Update from wang5617

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- AmberYifan/SPIN-trans-DPOformat
+model-index:
+- name: zephyr-simpo-data-zephyr
+  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. -->
+
+# zephyr-simpo-data-zephyr
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the AmberYifan/SPIN-trans-DPOformat 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- 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 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9929622520793346,
+    "eval_logits/chosen": -3.004377603530884,
+    "eval_logits/rejected": -2.9803078174591064,
+    "eval_logps/chosen": -2.1619315147399902,
+    "eval_logps/rejected": -10.050172805786133,
+    "eval_loss": 2.3342242627677479e-07,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -5.404829502105713,
+    "eval_rewards/margins": 19.72060203552246,
+    "eval_rewards/rejected": -25.125431060791016,
+    "eval_runtime": 337.3765,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 14.82,
+    "eval_steps_per_second": 0.465,
+    "total_flos": 0.0,
+    "train_loss": 0.016540080016594853,
+    "train_runtime": 11118.1076,
+    "train_samples": 50000,
+    "train_samples_per_second": 4.497,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9929622520793346,
+    "eval_logits/chosen": -3.004377603530884,
+    "eval_logits/rejected": -2.9803078174591064,
+    "eval_logps/chosen": -2.1619315147399902,
+    "eval_logps/rejected": -10.050172805786133,
+    "eval_loss": 2.3342242627677479e-07,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -5.404829502105713,
+    "eval_rewards/margins": 19.72060203552246,
+    "eval_rewards/rejected": -25.125431060791016,
+    "eval_runtime": 337.3765,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 14.82,
+    "eval_steps_per_second": 0.465
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c532c83ac1f65d98a2f7b26f537c26f8fdf11b48e4b982a64eb4e90233854a3b
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e013955468893a2257d2653c2497a8c38c606967f29215b53f8accbcf9a4e3a3
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d18bb12d87334f10614cc94d18f2e241d395813e3ebab8058e533e997615cc
+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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9929622520793346,
+    "total_flos": 0.0,
+    "train_loss": 0.016540080016594853,
+    "train_runtime": 11118.1076,
+    "train_samples": 50000,
+    "train_samples_per_second": 4.497,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,327 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9929622520793346,
+  "eval_steps": 500,
+  "global_step": 97,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05118362124120281,
+      "grad_norm": 142.04534883137924,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": -3.121891498565674,
+      "logits/rejected": -3.0059380531311035,
+      "logps/chosen": -1.436647653579712,
+      "logps/rejected": -2.13486909866333,
+      "loss": 0.263,
+      "rewards/accuracies": 0.9781249761581421,
+      "rewards/chosen": -3.5916194915771484,
+      "rewards/margins": 1.7455530166625977,
+      "rewards/rejected": -5.337172508239746,
+      "step": 5
+    },
+    {
+      "epoch": 0.10236724248240563,
+      "grad_norm": 8.928774478177914,
+      "learning_rate": 5e-07,
+      "logits/chosen": -3.1206612586975098,
+      "logits/rejected": -3.020460844039917,
+      "logps/chosen": -1.482598066329956,
+      "logps/rejected": -3.0258779525756836,
+      "loss": 0.0557,
+      "rewards/accuracies": 0.9984375238418579,
+      "rewards/chosen": -3.7064952850341797,
+      "rewards/margins": 3.8581995964050293,
+      "rewards/rejected": -7.564694881439209,
+      "step": 10
+    },
+    {
+      "epoch": 0.15355086372360843,
+      "grad_norm": 0.011898667770509092,
+      "learning_rate": 4.959362109830006e-07,
+      "logits/chosen": -3.10644793510437,
+      "logits/rejected": -3.03446102142334,
+      "logps/chosen": -1.575461983680725,
+      "logps/rejected": -5.494174003601074,
+      "loss": 0.0004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.938655138015747,
+      "rewards/margins": 9.796780586242676,
+      "rewards/rejected": -13.735437393188477,
+      "step": 15
+    },
+    {
+      "epoch": 0.20473448496481125,
