Model save

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-mypo3_sim-full-beta10.0-lr3e-7
+  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-7b-mypo3_sim-full-beta10.0-lr3e-7
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3558
+- Rewards/chosen: 0.0514
+- Rewards/rejected: -0.3071
+- Rewards/accuracies: 0.7460
+- Rewards/margins: 0.3586
+- Logps/rejected: -1.1584
+- Logps/chosen: -0.9738
+- Logits/rejected: -2.6024
+- Logits/chosen: -2.6552
+
+## 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: 3e-07
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- 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
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 1.3576        | 0.4187 | 100  | 1.3627          | 0.1418         | -0.1881          | 0.7381             | 0.3299          | -1.1465        | -0.9648      | -2.6131         | -2.6646       |
+| 1.348         | 0.8375 | 200  | 1.3558          | 0.0514         | -0.3071          | 0.7460             | 0.3586          | -1.1584        | -0.9738      | -2.6024         | -2.6552       |
+
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9965977492802931,
+    "total_flos": 0.0,
+    "train_loss": 1.3578679581650166,
+    "train_runtime": 22459.6266,
+    "train_samples": 61134,
+    "train_samples_per_second": 2.722,
+    "train_steps_per_second": 0.011
+}

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": "4.43.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5677674ebec32a0aa45c50f1a668ddd63cb996eaab6be0517d69d6379ed31461
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6960cfa0af22c0bdc9937d2c35b85ca9fbc4bc498c5a81837a5dbb298b1cf184
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383927d7b99f5af5044dc82d0998fad3368e1703ca9a83a1bac071c1363a0e66
+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/events.out.tfevents.1747197781.gpu024.67210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d94785e3ddd708e8e94012bf4b01f3a8f7b0681755c3dd483cb706834b64933
+size 23646

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": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9965977492802931,
+    "total_flos": 0.0,
+    "train_loss": 1.3578679581650166,
+    "train_runtime": 22459.6266,
+    "train_samples": 61134,
+    "train_samples_per_second": 2.722,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,419 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9965977492802931,
+  "eval_steps": 100,
+  "global_step": 238,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04187385501177702,
+      "grad_norm": 24.340056134893707,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": -2.7158608436584473,
+      "logits/rejected": -2.6638858318328857,
+      "logps/chosen": -1.014740228652954,
+      "logps/rejected": -1.1192779541015625,
+      "loss": 1.386,
+      "rewards/accuracies": 0.4312500059604645,
+      "rewards/chosen": -0.00034439191222190857,
+      "rewards/margins": 0.002198622329160571,
+      "rewards/rejected": -0.0025430142413824797,
+      "step": 10
+    },
+    {
+      "epoch": 0.08374771002355404,
+      "grad_norm": 23.517292982985236,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": -2.693288564682007,
+      "logits/rejected": -2.635396718978882,
+      "logps/chosen": -1.0116121768951416,
+      "logps/rejected": -1.117175579071045,
+      "loss": 1.3805,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.04239145666360855,
+      "rewards/margins": 0.04076405242085457,
+      "rewards/rejected": -0.08315549790859222,
+      "step": 20
+    },
+    {
+      "epoch": 0.12562156503533106,
+      "grad_norm": 45.533774110951185,
+      "learning_rate": 2.994184927185504e-07,
+      "logits/chosen": -2.689222812652588,
+      "logits/rejected": -2.6270663738250732,
+      "logps/chosen": -1.0028706789016724,
+      "logps/rejected": -1.175140380859375,
+      "loss": 1.3745,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.003554924624040723,
+      "rewards/margins": 0.18481962382793427,
+      "rewards/rejected": -0.18837454915046692,
+      "step": 30
+    },
+    {
+      "epoch": 0.16749542004710807,
