Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- maxidl/distilabel-capybara-dpo-7k-binarized_en_de
+model-index:
+- name: Mistral-7B-v0.1-capybara-orpo-en-de
+  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. -->
+
+# Mistral-7B-v0.1-capybara-orpo-en-de
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the maxidl/distilabel-capybara-dpo-7k-binarized_en_de 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-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: inverse_sqrt
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.649145109749539,
+    "train_runtime": 4268.1705,
+    "train_samples": 11530,
+    "train_samples_per_second": 8.104,
+    "train_steps_per_second": 0.064
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056ed418415554f05069301338398b9b9334b179422c0742528d233f95ce257b
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37135ccd1e8747eaee06af0b760d16de278d59067f5eb7c88cf272c879c9730f
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5588779b0dee3055d50ecd18ac217f059f5e9e0c4d99592645f0d914034f93
+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"
+  }
+}

runs/Apr15_17-36-59_ggpu163/events.out.tfevents.1713195547.ggpu163.2260874.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0184086f44b7db1e4f01a23e1266c7843f383abcb5afd1061b8744b6ee8076b4
+size 28511

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.649145109749539,
+    "train_runtime": 4268.1705,
+    "train_samples": 11530,
+    "train_samples_per_second": 8.104,
+    "train_steps_per_second": 0.064
+}

trainer_state.json

@@ -0,0 +1,516 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 273,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "grad_norm": 498.0,
+      "learning_rate": 5.000000000000001e-07,
+      "log_odds_chosen": 0.2863905131816864,
+      "log_odds_ratio": -0.5870538949966431,
+      "logits/chosen": -2.007096767425537,
+      "logits/rejected": -2.008589029312134,
+      "logps/chosen": -0.9226220846176147,
+      "logps/rejected": -1.105508804321289,
+      "loss": 3.8837,
+      "nll_loss": 4.084702491760254,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.04613110423088074,
+      "rewards/margins": 0.009144341573119164,
+      "rewards/rejected": -0.05527544766664505,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 50.5,
+      "learning_rate": 1.0000000000000002e-06,
+      "log_odds_chosen": 0.3382885456085205,
+      "log_odds_ratio": -0.5765059590339661,
+      "logits/chosen": -2.6738319396972656,
+      "logits/rejected": -2.6777594089508057,
+      "logps/chosen": -0.902550220489502,
+      "logps/rejected": -1.1331396102905273,
+      "loss": 1.6578,
+      "nll_loss": 1.7452325820922852,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.0451275110244751,
+      "rewards/margins": 0.011529467068612576,
+      "rewards/rejected": -0.05665697902441025,
+      "step": 20
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.5e-06,
+      "log_odds_chosen": 0.2815089225769043,
+      "log_odds_ratio": -0.5875880122184753,
+      "logits/chosen": -2.437102794647217,
+      "logits/rejected": -2.4390525817871094,
+      "logps/chosen": -0.8905347585678101,
+      "logps/rejected": -1.0546678304672241,
+      "loss": 0.5865,
+      "nll_loss": 0.5374206900596619,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.044526733458042145,
+      "rewards/margins": 0.008206663653254509,
+      "rewards/rejected": -0.0527334026992321,
+      "step": 30
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.0000000000000003e-06,
+      "log_odds_chosen": 0.3029056787490845,
+      "log_odds_ratio": -0.6036669611930847,
+      "logits/chosen": -2.1445510387420654,
+      "logits/rejected": -2.166757583618164,
+      "logps/chosen": -0.9048384428024292,
+      "logps/rejected": -1.0757750272750854,
+      "loss": 0.5633,
+      "nll_loss": 0.5419524908065796,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.04524192586541176,
+      "rewards/margins": 0.008546831086277962,
+      "rewards/rejected": -0.05378875881433487,
+      "step": 40
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.6796875,
+      "learning_rate": 2.5e-06,
+      "log_odds_chosen": 0.2378097027540207,
+      "log_odds_ratio": -0.630806565284729,
+      "logits/chosen": -1.8973627090454102,
+      "logits/rejected": -1.934752106666565,
+      "logps/chosen": -0.8510879278182983,
+      "logps/rejected": -1.0084228515625,
+      "loss": 0.5498,
+      "nll_loss": 0.47691044211387634,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.042554400861263275,
+      "rewards/margins": 0.007866747677326202,
+      "rewards/rejected": -0.050421155989170074,
+      "step": 50