+      "grad_norm": 0.02098359966143572,
+      "learning_rate": 4.838769589814002e-07,
+      "logits/chosen": -3.0926451683044434,
+      "logits/rejected": -3.0563385486602783,
+      "logps/chosen": -1.6248165369033813,
+      "logps/rejected": -6.373618125915527,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.062041759490967,
+      "rewards/margins": 11.872003555297852,
+      "rewards/rejected": -15.934043884277344,
+      "step": 20
+    },
+    {
+      "epoch": 0.2559181062060141,
+      "grad_norm": 0.0019588953751018155,
+      "learning_rate": 4.642142940418973e-07,
+      "logits/chosen": -3.0899291038513184,
+      "logits/rejected": -3.0629467964172363,
+      "logps/chosen": -1.6836541891098022,
+      "logps/rejected": -7.282121181488037,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.209136009216309,
+      "rewards/margins": 13.996167182922363,
+      "rewards/rejected": -18.205303192138672,
+      "step": 25
+    },
+    {
+      "epoch": 0.30710172744721687,
+      "grad_norm": 0.0011161418830464636,
+      "learning_rate": 4.375874555391006e-07,
+      "logits/chosen": -3.0745973587036133,
+      "logits/rejected": -3.052220106124878,
+      "logps/chosen": -1.7839086055755615,
+      "logps/rejected": -7.939328670501709,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.459771633148193,
+      "rewards/margins": 15.3885498046875,
+      "rewards/rejected": -19.84832191467285,
+      "step": 30
+    },
+    {
+      "epoch": 0.3582853486884197,
+      "grad_norm": 0.0009076724860371347,
+      "learning_rate": 4.0486209030393077e-07,
+      "logits/chosen": -3.0616514682769775,
+      "logits/rejected": -3.033237934112549,
+      "logps/chosen": -1.8522485494613647,
+      "logps/rejected": -8.748382568359375,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.630621433258057,
+      "rewards/margins": 17.24033546447754,
+      "rewards/rejected": -21.87095832824707,
+      "step": 35
+    },
+    {
+      "epoch": 0.4094689699296225,
+      "grad_norm": 0.00013148852405563184,
+      "learning_rate": 3.6710211017494754e-07,
+      "logits/chosen": -3.0289058685302734,
+      "logits/rejected": -3.002310276031494,
+      "logps/chosen": -1.935601830482483,
+      "logps/rejected": -9.641812324523926,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.8390045166015625,
+      "rewards/margins": 19.26552391052246,
+      "rewards/rejected": -24.104528427124023,
+      "step": 40
+    },
+    {
+      "epoch": 0.46065259117082535,
+      "grad_norm": 7.439987461568028e-05,
+      "learning_rate": 3.2553510389239316e-07,
+      "logits/chosen": -3.0215375423431396,
+      "logits/rejected": -2.998112201690674,
+      "logps/chosen": -1.993088960647583,
+      "logps/rejected": -10.117258071899414,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.982722282409668,
+      "rewards/margins": 20.310420989990234,
+      "rewards/rejected": -25.29314613342285,
+      "step": 45
+    },
+    {
+      "epoch": 0.5118362124120281,
+      "grad_norm": 0.0002479185108431476,
+      "learning_rate": 2.8151242780507236e-07,
+      "logits/chosen": -3.010772466659546,
+      "logits/rejected": -2.990293264389038,
+      "logps/chosen": -2.0182385444641113,
+      "logps/rejected": -10.393533706665039,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.045596122741699,
+      "rewards/margins": 20.938236236572266,
+      "rewards/rejected": -25.983835220336914,
+      "step": 50
+    },
+    {
+      "epoch": 0.5630198336532309,
+      "grad_norm": 5.564430896058611e-05,
+      "learning_rate": 2.3646527285364563e-07,
+      "logits/chosen": -3.001908779144287,
+      "logits/rejected": -2.984178066253662,
+      "logps/chosen": -2.0269970893859863,
+      "logps/rejected": -10.485576629638672,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.0674920082092285,
+      "rewards/margins": 21.14645004272461,
+      "rewards/rejected": -26.213939666748047,
+      "step": 55
+    },
+    {
+      "epoch": 0.6142034548944337,
+      "grad_norm": 2.3732297250695814e-05,
+      "learning_rate": 1.9185813610642245e-07,
+      "logits/chosen": -2.9939801692962646,
+      "logits/rejected": -2.9763240814208984,
+      "logps/chosen": -2.1204419136047363,
