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:
+- EllieS/Temp-L2-DPO
 model-index:
 - name: Temp-L1-SFT-L2-KTO
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Temp-L1-SFT-L2-KTO
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [EllieS/TempReason-L1](https://huggingface.co/EllieS/TempReason-L1) on the EllieS/Temp-L2-DPO dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2213
 - Rewards/chosen: 0.2579

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9998751404669747,
+    "eval_logits/chosen": -2.571059465408325,
+    "eval_logits/rejected": -2.6589972972869873,
+    "eval_logps/chosen": -0.11967950314283371,
+    "eval_logps/rejected": -652.1184692382812,
+    "eval_loss": 0.22132086753845215,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": 0.2579382359981537,
+    "eval_rewards/margins": 6.330402374267578,
+    "eval_rewards/rejected": -6.072464466094971,
+    "eval_runtime": 0.6743,
+    "eval_samples": 5,
+    "eval_samples_per_second": 7.415,
+    "eval_steps_per_second": 4.449,
     "total_flos": 0.0,
     "train_loss": 0.2426841035559699,
     "train_runtime": 8271.4989,

config.json

@@ -0,0 +1,26 @@
+{
+  "_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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9998751404669747,
+    "eval_logits/chosen": -2.571059465408325,
+    "eval_logits/rejected": -2.6589972972869873,
+    "eval_logps/chosen": -0.11967950314283371,
+    "eval_logps/rejected": -652.1184692382812,
+    "eval_loss": 0.22132086753845215,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": 0.2579382359981537,
+    "eval_rewards/margins": 6.330402374267578,
+    "eval_rewards/rejected": -6.072464466094971,
+    "eval_runtime": 0.6743,
+    "eval_samples": 5,
+    "eval_samples_per_second": 7.415,
+    "eval_steps_per_second": 4.449
+}

runs/May09_06-20-11_612e66badb5c/events.out.tfevents.1715243995.612e66badb5c.49874.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898a6a4de14f990850e9f50e2f26f63a62c7d0c82c6ef59afdf689529939ace4
+size 828