End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- SeniorKabanocci/SHP-binarized
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -17,7 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jan-majkutewicz/huggingface/runs/8xusrxfz)
 # zephyr-7b-shp
 
-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.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the SeniorKabanocci/SHP-binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4546
+- Rewards/chosen: -1.0035
+- Rewards/rejected: -2.3680
+- Rewards/accuracies: 0.7864
+- Rewards/margins: 1.3644
+- Logps/rejected: -260.2372
+- Logps/chosen: -378.4407
+- Logits/rejected: -2.7522
+- Logits/chosen: -2.7984
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9999197753710389,
+    "eval_logits/chosen": -2.79840087890625,
+    "eval_logits/rejected": -2.752188205718994,
+    "eval_logps/chosen": -378.4407043457031,
+    "eval_logps/rejected": -260.23724365234375,
+    "eval_loss": 0.45464351773262024,
+    "eval_rewards/accuracies": 0.7863636612892151,
+    "eval_rewards/chosen": -1.0035351514816284,
+    "eval_rewards/margins": 1.364441156387329,
+    "eval_rewards/rejected": -2.367976188659668,
+    "eval_runtime": 2783.2579,
+    "eval_samples": 10555,
+    "eval_samples_per_second": 3.792,
+    "eval_steps_per_second": 0.474,
     "total_flos": 0.0,
     "train_loss": 0.44136011642577255,
     "train_runtime": 57646.808,

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "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": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9999197753710389,
+    "eval_logits/chosen": -2.79840087890625,
+    "eval_logits/rejected": -2.752188205718994,
+    "eval_logps/chosen": -378.4407043457031,
+    "eval_logps/rejected": -260.23724365234375,
+    "eval_loss": 0.45464351773262024,
+    "eval_rewards/accuracies": 0.7863636612892151,
+    "eval_rewards/chosen": -1.0035351514816284,
+    "eval_rewards/margins": 1.364441156387329,
+    "eval_rewards/rejected": -2.367976188659668,
+    "eval_runtime": 2783.2579,
+    "eval_samples": 10555,
+    "eval_samples_per_second": 3.792,
+    "eval_steps_per_second": 0.474
+}