End of training

README.md

@@ -2,10 +2,13 @@
 license: llama3
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - orpo
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-70B-Instruct
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: Meta-Llama-3-70B-Instruct
   results: []
@@ -17,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/f61fvw8u)
 # Meta-Llama-3-70B-Instruct
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2884
 - Rewards/chosen: -0.0888

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 0.9999296814570002,
+    "eval_log_odds_chosen": 0.3767525255680084,
+    "eval_log_odds_ratio": -0.62775719165802,
+    "eval_logits/chosen": 0.20116207003593445,
+    "eval_logits/rejected": -0.0032512724865227938,
+    "eval_logps/chosen": -0.8883616924285889,
+    "eval_logps/rejected": -1.1382248401641846,
+    "eval_loss": 1.2883824110031128,
+    "eval_nll_loss": 1.2074565887451172,
+    "eval_rewards/accuracies": 0.6132478713989258,
+    "eval_rewards/chosen": -0.08883616328239441,
+    "eval_rewards/margins": 0.02498631551861763,
+    "eval_rewards/rejected": -0.11382248252630234,
+    "eval_runtime": 975.3638,
+    "eval_samples": 1869,
+    "eval_samples_per_second": 1.916,
+    "eval_steps_per_second": 0.48,
     "total_flos": 0.0,
     "train_loss": 1.4252014341233652,
     "train_runtime": 102484.8577,

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128256,
+  "eos_token_id": 128257,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128257,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 128258
+}

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 0.9999296814570002,
+    "eval_log_odds_chosen": 0.3767525255680084,
+    "eval_log_odds_ratio": -0.62775719165802,
+    "eval_logits/chosen": 0.20116207003593445,
+    "eval_logits/rejected": -0.0032512724865227938,
+    "eval_logps/chosen": -0.8883616924285889,
+    "eval_logps/rejected": -1.1382248401641846,
+    "eval_loss": 1.2883824110031128,
+    "eval_nll_loss": 1.2074565887451172,
+    "eval_rewards/accuracies": 0.6132478713989258,
+    "eval_rewards/chosen": -0.08883616328239441,
+    "eval_rewards/margins": 0.02498631551861763,
+    "eval_rewards/rejected": -0.11382248252630234,
+    "eval_runtime": 975.3638,
+    "eval_samples": 1869,
+    "eval_samples_per_second": 1.916,
+    "eval_steps_per_second": 0.48
+}