Model save

README.md

@@ -2,14 +2,9 @@
 license: apache-2.0
 base_model: ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_iter_1
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
-datasets:
-- updated
-- original
 model-index:
 - name: 0.001_withdpo_4iters_bs256_5102lr_misit_iter_2
   results: []
@@ -20,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.001_withdpo_4iters_bs256_5102lr_misit_iter_2
 
-This model is a fine-tuned version of [ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_iter_1](https://huggingface.co/ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_iter_1) on the updated and the original datasets.
+This model is a fine-tuned version of [ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_iter_1](https://huggingface.co/ShenaoZ/0.001_withdpo_4iters_bs256_5102lr_misit_iter_1) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
     "train_loss": 0.5042527813022419,
-    "train_runtime": 3404.6409,
+    "train_runtime": 3406.4519,
     "train_samples": 15283,
-    "train_samples_per_second": 4.489,
+    "train_samples_per_second": 4.486,
     "train_steps_per_second": 0.017
 }

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
     "train_loss": 0.5042527813022419,
-    "train_runtime": 3404.6409,
+    "train_runtime": 3406.4519,
     "train_samples": 15283,
-    "train_samples_per_second": 4.489,
+    "train_samples_per_second": 4.486,
     "train_steps_per_second": 0.017
 }

trainer_state.json

@@ -109,8 +109,8 @@
       "step": 59,
       "total_flos": 0.0,
       "train_loss": 0.5042527813022419,
-      "train_runtime": 3404.6409,
-      "train_samples_per_second": 4.489,
+      "train_runtime": 3406.4519,
+      "train_samples_per_second": 4.486,
       "train_steps_per_second": 0.017
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac9ebf7fbe1ff4faf5fd907411a78fdc25d7219fb310f5a63e1f4eba9202313
+oid sha256:78645ceb1f866f592bd6536f05c88f93d3d128eb1cc45ecba183f64186efaae0
 size 6072