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
 
@@ -62,7 +58,6 @@ The following hyperparameters were used during training:
 | 1.9567        | 7.0   | 385  | 1.9889          |
 | 1.9235        | 8.0   | 440  | 1.9856          |
 | 1.8121        | 9.0   | 495  | 1.9849          |
-| 1.874         | 10.0  | 550  | 1.9848          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "k_proj",
     "q_proj",
     "up_proj",
     "v_proj",
-    "k_proj",
-    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
     "eval_loss": 1.9848212003707886,
-    "eval_runtime": 4.9008,
+    "eval_runtime": 6.6898,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.693,
-    "eval_steps_per_second": 1.224,
-    "train_loss": 1.5526252421465787,
-    "train_runtime": 23283.78,
+    "eval_samples_per_second": 3.438,
+    "eval_steps_per_second": 0.897,
+    "train_loss": 0.0,
+    "train_runtime": 10.6048,
     "train_samples": 217,
-    "train_samples_per_second": 0.093,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 204.624,
+    "train_steps_per_second": 51.863
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "eval_loss": 1.9848212003707886,
-    "eval_runtime": 4.9008,
+    "eval_runtime": 6.6898,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.693,
-    "eval_steps_per_second": 1.224
+    "eval_samples_per_second": 3.438,
+    "eval_steps_per_second": 0.897
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 1.5526252421465787,
-    "train_runtime": 23283.78,
+    "train_loss": 0.0,
+    "train_runtime": 10.6048,
     "train_samples": 217,
-    "train_samples_per_second": 0.093,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 204.624,
+    "train_steps_per_second": 51.863
 }

trainer_state.json

@@ -948,28 +948,14 @@
       "loss": 1.874,
       "step": 548
     },
-    {
-      "epoch": 10.0,
-      "pls_score": 62.44897959183673,
-      "std": 4.1477362667705515,
-      "step": 550
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 1.9848212003707886,
-      "eval_runtime": 4.9046,
-      "eval_samples_per_second": 4.689,
-      "eval_steps_per_second": 1.223,
-      "step": 550
-    },
     {
       "epoch": 10.0,
       "step": 550,
       "total_flos": 1.8756405193949184e+16,
-      "train_loss": 1.5526252421465787,
-      "train_runtime": 23283.78,
-      "train_samples_per_second": 0.093,
-      "train_steps_per_second": 0.024
+      "train_loss": 0.0,
+      "train_runtime": 10.6048,
+      "train_samples_per_second": 204.624,
+      "train_steps_per_second": 51.863
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c677dd79b462fc73f2789bacd7347362aa793784208e35b1e034cb575ba3a945
+oid sha256:938118a4b8fb53568603026389e5c4b53d109d040e802d31dbc20c458c2001b2
 size 4792