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-5-50
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Yi-6B-ruozhiba-5e-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: 3.0795
 
@@ -62,7 +58,6 @@ The following hyperparameters were used during training:
 | 0.8124        | 7.0   | 385  | 2.8052          |
 | 0.6269        | 8.0   | 440  | 2.9866          |
 | 0.5743        | 9.0   | 495  | 3.0649          |
-| 0.5465        | 10.0  | 550  | 3.0795          |
 
 
 ### Framework versions

adapter_config.json

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

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
     "eval_loss": 3.079519748687744,
-    "eval_runtime": 4.9055,
+    "eval_runtime": 6.4714,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.689,
-    "eval_steps_per_second": 1.223,
-    "train_loss": 1.0206408483331855,
-    "train_runtime": 23074.2586,
+    "eval_samples_per_second": 3.554,
+    "eval_steps_per_second": 0.927,
+    "train_loss": 0.0,
+    "train_runtime": 9.9064,
     "train_samples": 217,
-    "train_samples_per_second": 0.094,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 219.05,
+    "train_steps_per_second": 55.52
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "eval_loss": 3.079519748687744,
-    "eval_runtime": 4.9055,
+    "eval_runtime": 6.4714,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.689,
-    "eval_steps_per_second": 1.223
+    "eval_samples_per_second": 3.554,
+    "eval_steps_per_second": 0.927
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 1.0206408483331855,
-    "train_runtime": 23074.2586,
+    "train_loss": 0.0,
+    "train_runtime": 9.9064,
     "train_samples": 217,
-    "train_samples_per_second": 0.094,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 219.05,
+    "train_steps_per_second": 55.52
 }

trainer_state.json

@@ -948,28 +948,14 @@
       "loss": 0.5465,
       "step": 548
     },
-    {
-      "epoch": 10.0,
-      "pls_score": 53.06122448979592,
-      "std": 4.340793602433762,
-      "step": 550
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 3.079519748687744,
-      "eval_runtime": 4.9095,
-      "eval_samples_per_second": 4.685,
-      "eval_steps_per_second": 1.222,
-      "step": 550
-    },
     {
       "epoch": 10.0,
       "step": 550,
       "total_flos": 1.876652342808576e+16,
-      "train_loss": 1.0206408483331855,
-      "train_runtime": 23074.2586,
-      "train_samples_per_second": 0.094,
-      "train_steps_per_second": 0.024
+      "train_loss": 0.0,
+      "train_runtime": 9.9064,
+      "train_samples_per_second": 219.05,
+      "train_steps_per_second": 55.52
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9b09f24f51fddb4e163c6d8b5dda5a40a8a6543c084d147043f7abd98091e1
+oid sha256:ca567657591541010e7d8d992760bfb0151e6b926d6a497bcbbd45c4d73cf974
 size 4792