+      "grad_norm": 38.20835919834735,
+      "learning_rate": 2.958811516942438e-07,
+      "logits/chosen": -2.692945957183838,
+      "logits/rejected": -2.623710870742798,
+      "logps/chosen": -1.0277819633483887,
+      "logps/rejected": -1.1636298894882202,
+      "loss": 1.3656,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": 0.03357527405023575,
+      "rewards/margins": 0.21717777848243713,
+      "rewards/rejected": -0.1836024820804596,
+      "step": 40
+    },
+    {
+      "epoch": 0.2093692750588851,
+      "grad_norm": 27.727327545771068,
+      "learning_rate": 2.892055336507641e-07,
+      "logits/chosen": -2.6938204765319824,
+      "logits/rejected": -2.63377046585083,
+      "logps/chosen": -1.0126545429229736,
+      "logps/rejected": -1.1827986240386963,
+      "loss": 1.3618,
+      "rewards/accuracies": 0.7265625,
+      "rewards/chosen": 0.06587468832731247,
+      "rewards/margins": 0.2524634003639221,
+      "rewards/rejected": -0.18658868968486786,
+      "step": 50
+    },
+    {
+      "epoch": 0.2512431300706621,
+      "grad_norm": 36.61802654815077,
+      "learning_rate": 2.7953524822137317e-07,
+      "logits/chosen": -2.6855249404907227,
+      "logits/rejected": -2.6335606575012207,
+      "logps/chosen": -1.0112508535385132,
+      "logps/rejected": -1.1557960510253906,
+      "loss": 1.3635,
+      "rewards/accuracies": 0.7046874761581421,
+      "rewards/chosen": 0.02390291728079319,
+      "rewards/margins": 0.2835007607936859,
+      "rewards/rejected": -0.2595978379249573,
+      "step": 60
+    },
+    {
+      "epoch": 0.29311698508243916,
+      "grad_norm": 47.95761499908156,
+      "learning_rate": 2.670783280009569e-07,
+      "logits/chosen": -2.6959950923919678,
+      "logits/rejected": -2.644470691680908,
+      "logps/chosen": -0.9967104196548462,
+      "logps/rejected": -1.1624212265014648,
+      "loss": 1.3634,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": 0.07805430889129639,
+      "rewards/margins": 0.33504945039749146,
+      "rewards/rejected": -0.2569951117038727,
+      "step": 70
+    },
+    {
+      "epoch": 0.33499084009421615,
+      "grad_norm": 25.627431998034837,
+      "learning_rate": 2.521027532323594e-07,
+      "logits/chosen": -2.7318599224090576,
+      "logits/rejected": -2.6757311820983887,
+      "logps/chosen": -0.9911890029907227,
+      "logps/rejected": -1.1725175380706787,
+      "loss": 1.3574,
+      "rewards/accuracies": 0.723437488079071,
+      "rewards/chosen": 0.04885227233171463,
+      "rewards/margins": 0.3072411119937897,
+      "rewards/rejected": -0.25838884711265564,
+      "step": 80
+    },
+    {
+      "epoch": 0.3768646951059932,
+      "grad_norm": 31.51024742390425,
+      "learning_rate": 2.3493068686534757e-07,
+      "logits/chosen": -2.6925442218780518,
+      "logits/rejected": -2.644313335418701,
+      "logps/chosen": -1.0035772323608398,
+      "logps/rejected": -1.1382865905761719,
+      "loss": 1.3544,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": 0.023231156170368195,
+      "rewards/margins": 0.2983705401420593,
+      "rewards/rejected": -0.27513939142227173,
+      "step": 90
+    },
+    {
+      "epoch": 0.4187385501177702,
+      "grad_norm": 30.525457932165672,
+      "learning_rate": 2.1593154400684523e-07,
+      "logits/chosen": -2.6577420234680176,
+      "logits/rejected": -2.6260898113250732,
+      "logps/chosen": -1.0194005966186523,
+      "logps/rejected": -1.1534370183944702,
+      "loss": 1.3576,
+      "rewards/accuracies": 0.6953125,
+      "rewards/chosen": 0.0678614005446434,
+      "rewards/margins": 0.30626654624938965,
+      "rewards/rejected": -0.23840510845184326,
+      "step": 100
+    },
+    {
+      "epoch": 0.4187385501177702,
+      "eval_logits/chosen": -2.6646392345428467,
+      "eval_logits/rejected": -2.6131396293640137,
+      "eval_logps/chosen": -0.9647728800773621,
+      "eval_logps/rejected": -1.146482229232788,
+      "eval_loss": 1.3626872301101685,
+      "eval_rewards/accuracies": 0.738095223903656,
+      "eval_rewards/chosen": 0.14184348285198212,
