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_2_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_2_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": 0.5574049902897255,
+    "train_runtime": 23264.0366,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.86,
+    "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 sha256:2cc6a9b8219b4a37cd0be50f2c86ba42f6808045a410aa27f7a8840dda6337be
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fadda4202ba082eb1d2b4cf9f4efe17702b9641bd0352ea104b261979ae4730a
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6052d324996eabc51ad4110ea5224d87e7842ccb3f0f7dd77e7b5d7691d5a230
+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": 0.5574049902897255,
+    "train_runtime": 23264.0366,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.86,
+    "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": 0.20925004399681482,
+      "learning_rate": 3.125e-08,
+      "logits/chosen": -1.6728180646896362,
+      "logits/rejected": -1.6728180646896362,
+      "logps/chosen": -139.26568603515625,
+      "logps/pi_response": -223.70187377929688,
+      "logps/ref_response": -223.70187377929688,
+      "logps/rejected": -139.26568603515625,
+      "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": 0.2664449122199502,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -1.9198987483978271,
+      "logits/rejected": -1.9198987483978271,
+      "logps/chosen": -185.7984161376953,
+      "logps/pi_response": -284.7489929199219,
+      "logps/ref_response": -274.8498229980469,
+      "logps/rejected": -185.7984161376953,
+      "loss": 0.693,
+      "rewards/accuracies": 0.09829059988260269,
+      "rewards/chosen": -0.05739467218518257,
+      "rewards/margins": -8.19944467878031e-09,
+      "rewards/rejected": -0.057394664734601974,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.17607425906899,
+      "learning_rate": 4.989490450759331e-07,
+      "logits/chosen": -1.2133342027664185,
+      "logits/rejected": -1.2133342027664185,
+      "logps/chosen": -344.1175231933594,
+      "logps/pi_response": -420.7164001464844,
+      "logps/ref_response": -268.8954772949219,
+      "logps/rejected": -344.1175231933594,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.17307692766189575,
+      "rewards/chosen": -1.5597572326660156,
+      "rewards/margins": 2.3523059056174134e-08,
+      "rewards/rejected": -1.5597573518753052,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9959359173659126,
+      "learning_rate": 4.872270441827174e-07,
+      "logits/chosen": 0.10036426037549973,
+      "logits/rejected": 0.10036426037549973,
+      "logps/chosen": -764.1023559570312,
+      "logps/pi_response": -850.1804809570312,
+      "logps/ref_response": -272.0489807128906,
+      "logps/rejected": -764.1023559570312,
+      "loss": 0.6873,
+      "rewards/accuracies": 0.11153846234083176,
+      "rewards/chosen": -5.858819007873535,
+      "rewards/margins": -3.943076620771535e-08,
+      "rewards/rejected": -5.858819484710693,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 1.9030553381279938,
+      "learning_rate": 4.6308512113530063e-07,
+      "logits/chosen": 2.6020889282226562,
+      "logits/rejected": 2.6020889282226562,
+      "logps/chosen": -15368.376953125,
+      "logps/pi_response": -9728.86328125,
+      "logps/ref_response": -275.9498596191406,
+      "logps/rejected": -15368.376953125,
+      "loss": 0.6,
+      "rewards/accuracies": 0.042307693511247635,
+      "rewards/chosen": -151.69932556152344,
+      "rewards/margins": 1.8339891028062993e-07,
+      "rewards/rejected": -151.69932556152344,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9022013856679871,
+      "learning_rate": 4.277872161641681e-07,
+      "logits/chosen": 5.100710391998291,
+      "logits/rejected": 5.100710391998291,
+      "logps/chosen": -25452.970703125,
+      "logps/pi_response": -16005.287109375,
+      "logps/ref_response": -266.91033935546875,
+      "logps/rejected": -25452.970703125,
+      "loss": 0.5304,
+      "rewards/accuracies": 0.023076923564076424,
+      "rewards/chosen": -252.7429656982422,
+      "rewards/margins": -4.69501202360334e-07,
+      "rewards/rejected": -252.7429656982422,
+      "step": 50
+    },
+    {
+      "epoch": 0.39,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9078413895498612,
+      "learning_rate": 3.8318133624280046e-07,
+      "logits/chosen": 4.621513843536377,
+      "logits/rejected": 4.621513843536377,
+      "logps/chosen": -29423.666015625,
+      "logps/pi_response": -17608.6015625,
+      "logps/ref_response": -265.94757080078125,
+      "logps/rejected": -29423.666015625,
+      "loss": 0.519,
+      "rewards/accuracies": 0.03076923079788685,
+      "rewards/chosen": -292.3346862792969,
+      "rewards/margins": 6.455641710090276e-07,
+      "rewards/rejected": -292.3346862792969,
+      "step": 60
+    },
+    {
+      "epoch": 0.46,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.7756777568132545,
+      "learning_rate": 3.316028034595861e-07,
+      "logits/chosen": 4.356642723083496,
+      "logits/rejected": 4.356642723083496,
+      "logps/chosen": -29171.62890625,
+      "logps/pi_response": -18937.943359375,
+      "logps/ref_response": -276.5423278808594,
+      "logps/rejected": -29171.62890625,
+      "loss": 0.5212,
+      "rewards/accuracies": 0.015384615398943424,
+      "rewards/chosen": -289.7953796386719,
+      "rewards/margins": 0.0,
+      "rewards/rejected": -289.7953796386719,
