End of training

README.md

@@ -2,10 +2,14 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: openbmb/Eurus-7b-sft
+datasets:
+- generation/UF
+- generation/UFfull
 model-index:
 - name: eurus-dpo-qlora-uf-ours-uffull-5e-7
   results: []
@@ -16,20 +20,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eurus-dpo-qlora-uf-ours-uffull-5e-7
 
-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 generation/UF and the generation/UFfull datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.5784
-- Rewards/chosen: -0.8141
-- Rewards/rejected: -1.4090
-- Rewards/accuracies: 0.6920
-- Rewards/margins: 0.5949
-- Rewards/margins Max: 2.7090
+- Rewards/chosen: -0.8137
+- Rewards/rejected: -1.4080
+- Rewards/accuracies: 0.6890
+- Rewards/margins: 0.5943
+- Rewards/margins Max: 2.7059
 - Rewards/margins Min: -0.7893
-- Rewards/margins Std: 1.1546
-- Logps/rejected: -402.1446
-- Logps/chosen: -353.0736
-- Logits/rejected: -2.0279
-- Logits/chosen: -2.1333
+- Rewards/margins Std: 1.1535
+- Logps/rejected: -402.0422
+- Logps/chosen: -353.0313
+- Logits/rejected: -2.0261
+- Logits/chosen: -2.1316
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.13159441947937,
+    "eval_logits/rejected": -2.0261080265045166,
+    "eval_logps/chosen": -353.0312805175781,
+    "eval_logps/rejected": -402.0422058105469,
+    "eval_loss": 0.5784093141555786,
+    "eval_rewards/accuracies": 0.6890000104904175,
+    "eval_rewards/chosen": -0.8136823177337646,
+    "eval_rewards/margins": 0.5943145751953125,
+    "eval_rewards/margins_max": 2.7059268951416016,
+    "eval_rewards/margins_min": -0.7893158197402954,
+    "eval_rewards/margins_std": 1.1535371541976929,
+    "eval_rewards/rejected": -1.4079967737197876,
+    "eval_runtime": 1498.5961,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 2.669,
+    "eval_steps_per_second": 0.167,
     "train_loss": 0.6004282865259383,
     "train_runtime": 118629.0501,
     "train_samples": 66812,

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 +1,19 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.13159441947937,
+    "eval_logits/rejected": -2.0261080265045166,
+    "eval_logps/chosen": -353.0312805175781,
+    "eval_logps/rejected": -402.0422058105469,
+    "eval_loss": 0.5784093141555786,
+    "eval_rewards/accuracies": 0.6890000104904175,
+    "eval_rewards/chosen": -0.8136823177337646,
+    "eval_rewards/margins": 0.5943145751953125,
+    "eval_rewards/margins_max": 2.7059268951416016,
+    "eval_rewards/margins_min": -0.7893158197402954,
+    "eval_rewards/margins_std": 1.1535371541976929,
+    "eval_rewards/rejected": -1.4079967737197876,
+    "eval_runtime": 1498.5961,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 2.669,
+    "eval_steps_per_second": 0.167
+}

runs/Jul16_15-39-24_node29/events.out.tfevents.1721232190.node29.1097085.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7aa2333d5c8c9b069bf71041d8f74e74b3a75e5fd227d1ca9a7ba655097011
+size 1017