+      "eval_rewards/margins": 0.32993972301483154,
+      "eval_rewards/rejected": -0.18809625506401062,
+      "eval_runtime": 284.7481,
+      "eval_samples_per_second": 7.024,
+      "eval_steps_per_second": 0.221,
+      "step": 100
+    },
+    {
+      "epoch": 0.46061240512954726,
+      "grad_norm": 25.03393375576096,
+      "learning_rate": 1.9551404485630487e-07,
+      "logits/chosen": -2.6635913848876953,
+      "logits/rejected": -2.6101059913635254,
+      "logps/chosen": -1.0057451725006104,
+      "logps/rejected": -1.1832140684127808,
+      "loss": 1.3639,
+      "rewards/accuracies": 0.6953125,
+      "rewards/chosen": 0.047422848641872406,
+      "rewards/margins": 0.283149778842926,
+      "rewards/rejected": -0.23572690784931183,
+      "step": 110
+    },
+    {
+      "epoch": 0.5024862601413242,
+      "grad_norm": 27.466161951263736,
+      "learning_rate": 1.7411742208792024e-07,
+      "logits/chosen": -2.6786978244781494,
+      "logits/rejected": -2.625096082687378,
+      "logps/chosen": -1.0151537656784058,
+      "logps/rejected": -1.1703256368637085,
+      "loss": 1.3554,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 0.04643763229250908,
+      "rewards/margins": 0.30899864435195923,
+      "rewards/rejected": -0.26256099343299866,
+      "step": 120
+    },
+    {
+      "epoch": 0.5443601151531012,
+      "grad_norm": 31.97149919437937,
+      "learning_rate": 1.522019718313975e-07,
+      "logits/chosen": -2.6894869804382324,
+      "logits/rejected": -2.6331231594085693,
+      "logps/chosen": -0.9996325373649597,
+      "logps/rejected": -1.1365792751312256,
+      "loss": 1.3518,
+      "rewards/accuracies": 0.7359374761581421,
+      "rewards/chosen": 0.05053108185529709,
+      "rewards/margins": 0.3217238485813141,
+      "rewards/rejected": -0.271192729473114,
+      "step": 130
+    },
+    {
+      "epoch": 0.5862339701648783,
+      "grad_norm": 24.450551252801993,
+      "learning_rate": 1.302391515238772e-07,
+      "logits/chosen": -2.6618473529815674,
+      "logits/rejected": -2.6052868366241455,
+      "logps/chosen": -1.0129234790802002,
+      "logps/rejected": -1.1488369703292847,
+      "loss": 1.3544,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": 0.07841094583272934,
+      "rewards/margins": 0.3113529086112976,
+      "rewards/rejected": -0.23294198513031006,
+      "step": 140
+    },
+    {
+      "epoch": 0.6281078251766553,
+      "grad_norm": 27.64687057764462,
+      "learning_rate": 1.0870143765356105e-07,
+      "logits/chosen": -2.6632533073425293,
+      "logits/rejected": -2.6142868995666504,
+      "logps/chosen": -1.0231969356536865,
+      "logps/rejected": -1.1415382623672485,
+      "loss": 1.3495,
+      "rewards/accuracies": 0.6859375238418579,
+      "rewards/chosen": 0.05594708397984505,
+      "rewards/margins": 0.2801240086555481,
+      "rewards/rejected": -0.22417697310447693,
+      "step": 150
+    },
+    {
+      "epoch": 0.6699816801884323,
+      "grad_norm": 25.842944468402685,
+      "learning_rate": 8.805216158094177e-08,
+      "logits/chosen": -2.6839606761932373,
+      "logits/rejected": -2.63551664352417,
+      "logps/chosen": -1.0320364236831665,
+      "logps/rejected": -1.1406912803649902,
+      "loss": 1.3473,
+      "rewards/accuracies": 0.7484375238418579,
+      "rewards/chosen": 0.07224779576063156,
+      "rewards/margins": 0.35364478826522827,
+      "rewards/rejected": -0.2813969552516937,
+      "step": 160
+    },
+    {
+      "epoch": 0.7118555352002094,
+      "grad_norm": 22.749366366142215,
+      "learning_rate": 6.873554209514085e-08,
+      "logits/chosen": -2.676924228668213,
+      "logits/rejected": -2.6334450244903564,
+      "logps/chosen": -1.0047929286956787,
+      "logps/rejected": -1.1567189693450928,
+      "loss": 1.3499,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.06494499742984772,
+      "rewards/margins": 0.34234869480133057,
+      "rewards/rejected": -0.27740365266799927,
+      "step": 170
+    },
+    {
+      "epoch": 0.7537293902119864,
+      "grad_norm": 25.456564914278125,
