End of training

README.md

@@ -2,10 +2,13 @@
 license: other
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- EllieS/Temp-L2-DPO
 model-index:
 - name: llama3-L1-SFT-L2-DPO
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-L1-SFT-L2-DPO
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [EllieS/TempReason-L1-llama3](https://huggingface.co/EllieS/TempReason-L1-llama3) on the EllieS/Temp-L2-DPO dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0028
 - Rewards/chosen: -0.4016

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9999375663357682,
+    "eval_logits/chosen": 0.6540641784667969,
+    "eval_logits/rejected": 1.569779634475708,
+    "eval_logps/chosen": -84.51407623291016,
+    "eval_logps/rejected": -994.2071533203125,
+    "eval_loss": 0.00282670627348125,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -0.40158194303512573,
+    "eval_rewards/margins": 8.929591178894043,
+    "eval_rewards/rejected": -9.33117389678955,
+    "eval_runtime": 0.6352,
+    "eval_samples": 5,
+    "eval_samples_per_second": 7.871,
+    "eval_steps_per_second": 7.871,
     "total_flos": 0.0,
     "train_loss": 0.05122942747121405,
     "train_runtime": 6577.5594,

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9999375663357682,
+    "eval_logits/chosen": 0.6540641784667969,
+    "eval_logits/rejected": 1.569779634475708,
+    "eval_logps/chosen": -84.51407623291016,
+    "eval_logps/rejected": -994.2071533203125,
+    "eval_loss": 0.00282670627348125,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -0.40158194303512573,
+    "eval_rewards/margins": 8.929591178894043,
+    "eval_rewards/rejected": -9.33117389678955,
+    "eval_runtime": 0.6352,
+    "eval_samples": 5,
+    "eval_samples_per_second": 7.871,
+    "eval_steps_per_second": 7.871
+}

runs/May10_08-42-30_612e66badb5c/events.out.tfevents.1715337276.612e66badb5c.57653.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc6331638ff561cca8f8b1b41a8024b40d531cbc7ad47921154041da9497b2b
+size 828