+      "step": 70
+    },
+    {
+      "epoch": 0.52,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9174650913563618,
+      "learning_rate": 2.7575199021178855e-07,
+      "logits/chosen": 4.428848743438721,
+      "logits/rejected": 4.428848743438721,
+      "logps/chosen": -27704.791015625,
+      "logps/pi_response": -18176.86328125,
+      "logps/ref_response": -271.93060302734375,
+      "logps/rejected": -27704.791015625,
+      "loss": 0.5132,
+      "rewards/accuracies": 0.01923076994717121,
+      "rewards/chosen": -275.2251281738281,
+      "rewards/margins": -9.97690108306415e-07,
+      "rewards/rejected": -275.2251281738281,
+      "step": 80
+    },
+    {
+      "epoch": 0.58,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9019855937057101,
+      "learning_rate": 2.1855294234408068e-07,
+      "logits/chosen": 4.3772735595703125,
+      "logits/rejected": 4.3772735595703125,
+      "logps/chosen": -29193.177734375,
+      "logps/pi_response": -17440.9921875,
+      "logps/ref_response": -266.1241455078125,
+      "logps/rejected": -29193.177734375,
+      "loss": 0.5231,
+      "rewards/accuracies": 0.03076923079788685,
+      "rewards/chosen": -290.08026123046875,
+      "rewards/margins": -2.9343825147520874e-08,
+      "rewards/rejected": -290.0802307128906,
+      "step": 90
+    },
+    {
+      "epoch": 0.65,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.8179873354250534,
+      "learning_rate": 1.6300029195778453e-07,
+      "logits/chosen": 4.375646114349365,
+      "logits/rejected": 4.375646114349365,
+      "logps/chosen": -27328.33203125,
+      "logps/pi_response": -17462.0546875,
+      "logps/ref_response": -267.173828125,
+      "logps/rejected": -27328.33203125,
+      "loss": 0.5171,
+      "rewards/accuracies": 0.026923077180981636,
+      "rewards/chosen": -271.51708984375,
+      "rewards/margins": 1.613910427522569e-07,
+      "rewards/rejected": -271.51708984375,
+      "step": 100
+    },
+    {
+      "epoch": 0.71,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9895798769556228,
+      "learning_rate": 1.1200247470632392e-07,
+      "logits/chosen": 4.529591083526611,
+      "logits/rejected": 4.529591083526611,
+      "logps/chosen": -28326.220703125,
+      "logps/pi_response": -18734.5078125,
+      "logps/ref_response": -291.685791015625,
+      "logps/rejected": -28326.220703125,
+      "loss": 0.5103,
+      "rewards/accuracies": 0.04615384712815285,
+      "rewards/chosen": -281.44744873046875,
+      "rewards/margins": 1.540550869094659e-07,
+      "rewards/rejected": -281.44744873046875,
+      "step": 110
+    },
+    {
+      "epoch": 0.78,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.9157342554933109,
+      "learning_rate": 6.822945986946385e-08,
+      "logits/chosen": 4.574192523956299,
+      "logits/rejected": 4.574192523956299,
+      "logps/chosen": -29500.658203125,
+      "logps/pi_response": -18083.599609375,
+      "logps/ref_response": -266.3084716796875,
+      "logps/rejected": -29500.658203125,
+      "loss": 0.5148,
+      "rewards/accuracies": 0.05384615436196327,
+      "rewards/chosen": -293.0876159667969,
+      "rewards/margins": 1.4085036355027114e-06,
+      "rewards/rejected": -293.0876159667969,
+      "step": 120
+    },
+    {
+      "epoch": 0.84,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.932891201307216,
+      "learning_rate": 3.397296523427806e-08,
+      "logits/chosen": 4.706723213195801,
+      "logits/rejected": 4.706723213195801,
+      "logps/chosen": -26521.8828125,
+      "logps/pi_response": -15752.3818359375,
+      "logps/ref_response": -260.1748046875,
+      "logps/rejected": -26521.884765625,
+      "loss": 0.5218,
+      "rewards/accuracies": 0.04615384712815285,
+      "rewards/chosen": -263.5008544921875,
+      "rewards/margins": 8.876506853994215e-07,
+      "rewards/rejected": -263.5008544921875,
+      "step": 130
+    },
+    {
+      "epoch": 0.91,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.7630353244282155,
+      "learning_rate": 1.1026475173977978e-08,
+      "logits/chosen": 4.662195205688477,
+      "logits/rejected": 4.662195205688477,
+      "logps/chosen": -29146.107421875,
+      "logps/pi_response": -18217.185546875,
+      "logps/ref_response": -266.84295654296875,
+      "logps/rejected": -29146.107421875,
+      "loss": 0.5144,
+      "rewards/accuracies": 0.03846153989434242,
+      "rewards/chosen": -289.6330261230469,
+      "rewards/margins": 5.868765029504175e-08,
+      "rewards/rejected": -289.6330261230469,
+      "step": 140
+    },
+    {
+      "epoch": 0.97,
+      "eta": 0.0010000000474974513,
+      "grad_norm": 0.7944892762549526,
+      "learning_rate": 5.913435276374834e-10,
+      "logits/chosen": 4.59439754486084,
+      "logits/rejected": 4.59439754486084,
+      "logps/chosen": -28846.330078125,
+      "logps/pi_response": -18351.314453125,
+      "logps/ref_response": -276.857666015625,
+      "logps/rejected": -28846.330078125,
+      "loss": 0.5191,
+      "rewards/accuracies": 0.03846153989434242,
+      "rewards/chosen": -286.6873779296875,
+      "rewards/margins": -8.803147579783399e-07,
+      "rewards/rejected": -286.6873779296875,
+      "step": 150
+    },
+    {
+      "epoch": 0.99,
+      "step": 153,
+      "total_flos": 0.0,
+      "train_loss": 0.5574049902897255,
+      "train_runtime": 23264.0366,
+      "train_samples_per_second": 0.86,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}