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
@@ -20,9 +16,9 @@ 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: 3.4046
+- Loss: 3.8564
 
 ## Model description
 
@@ -66,6 +62,6 @@ 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

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
     "up_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj",
-    "k_proj",
     "down_proj",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.40458345413208,
-    "eval_runtime": 7.4156,
+    "eval_loss": 3.856374740600586,
+    "eval_runtime": 6.9621,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.102,
-    "eval_steps_per_second": 0.809,
+    "eval_samples_per_second": 3.304,
+    "eval_steps_per_second": 0.862,
     "train_loss": 0.0,
-    "train_runtime": 16.9739,
+    "train_runtime": 13.7041,
     "train_samples": 217,
-    "train_samples_per_second": 127.843,
-    "train_steps_per_second": 32.403
+    "train_samples_per_second": 158.347,
+    "train_steps_per_second": 40.134
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.40458345413208,
-    "eval_runtime": 7.4156,
+    "eval_loss": 3.856374740600586,
+    "eval_runtime": 6.9621,
     "eval_samples": 23,
-    "eval_samples_per_second": 3.102,
-    "eval_steps_per_second": 0.809
+    "eval_samples_per_second": 3.304,
+    "eval_steps_per_second": 0.862
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "train_loss": 0.0,
-    "train_runtime": 16.9739,
+    "train_runtime": 13.7041,
     "train_samples": 217,
-    "train_samples_per_second": 127.843,
-    "train_steps_per_second": 32.403
+    "train_samples_per_second": 158.347,
+    "train_steps_per_second": 40.134
 }

trainer_state.json

@@ -949,9 +949,9 @@
       "step": 550,
       "total_flos": 1.879358707856179e+16,
       "train_loss": 0.0,
-      "train_runtime": 16.9739,
-      "train_samples_per_second": 127.843,
-      "train_steps_per_second": 32.403
+      "train_runtime": 13.7041,
+      "train_samples_per_second": 158.347,
+      "train_steps_per_second": 40.134
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15469a96348f5cb785a51a156b48ad22e68226bd7cb275db840025eac257b8ea
+oid sha256:e818941085b837686156038b4f6804110009ec8397a48148843c32cdf4ce9d5d
 size 4792