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.7265625,
+      "learning_rate": 3e-06,
+      "log_odds_chosen": 0.34561508893966675,
+      "log_odds_ratio": -0.5882634520530701,
+      "logits/chosen": -1.789703369140625,
+      "logits/rejected": -1.8299936056137085,
+      "logps/chosen": -0.8602263331413269,
+      "logps/rejected": -1.0266495943069458,
+      "loss": 0.5348,
+      "nll_loss": 0.4759138524532318,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.043011318892240524,
+      "rewards/margins": 0.008321164175868034,
+      "rewards/rejected": -0.05133248120546341,
+      "step": 60
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.5e-06,
+      "log_odds_chosen": 0.306732177734375,
+      "log_odds_ratio": -0.6226531267166138,
+      "logits/chosen": -1.8786418437957764,
+      "logits/rejected": -1.9659067392349243,
+      "logps/chosen": -0.8097027540206909,
+      "logps/rejected": -0.9237287640571594,
+      "loss": 0.5199,
+      "nll_loss": 0.47153204679489136,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.040485139936208725,
+      "rewards/margins": 0.005701296962797642,
+      "rewards/rejected": -0.04618643969297409,
+      "step": 70
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.5703125,
+      "learning_rate": 4.000000000000001e-06,
+      "log_odds_chosen": 0.46479716897010803,
+      "log_odds_ratio": -0.5484603047370911,
+      "logits/chosen": -1.894330382347107,
+      "logits/rejected": -1.9072799682617188,
+      "logps/chosen": -0.8353139758110046,
+      "logps/rejected": -1.0923199653625488,
+      "loss": 0.5272,
+      "nll_loss": 0.49910029768943787,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.04176569730043411,
+      "rewards/margins": 0.012850301340222359,
+      "rewards/rejected": -0.05461599677801132,
+      "step": 80
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.5703125,
+      "learning_rate": 4.5e-06,
+      "log_odds_chosen": 0.46429938077926636,
+      "log_odds_ratio": -0.561553418636322,
+      "logits/chosen": -1.9992767572402954,
+      "logits/rejected": -2.0206494331359863,
+      "logps/chosen": -0.7664617300033569,
+      "logps/rejected": -0.9973196983337402,
+      "loss": 0.5236,
+      "nll_loss": 0.47519445419311523,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.038323089480400085,
+      "rewards/margins": 0.01154289674013853,
+      "rewards/rejected": -0.04986598342657089,
+      "step": 90
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.75,
+      "learning_rate": 5e-06,
+      "log_odds_chosen": 0.357390433549881,
+      "log_odds_ratio": -0.5652999877929688,
+      "logits/chosen": -1.8920485973358154,
+      "logits/rejected": -1.9230598211288452,
+      "logps/chosen": -0.7654845118522644,
+      "logps/rejected": -0.9835049510002136,
+      "loss": 0.4967,
+      "nll_loss": 0.4664408266544342,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.03827423229813576,
+      "rewards/margins": 0.010901018045842648,
+      "rewards/rejected": -0.04917524382472038,
+      "step": 100
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.6015625,
+      "learning_rate": 4.767312946227961e-06,
+      "log_odds_chosen": 0.2798970341682434,
+      "log_odds_ratio": -0.5895387530326843,
+      "logits/chosen": -1.9187400341033936,
+      "logits/rejected": -1.9244420528411865,
+      "logps/chosen": -0.8067512512207031,
+      "logps/rejected": -0.9561241269111633,
+      "loss": 0.4901,
+      "nll_loss": 0.6010779738426208,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.040337562561035156,
+      "rewards/margins": 0.007468645926564932,
+      "rewards/rejected": -0.047806207090616226,
+      "step": 110
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.564354645876385e-06,
+      "log_odds_chosen": 0.6895818114280701,
+      "log_odds_ratio": -0.45160675048828125,
+      "logits/chosen": -1.7748291492462158,
+      "logits/rejected": -1.8056682348251343,
+      "logps/chosen": -0.7309473752975464,
+      "logps/rejected": -1.0976765155792236,
+      "loss": 0.4873,
+      "nll_loss": 0.4398137629032135,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.03654736652970314,
+      "rewards/margins": 0.018336456269025803,
+      "rewards/rejected": -0.054883819073438644,
+      "step": 120
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.7890625,
+      "learning_rate": 4.385290096535147e-06,
+      "log_odds_chosen": 0.658761203289032,
+      "log_odds_ratio": -0.47310584783554077,
+      "logits/chosen": -1.9612312316894531,
+      "logits/rejected": -1.9696747064590454,
+      "logps/chosen": -0.7409031987190247,
+      "logps/rejected": -1.0737724304199219,
