End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-qlora-uf-ours-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/UF dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.0975
-- Positive Losses: 42.8746
-- Dpo Losses: 0.6098
-- Rewards/chosen: -0.3872
-- Rewards/rejected: -0.7242
-- Rewards/accuracies: 0.6680
+- Loss: 5.1264
+- Positive Losses: 43.1884
+- Dpo Losses: 0.6101
+- Rewards/chosen: -0.3903
+- Rewards/rejected: -0.7274
+- Rewards/accuracies: 0.6670
 - Rewards/margins: 0.3370
-- Rewards/margins Max: 1.4157
-- Rewards/margins Min: -0.8369
-- Rewards/margins Std: 0.7695
-- Logps/rejected: -331.0000
-- Logps/chosen: -323.3101
-- Logits/rejected: -2.4816
-- Logits/chosen: -2.5285
+- Rewards/margins Max: 1.4167
+- Rewards/margins Min: -0.8378
+- Rewards/margins Std: 0.7707
+- Logps/rejected: -331.3143
+- Logps/chosen: -323.6263
+- Logits/rejected: -2.4808
+- Logits/chosen: -2.5277
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 3.0,
+    "eval_dpo_losses": 0.6100724935531616,
+    "eval_logits/chosen": -2.5277466773986816,
+    "eval_logits/rejected": -2.480801582336426,
+    "eval_logps/chosen": -323.6263122558594,
+    "eval_logps/rejected": -331.3143005371094,
+    "eval_loss": 5.126430988311768,
+    "eval_positive_losses": 43.18838882446289,
+    "eval_rewards/accuracies": 0.6669999957084656,
+    "eval_rewards/chosen": -0.39032912254333496,
+    "eval_rewards/margins": 0.3370245695114136,
+    "eval_rewards/margins_max": 1.416748046875,
+    "eval_rewards/margins_min": -0.8377854228019714,
+    "eval_rewards/margins_std": 0.7706853747367859,
+    "eval_rewards/rejected": -0.7273536920547485,
+    "eval_runtime": 428.2171,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.671,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.4752508000029085,
     "train_runtime": 13210.775,
     "train_samples": 5678,

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": 3.0,
+    "eval_dpo_losses": 0.6100724935531616,
+    "eval_logits/chosen": -2.5277466773986816,
+    "eval_logits/rejected": -2.480801582336426,
+    "eval_logps/chosen": -323.6263122558594,
+    "eval_logps/rejected": -331.3143005371094,
+    "eval_loss": 5.126430988311768,
+    "eval_positive_losses": 43.18838882446289,
+    "eval_rewards/accuracies": 0.6669999957084656,
+    "eval_rewards/chosen": -0.39032912254333496,
+    "eval_rewards/margins": 0.3370245695114136,
+    "eval_rewards/margins_max": 1.416748046875,
+    "eval_rewards/margins_min": -0.8377854228019714,
+    "eval_rewards/margins_std": 0.7706853747367859,
+    "eval_rewards/rejected": -0.7273536920547485,
+    "eval_runtime": 428.2171,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.671,
+    "eval_steps_per_second": 0.292
+}

runs/Jul15_16-54-43_notebook-deployment-48-7d9b6c99-p5kv4/events.out.tfevents.1721076216.notebook-deployment-48-7d9b6c99-p5kv4.52522.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39400feccbd4f736ebb79a069e9662ae778f033efc5bc4f2e1fee35f50d99ca9
+size 1130