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-5e-4-50
@@ -20,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Yi-6B-ruozhiba-5e-4-50
 
-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: 3.5394
+- Loss: 4.1158
 
 ## Model description
 
@@ -79,6 +75,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.7.1
 - Transformers 4.36.2
-- Pytorch 2.2.2+cu118
+- Pytorch 2.3.0+cu121
 - Datasets 2.14.6
 - Tokenizers 0.15.2

adapter_config.json

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

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 20.0,
-    "eval_loss": 3.5393826961517334,
-    "eval_runtime": 6.2217,
+    "eval_loss": 4.1158246994018555,
+    "eval_runtime": 6.5886,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.697,
-    "eval_steps_per_second": 0.964,
+    "eval_samples_per_second": 3.491,
+    "eval_steps_per_second": 0.911,
     "train_loss": 0.0,
-    "train_runtime": 10.4648,
+    "train_runtime": 11.9759,
     "train_samples": 217,
-    "train_samples_per_second": 207.361,
-    "train_steps_per_second": 52.557
+    "train_samples_per_second": 181.197,
+    "train_steps_per_second": 45.925
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "eval_loss": 3.5393826961517334,
-    "eval_runtime": 6.2217,
+    "eval_loss": 4.1158246994018555,
+    "eval_runtime": 6.5886,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.697,
-    "eval_steps_per_second": 0.964
+    "eval_samples_per_second": 3.491,
+    "eval_steps_per_second": 0.911
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
     "train_loss": 0.0,
-    "train_runtime": 10.4648,
+    "train_runtime": 11.9759,
     "train_samples": 217,
-    "train_samples_per_second": 207.361,
-    "train_steps_per_second": 52.557
+    "train_samples_per_second": 181.197,
+    "train_steps_per_second": 45.925
 }

trainer_state.json

@@ -2011,9 +2011,9 @@
       "step": 1100,
       "total_flos": 3.792163606268314e+16,
       "train_loss": 0.0,
-      "train_runtime": 10.4648,
-      "train_samples_per_second": 207.361,
-      "train_steps_per_second": 52.557
+      "train_runtime": 11.9759,
+      "train_samples_per_second": 181.197,
+      "train_steps_per_second": 45.925
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067278813e5531ea0ebcd32f207e9c4e28e7ff60c4fe15536189c80bdc3266ee
+oid sha256:80a8894d431c206e6e47301949f4364b55937f8e0dfc94c3023d0b32796629fd
 size 4792