "step": 130
+    },
+    {
+      "epoch": 0.91,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 14.158010485809152,
+      "learning_rate": 1.1026475173977978e-08,
+      "logits/chosen": -1.430467963218689,
+      "logits/rejected": -1.3737958669662476,
+      "logps/chosen": -206.46617126464844,
+      "logps/pi_response": -334.0456848144531,
+      "logps/ref_response": -264.9248352050781,
+      "logps/rejected": -205.56634521484375,
+      "loss": 0.6856,
+      "rewards/accuracies": 0.5269230604171753,
+      "rewards/chosen": -0.42677730321884155,
+      "rewards/margins": 0.021916242316365242,
+      "rewards/rejected": -0.44869354367256165,
+      "step": 140
+    },
+    {
+      "epoch": 0.97,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 15.33322379707595,
+      "learning_rate": 5.913435276374834e-10,
+      "logits/chosen": -1.2695854902267456,
+      "logits/rejected": -1.342061996459961,
+      "logps/chosen": -197.76773071289062,
+      "logps/pi_response": -341.5782165527344,
+      "logps/ref_response": -275.605224609375,
+      "logps/rejected": -205.83673095703125,
+      "loss": 0.681,
+      "rewards/accuracies": 0.5730769038200378,
+      "rewards/chosen": -0.42948493361473083,
+      "rewards/margins": 0.03518623486161232,
+      "rewards/rejected": -0.46467119455337524,
+      "step": 150
+    },
+    {
+      "epoch": 0.99,
+      "step": 153,
+      "total_flos": 0.0,
+      "train_loss": 0.687004194540136,
+      "train_runtime": 23329.5349,
+      "train_samples_per_second": 0.857,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}