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: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF6k
 model-index:
 - name: zephyr-dpop-qlora-uf-oursuf6k-5e-6
   results: []
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-qlora-uf-oursuf6k-5e-6
 
-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 None 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 generation/UF6k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0992
-- Positive Losses: 4.5979
-- Dpo Losses: 0.6512
-- Rewards/chosen: 0.1035
-- Rewards/rejected: -0.0073
-- Rewards/accuracies: 0.6190
-- Rewards/margins: 0.1109
-- Rewards/margins Max: 0.4368
-- Rewards/margins Min: -0.1884
-- Rewards/margins Std: 0.2790
-- Logps/rejected: -259.9164
-- Logps/chosen: -274.8698
-- Logits/rejected: -2.7839
-- Logits/chosen: -2.8279
+- Loss: 1.0972
+- Positive Losses: 4.6136
+- Dpo Losses: 0.6513
+- Rewards/chosen: 0.1036
+- Rewards/rejected: -0.0071
+- Rewards/accuracies: 0.6270
+- Rewards/margins: 0.1107
+- Rewards/margins Max: 0.4366
+- Rewards/margins Min: -0.1898
+- Rewards/margins Std: 0.2797
+- Logps/rejected: -259.8883
+- Logps/chosen: -274.8616
+- Logits/rejected: -2.7883
+- Logits/chosen: -2.8318
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6513049602508545,
+    "eval_logits/chosen": -2.831768035888672,
+    "eval_logits/rejected": -2.788257598876953,
+    "eval_logps/chosen": -274.86163330078125,
+    "eval_logps/rejected": -259.8882751464844,
+    "eval_loss": 1.0971728563308716,
+    "eval_positive_losses": 4.613582134246826,
+    "eval_rewards/accuracies": 0.6269841194152832,
+    "eval_rewards/chosen": 0.10359582304954529,
+    "eval_rewards/margins": 0.11065211147069931,
+    "eval_rewards/margins_max": 0.4366241991519928,
+    "eval_rewards/margins_min": -0.18976463377475739,
+    "eval_rewards/margins_std": 0.27969247102737427,
+    "eval_rewards/rejected": -0.007056289818137884,
+    "eval_runtime": 283.0495,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.066,
+    "eval_steps_per_second": 0.223,
     "train_loss": 0.641208895814349,
     "train_runtime": 6249.598,
     "train_samples": 10941,

config.json

@@ -0,0 +1,40 @@
+{
+  "_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,
+  "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": 0.6513049602508545,
+    "eval_logits/chosen": -2.831768035888672,
+    "eval_logits/rejected": -2.788257598876953,
+    "eval_logps/chosen": -274.86163330078125,
+    "eval_logps/rejected": -259.8882751464844,
+    "eval_loss": 1.0971728563308716,
+    "eval_positive_losses": 4.613582134246826,
+    "eval_rewards/accuracies": 0.6269841194152832,
+    "eval_rewards/chosen": 0.10359582304954529,
+    "eval_rewards/margins": 0.11065211147069931,
+    "eval_rewards/margins_max": 0.4366241991519928,
+    "eval_rewards/margins_min": -0.18976463377475739,
+    "eval_rewards/margins_std": 0.27969247102737427,
+    "eval_rewards/rejected": -0.007056289818137884,
+    "eval_runtime": 283.0495,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.066,
+    "eval_steps_per_second": 0.223
+}

runs/Jul24_17-19-18_node03/events.out.tfevents.1721816369.node03.3766044.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4bdd3f54621dd1ec4e10295d932ddf2f92435e14a04c219e5a64739980a4d9
+size 1130