End of training

README.md

@@ -2,10 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: openbmb/Eurus-7b-sft
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: eurus-dpop-qlora-uffull-5e-6
   results: []
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eurus-dpop-qlora-uffull-5e-6
 
-This model is a fine-tuned version of [openbmb/Eurus-7b-sft](https://huggingface.co/openbmb/Eurus-7b-sft) on the None dataset.
+This model is a fine-tuned version of [openbmb/Eurus-7b-sft](https://huggingface.co/openbmb/Eurus-7b-sft) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6839
-- Positive Losses: 0.1611
-- Dpo Losses: 0.6520
-- Rewards/chosen: 0.1701
-- Rewards/rejected: 0.0788
-- Rewards/accuracies: 0.6984
-- Rewards/margins: 0.0913
-- Rewards/margins Max: 0.3629
-- Rewards/margins Min: -0.1212
-- Rewards/margins Std: 0.1624
-- Logps/rejected: -254.9432
-- Logps/chosen: -258.7651
-- Logits/rejected: -2.1329
-- Logits/chosen: -2.2368
+- Positive Losses: 0.1624
+- Dpo Losses: 0.6521
+- Rewards/chosen: 0.1700
+- Rewards/rejected: 0.0789
+- Rewards/accuracies: 0.6925
+- Rewards/margins: 0.0911
+- Rewards/margins Max: 0.3628
+- Rewards/margins Min: -0.1215
+- Rewards/margins Std: 0.1623
+- Logps/rejected: -254.9311
+- Logps/chosen: -258.7703
+- Logits/rejected: -2.1337
+- Logits/chosen: -2.2374
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6521267890930176,
+    "eval_logits/chosen": -2.2373995780944824,
+    "eval_logits/rejected": -2.133667230606079,
+    "eval_logps/chosen": -258.7702941894531,
+    "eval_logps/rejected": -254.93106079101562,
+    "eval_loss": 0.6839185953140259,
+    "eval_positive_losses": 0.16242748498916626,
+    "eval_rewards/accuracies": 0.692460298538208,
+    "eval_rewards/chosen": 0.17003849148750305,
+    "eval_rewards/margins": 0.09114638715982437,
+    "eval_rewards/margins_max": 0.362783819437027,
+    "eval_rewards/margins_min": -0.12145084142684937,
+    "eval_rewards/margins_std": 0.1623499095439911,
+    "eval_rewards/rejected": 0.07889209687709808,
+    "eval_runtime": 385.7962,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.184,
+    "eval_steps_per_second": 0.163,
     "train_loss": 0.6847423079499896,
     "train_runtime": 42109.9082,
     "train_samples": 61134,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openbmb/Eurus-7b-sft",
+  "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,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_dpo_losses": 0.6521267890930176,
+    "eval_logits/chosen": -2.2373995780944824,
+    "eval_logits/rejected": -2.133667230606079,
+    "eval_logps/chosen": -258.7702941894531,
+    "eval_logps/rejected": -254.93106079101562,
+    "eval_loss": 0.6839185953140259,
+    "eval_positive_losses": 0.16242748498916626,
+    "eval_rewards/accuracies": 0.692460298538208,
+    "eval_rewards/chosen": 0.17003849148750305,
+    "eval_rewards/margins": 0.09114638715982437,
+    "eval_rewards/margins_max": 0.362783819437027,
+    "eval_rewards/margins_min": -0.12145084142684937,
+    "eval_rewards/margins_std": 0.1623499095439911,
+    "eval_rewards/rejected": 0.07889209687709808,
+    "eval_runtime": 385.7962,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.184,
+    "eval_steps_per_second": 0.163
+}

runs/Jul18_23-31-24_node30/events.out.tfevents.1721355809.node30.3165905.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d068ce8eb86f8590436970297debc9781d9b1dbdc1ebb7983260425f9b9a574
+size 1130