+      "loss": 0.4918,
+      "nll_loss": 0.43778449296951294,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.037045158445835114,
+      "rewards/margins": 0.016643470153212547,
+      "rewards/rejected": -0.05368863418698311,
+      "step": 130
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.75,
+      "learning_rate": 4.2257712736425835e-06,
+      "log_odds_chosen": 0.5739403367042542,
+      "log_odds_ratio": -0.5177870988845825,
+      "logits/chosen": -1.7142318487167358,
+      "logits/rejected": -1.7519795894622803,
+      "logps/chosen": -0.724389374256134,
+      "logps/rejected": -1.0089597702026367,
+      "loss": 0.475,
+      "nll_loss": 0.4226527214050293,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.03621947020292282,
+      "rewards/margins": 0.014228522777557373,
+      "rewards/rejected": -0.050447989255189896,
+      "step": 140
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.53125,
+      "learning_rate": 4.082482904638631e-06,
+      "log_odds_chosen": 0.437107652425766,
+      "log_odds_ratio": -0.5386956334114075,
+      "logits/chosen": -1.970740556716919,
+      "logits/rejected": -2.0762734413146973,
+      "logps/chosen": -0.736059308052063,
+      "logps/rejected": -0.9635001420974731,
+      "loss": 0.4783,
+      "nll_loss": 0.4815542697906494,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.03680296614766121,
+      "rewards/margins": 0.011372040025889874,
+      "rewards/rejected": -0.04817500710487366,
+      "step": 150
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.6484375,
+      "learning_rate": 3.952847075210474e-06,
+      "log_odds_chosen": 0.25039786100387573,
+      "log_odds_ratio": -0.6173754334449768,
+      "logits/chosen": -1.8762115240097046,
+      "logits/rejected": -1.9119548797607422,
+      "logps/chosen": -0.8681584596633911,
+      "logps/rejected": -1.0069737434387207,
+      "loss": 0.4902,
+      "nll_loss": 0.4779680371284485,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.043407924473285675,
+      "rewards/margins": 0.006940762512385845,
+      "rewards/rejected": -0.050348687916994095,
+      "step": 160
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.8046875,
+      "learning_rate": 3.834824944236852e-06,
+      "log_odds_chosen": 0.8294051885604858,
+      "log_odds_ratio": -0.4564356803894043,
+      "logits/chosen": -1.9998172521591187,
+      "logits/rejected": -2.012346029281616,
+      "logps/chosen": -0.7080036997795105,
+      "logps/rejected": -1.075842022895813,
+      "loss": 0.4728,
+      "nll_loss": 0.4948364198207855,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.035400185734033585,
+      "rewards/margins": 0.018391914665699005,
+      "rewards/rejected": -0.05379210039973259,
+      "step": 170
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.5234375,
+      "learning_rate": 3.72677996249965e-06,
+      "log_odds_chosen": 0.6013724207878113,
+      "log_odds_ratio": -0.5433425307273865,
+      "logits/chosen": -1.8251736164093018,
+      "logits/rejected": -1.8962123394012451,
+      "logps/chosen": -0.7299692034721375,
+      "logps/rejected": -1.0021026134490967,
+      "loss": 0.4729,
+      "nll_loss": 0.419732004404068,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.036498457193374634,
+      "rewards/margins": 0.013606672175228596,
+      "rewards/rejected": -0.05010513216257095,
+      "step": 180
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.9921875,
+      "learning_rate": 3.6273812505500587e-06,
+      "log_odds_chosen": 0.9894807934761047,
+      "log_odds_ratio": -0.3992963433265686,
+      "logits/chosen": -1.8533046245574951,
+      "logits/rejected": -1.8780378103256226,
+      "logps/chosen": -0.6669403314590454,
+      "logps/rejected": -1.1133853197097778,
+      "loss": 0.441,
+      "nll_loss": 0.40508294105529785,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.03334701806306839,
+      "rewards/margins": 0.02232225239276886,
+      "rewards/rejected": -0.05566927045583725,
+      "step": 190
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.6015625,
+      "learning_rate": 3.5355339059327378e-06,
+      "log_odds_chosen": 0.7237910032272339,
+      "log_odds_ratio": -0.43176889419555664,
+      "logits/chosen": -1.7843163013458252,
+      "logits/rejected": -1.8297704458236694,
+      "logps/chosen": -0.6735831499099731,
+      "logps/rejected": -1.0497777462005615,
+      "loss": 0.4287,
+      "nll_loss": 0.4101743698120117,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.033679161220788956,
+      "rewards/margins": 0.01880973018705845,
+      "rewards/rejected": -0.052488893270492554,