+      "logps/rejected": -10.583490371704102,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.9984375238418579,
+      "rewards/chosen": -5.301104545593262,
+      "rewards/margins": 21.157623291015625,
+      "rewards/rejected": -26.458728790283203,
+      "step": 60
+    },
+    {
+      "epoch": 0.6653870761356366,
+      "grad_norm": 3.5153653165787e-05,
+      "learning_rate": 1.491412095025479e-07,
+      "logits/chosen": -3.0078186988830566,
+      "logits/rejected": -2.990968704223633,
+      "logps/chosen": -2.0652410984039307,
+      "logps/rejected": -10.685462951660156,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.9984375238418579,
+      "rewards/chosen": -5.163102626800537,
+      "rewards/margins": 21.550552368164062,
+      "rewards/rejected": -26.71365737915039,
+      "step": 65
+    },
+    {
+      "epoch": 0.7165706973768394,
+      "grad_norm": 4.722931910809097e-05,
+      "learning_rate": 1.0970323365940443e-07,
+      "logits/chosen": -2.9940237998962402,
+      "logits/rejected": -2.9749436378479004,
+      "logps/chosen": -2.1152796745300293,
+      "logps/rejected": -10.595209121704102,
+      "loss": 0.0004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.288198947906494,
+      "rewards/margins": 21.1998233795166,
+      "rewards/rejected": -26.488025665283203,
+      "step": 70
+    },
+    {
+      "epoch": 0.7677543186180422,
+      "grad_norm": 0.00043712476558793484,
+      "learning_rate": 7.482634948166442e-08,
+      "logits/chosen": -3.0042853355407715,
+      "logits/rejected": -2.9820871353149414,
+      "logps/chosen": -2.102086067199707,
+      "logps/rejected": -10.324960708618164,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.255215644836426,
+      "rewards/margins": 20.557186126708984,
+      "rewards/rejected": -25.812402725219727,
+      "step": 75
+    },
+    {
+      "epoch": 0.818937939859245,
+      "grad_norm": 0.0013776814183359047,
+      "learning_rate": 4.564441536027705e-08,
+      "logits/chosen": -3.00022292137146,
+      "logits/rejected": -2.9755115509033203,
+      "logps/chosen": -2.1440300941467285,
+      "logps/rejected": -10.0432767868042,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.360074520111084,
+      "rewards/margins": 19.748117446899414,
+      "rewards/rejected": -25.10819435119629,
+      "step": 80
+    },
+    {
+      "epoch": 0.8701215611004478,
+      "grad_norm": 0.0005507801821536249,
+      "learning_rate": 2.3106145082260774e-08,
+      "logits/chosen": -3.0011277198791504,
+      "logits/rejected": -2.974482297897339,
+      "logps/chosen": -2.1504433155059814,
+      "logps/rejected": -10.013360977172852,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.376108646392822,
+      "rewards/margins": 19.65729331970215,
+      "rewards/rejected": -25.03339958190918,
+      "step": 85
+    },
+    {
+      "epoch": 0.9213051823416507,
+      "grad_norm": 0.00025207548670523616,
+      "learning_rate": 7.944264849359172e-09,
+      "logits/chosen": -3.0121123790740967,
+      "logits/rejected": -2.981370449066162,
+      "logps/chosen": -2.1106839179992676,
+      "logps/rejected": -10.074134826660156,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.27670955657959,
+      "rewards/margins": 19.90863037109375,
+      "rewards/rejected": -25.185338973999023,
+      "step": 90
+    },
+    {
+      "epoch": 0.9724888035828535,
+      "grad_norm": 0.0001811770725552188,
+      "learning_rate": 6.516921205125537e-10,
+      "logits/chosen": -2.9971859455108643,
+      "logits/rejected": -2.97003173828125,
+      "logps/chosen": -2.143008232116699,
+      "logps/rejected": -10.052621841430664,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.357520580291748,
+      "rewards/margins": 19.774032592773438,
+      "rewards/rejected": -25.131555557250977,
+      "step": 95
+    },
+    {
+      "epoch": 0.9929622520793346,
+      "step": 97,
+      "total_flos": 0.0,
+      "train_loss": 0.016540080016594853,
+      "train_runtime": 11118.1076,
+      "train_samples_per_second": 4.497,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 97,
+  "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": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060d71b5fbae247c87dbf2fcec7a35fe083307fbb8a0d8d7897d3128560e1ee0
+size 7224