+      "learning_rate": 5.1167129130583346e-08,
+      "logits/chosen": -2.7176437377929688,
+      "logits/rejected": -2.652817487716675,
+      "logps/chosen": -1.005036473274231,
+      "logps/rejected": -1.1663529872894287,
+      "loss": 1.3525,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": 0.07035967707633972,
+      "rewards/margins": 0.32980746030807495,
+      "rewards/rejected": -0.25944775342941284,
+      "step": 180
+    },
+    {
+      "epoch": 0.7956032452237635,
+      "grad_norm": 26.971703897210418,
+      "learning_rate": 3.572486422412786e-08,
+      "logits/chosen": -2.6526055335998535,
+      "logits/rejected": -2.5890986919403076,
+      "logps/chosen": -1.0459108352661133,
+      "logps/rejected": -1.1826167106628418,
+      "loss": 1.3522,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.044779714196920395,
+      "rewards/margins": 0.3459870219230652,
+      "rewards/rejected": -0.3012073338031769,
+      "step": 190
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "grad_norm": 47.868926072589815,
+      "learning_rate": 2.2740950025102763e-08,
+      "logits/chosen": -2.683851718902588,
+      "logits/rejected": -2.6368541717529297,
+      "logps/chosen": -1.0166388750076294,
+      "logps/rejected": -1.1575015783309937,
+      "loss": 1.348,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": 0.06305424124002457,
+      "rewards/margins": 0.3817756772041321,
+      "rewards/rejected": -0.3187214136123657,
+      "step": 200
+    },
+    {
+      "epoch": 0.8374771002355405,
+      "eval_logits/chosen": -2.655203104019165,
+      "eval_logits/rejected": -2.6023638248443604,
+      "eval_logps/chosen": -0.973812460899353,
+      "eval_logps/rejected": -1.158385992050171,
+      "eval_loss": 1.355798602104187,
+      "eval_rewards/accuracies": 0.7460317611694336,
+      "eval_rewards/chosen": 0.05144636332988739,
+      "eval_rewards/margins": 0.358581006526947,
+      "eval_rewards/rejected": -0.30713462829589844,
+      "eval_runtime": 285.9953,
+      "eval_samples_per_second": 6.993,
+      "eval_steps_per_second": 0.22,
+      "step": 200
+    },
+    {
+      "epoch": 0.8793509552473174,
+      "grad_norm": 22.673186907743524,
+      "learning_rate": 1.2494703765902337e-08,
+      "logits/chosen": -2.6811373233795166,
+      "logits/rejected": -2.638986825942993,
+      "logps/chosen": -1.0244842767715454,
+      "logps/rejected": -1.1758297681808472,
+      "loss": 1.3506,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.051802605390548706,
+      "rewards/margins": 0.31066805124282837,
+      "rewards/rejected": -0.2588654160499573,
+      "step": 210
+    },
+    {
+      "epoch": 0.9212248102590945,
+      "grad_norm": 24.059659096859182,
+      "learning_rate": 5.206548433283803e-09,
+      "logits/chosen": -2.6909804344177246,
+      "logits/rejected": -2.6151442527770996,
+      "logps/chosen": -1.0407359600067139,
+      "logps/rejected": -1.1654198169708252,
+      "loss": 1.3477,
+      "rewards/accuracies": 0.6796875,
+      "rewards/chosen": 0.06382963806390762,
+      "rewards/margins": 0.2894967198371887,
+      "rewards/rejected": -0.2256670892238617,
+      "step": 220
+    },
+    {
+      "epoch": 0.9630986652708715,
+      "grad_norm": 31.264520298090485,
+      "learning_rate": 1.033270905653949e-09,
+      "logits/chosen": -2.6356711387634277,
+      "logits/rejected": -2.5780301094055176,
+      "logps/chosen": -1.013745903968811,
+      "logps/rejected": -1.2099864482879639,
+      "loss": 1.3485,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 0.05294634774327278,
+      "rewards/margins": 0.3595525026321411,
+      "rewards/rejected": -0.3066061735153198,
+      "step": 230
+    },
+    {
+      "epoch": 0.9965977492802931,
+      "step": 238,
+      "total_flos": 0.0,
+      "train_loss": 1.3578679581650166,
+      "train_runtime": 22459.6266,
+      "train_samples_per_second": 2.722,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 238,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede479bea1da1fa17e3008f8e967ece4ef45fd7fe65605a7f540d997859b14d8
+size 7416