+      "step": 200
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.450327796711771e-06,
+      "log_odds_chosen": 0.6548705101013184,
+      "log_odds_ratio": -0.4936867654323578,
+      "logits/chosen": -1.9768335819244385,
+      "logits/rejected": -1.964470624923706,
+      "logps/chosen": -0.7660457491874695,
+      "logps/rejected": -1.0849239826202393,
+      "loss": 0.4251,
+      "nll_loss": 0.4697703421115875,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.03830229118466377,
+      "rewards/margins": 0.01594390906393528,
+      "rewards/rejected": -0.0542462058365345,
+      "step": 210
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.3709993123162106e-06,
+      "log_odds_chosen": 0.9413236379623413,
+      "log_odds_ratio": -0.3946041464805603,
+      "logits/chosen": -1.8952887058258057,
+      "logits/rejected": -1.9475895166397095,
+      "logps/chosen": -0.6552693247795105,
+      "logps/rejected": -1.1159121990203857,
+      "loss": 0.4313,
+      "nll_loss": 0.44144296646118164,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.032763466238975525,
+      "rewards/margins": 0.023032139986753464,
+      "rewards/rejected": -0.05579560995101929,
+      "step": 220
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.71875,
+      "learning_rate": 3.296902366978936e-06,
+      "log_odds_chosen": 0.8275907635688782,
+      "log_odds_ratio": -0.4250548481941223,
+      "logits/chosen": -1.8575712442398071,
+      "logits/rejected": -1.9162076711654663,
+      "logps/chosen": -0.6322061419487,
+      "logps/rejected": -1.0946836471557617,
+      "loss": 0.4229,
+      "nll_loss": 0.3766014575958252,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.03161030635237694,
+      "rewards/margins": 0.023123880848288536,
+      "rewards/rejected": -0.05473419278860092,
+      "step": 230
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.828125,
+      "learning_rate": 3.2274861218395142e-06,
+      "log_odds_chosen": 0.7520133852958679,
+      "log_odds_ratio": -0.45257338881492615,
+      "logits/chosen": -1.8115984201431274,
+      "logits/rejected": -1.8446438312530518,
+      "logps/chosen": -0.7262736558914185,
+      "logps/rejected": -1.1011757850646973,
+      "loss": 0.423,
+      "nll_loss": 0.4082041382789612,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.03631368279457092,
+      "rewards/margins": 0.01874510571360588,
+      "rewards/rejected": -0.055058788508176804,
+      "step": 240
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.765625,
+      "learning_rate": 3.1622776601683796e-06,
+      "log_odds_chosen": 0.9655596017837524,
+      "log_odds_ratio": -0.42737776041030884,
+      "logits/chosen": -1.9757699966430664,
+      "logits/rejected": -1.9998546838760376,
+      "logps/chosen": -0.6736587285995483,
+      "logps/rejected": -1.1431043148040771,
+      "loss": 0.4281,
+      "nll_loss": 0.4197885990142822,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.0336829349398613,
+      "rewards/margins": 0.023472286760807037,
+      "rewards/rejected": -0.057155221700668335,
+      "step": 250
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.1008683647302113e-06,
+      "log_odds_chosen": 1.018965482711792,
+      "log_odds_ratio": -0.3666786551475525,
+      "logits/chosen": -1.9215749502182007,
+      "logits/rejected": -1.9601131677627563,
+      "logps/chosen": -0.5990187525749207,
+      "logps/rejected": -1.1184070110321045,
+      "loss": 0.421,
+      "nll_loss": 0.39652419090270996,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.0299509409815073,
+      "rewards/margins": 0.025969412177801132,
+      "rewards/rejected": -0.055920351296663284,
+      "step": 260
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.0429030972509227e-06,
+      "log_odds_chosen": 0.7740264534950256,
+      "log_odds_ratio": -0.44708919525146484,
+      "logits/chosen": -1.8729135990142822,
+      "logits/rejected": -1.9034210443496704,
+      "logps/chosen": -0.6478686332702637,
+      "logps/rejected": -0.9832038879394531,
+      "loss": 0.4251,
+      "nll_loss": 0.4181249141693115,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.0323934331536293,
+      "rewards/margins": 0.016766764223575592,
+      "rewards/rejected": -0.0491601899266243,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "step": 273,
+      "total_flos": 0.0,
+      "train_loss": 0.649145109749539,
+      "train_runtime": 4268.1705,
+      "train_samples_per_second": 8.104,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 273,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b00013854d73dd32b49a09ad19cc8651054680a280196abbf9e2866c48d694
+size 5368