End of training

README.md

@@ -1,8 +1,12 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF
+- generation/UFfull2
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,22 +20,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-qlora-uf-ours-uffull-5e-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 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/UF and the generation/UFfull2 datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.6825
-- Positive Losses: 0.1480
+- Loss: 0.6824
+- Positive Losses: 0.1476
 - Dpo Losses: 0.6646
 - Rewards/chosen: 0.1662
-- Rewards/rejected: 0.1036
-- Rewards/accuracies: 0.6810
-- Rewards/margins: 0.0626
-- Rewards/margins Max: 0.2720
-- Rewards/margins Min: -0.1174
+- Rewards/rejected: 0.1035
+- Rewards/accuracies: 0.6815
+- Rewards/margins: 0.0627
+- Rewards/margins Max: 0.2718
+- Rewards/margins Min: -0.1172
 - Rewards/margins Std: 0.1305
-- Logps/rejected: -255.4913
-- Logps/chosen: -267.8348
-- Logits/rejected: -2.7189
-- Logits/chosen: -2.7542
+- Logps/rejected: -255.5023
+- Logps/chosen: -267.8385
+- Logits/rejected: -2.7203
+- Logits/chosen: -2.7554
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.664600670337677,
+    "eval_logits/chosen": -2.755434513092041,
+    "eval_logits/rejected": -2.7203128337860107,
+    "eval_logps/chosen": -267.8385314941406,
+    "eval_logps/rejected": -255.50228881835938,
+    "eval_loss": 0.6824241876602173,
+    "eval_positive_losses": 0.1476137936115265,
+    "eval_rewards/accuracies": 0.6815000176429749,
+    "eval_rewards/chosen": 0.1661677062511444,
+    "eval_rewards/margins": 0.06265779584646225,
+    "eval_rewards/margins_max": 0.27175262570381165,
+    "eval_rewards/margins_min": -0.11723098903894424,
+    "eval_rewards/margins_std": 0.1305234432220459,
+    "eval_rewards/rejected": 0.10350991785526276,
+    "eval_runtime": 858.7209,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 4.658,
+    "eval_steps_per_second": 0.291,
     "train_loss": 0.6776896565581647,
     "train_runtime": 67917.559,
     "train_samples": 66812,

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": 0.664600670337677,
+    "eval_logits/chosen": -2.755434513092041,
+    "eval_logits/rejected": -2.7203128337860107,
+    "eval_logps/chosen": -267.8385314941406,
+    "eval_logps/rejected": -255.50228881835938,
+    "eval_loss": 0.6824241876602173,
+    "eval_positive_losses": 0.1476137936115265,
+    "eval_rewards/accuracies": 0.6815000176429749,
+    "eval_rewards/chosen": 0.1661677062511444,
+    "eval_rewards/margins": 0.06265779584646225,
+    "eval_rewards/margins_max": 0.27175262570381165,
+    "eval_rewards/margins_min": -0.11723098903894424,
+    "eval_rewards/margins_std": 0.1305234432220459,
+    "eval_rewards/rejected": 0.10350991785526276,
+    "eval_runtime": 858.7209,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 4.658,
+    "eval_steps_per_second": 0.291
+}

runs/Jul16_03-11-50_notebook-deployment-48-7d9b6c99-p5kv4/events.out.tfevents.1721168847.notebook-deployment-48-7d9b6c99-p5kv4.69846.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3542b7c4f1126fe05e4d0c5abe42f0419b07995d351956968a92f54446cfe771
+size 1130