Model save

README.md

@@ -2,13 +2,9 @@
 license: other
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- ruozhiba
 base_model: 01-ai/Yi-6B
 model-index:
 - name: Yi-6B-ruozhiba-1e-5-50
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Yi-6B-ruozhiba-1e-5-50
 
-This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the ruozhiba dataset.
+This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.9848
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
     "v_proj",
-    "down_proj"
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
     "eval_loss": 1.9848212003707886,
-    "eval_runtime": 6.6898,
+    "eval_runtime": 6.5227,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.438,
-    "eval_steps_per_second": 0.897,
+    "eval_samples_per_second": 3.526,
+    "eval_steps_per_second": 0.92,
     "train_loss": 0.0,
-    "train_runtime": 10.6048,
+    "train_runtime": 11.1151,
     "train_samples": 217,
-    "train_samples_per_second": 204.624,
-    "train_steps_per_second": 51.863
+    "train_samples_per_second": 195.23,
+    "train_steps_per_second": 49.482
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "eval_loss": 1.9848212003707886,
-    "eval_runtime": 6.6898,
+    "eval_runtime": 6.5227,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.438,
-    "eval_steps_per_second": 0.897
+    "eval_samples_per_second": 3.526,
+    "eval_steps_per_second": 0.92
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "train_loss": 0.0,
-    "train_runtime": 10.6048,
+    "train_runtime": 11.1151,
     "train_samples": 217,
-    "train_samples_per_second": 204.624,
-    "train_steps_per_second": 51.863
+    "train_samples_per_second": 195.23,
+    "train_steps_per_second": 49.482
 }

trainer_state.json

@@ -953,9 +953,9 @@
       "step": 550,
       "total_flos": 1.8756405193949184e+16,
       "train_loss": 0.0,
-      "train_runtime": 10.6048,
-      "train_samples_per_second": 204.624,
-      "train_steps_per_second": 51.863
+      "train_runtime": 11.1151,
+      "train_samples_per_second": 195.23,
+      "train_steps_per_second": 49.482
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938118a4b8fb53568603026389e5c4b53d109d040e802d31dbc20c458c2001b2
+oid sha256:9aea1390a45fca6e95093bf62846bc8d4053e7d5e1f37131e30d4f67939d1682
 size 4792