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
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Yi-6B-ruozhiba-1e-5
 
-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: 1.9852
 
@@ -70,7 +66,6 @@ The following hyperparameters were used during training:
 | 1.3015        | 17.0  | 935  | 1.9796          |
 | 1.3456        | 18.0  | 990  | 1.9831          |
 | 1.2136        | 19.0  | 1045 | 1.9848          |
-| 1.302         | 20.0  | 1100 | 1.9852          |
 
 
 ### Framework versions

adapter_config.json

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

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 20.0,
     "eval_loss": 1.9851655960083008,
-    "eval_runtime": 4.9249,
+    "eval_runtime": 6.5053,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.67,
-    "eval_steps_per_second": 1.218,
-    "train_loss": 0.4608629340475256,
-    "train_runtime": 2621.4029,
+    "eval_samples_per_second": 3.536,
+    "eval_steps_per_second": 0.922,
+    "train_loss": 0.0,
+    "train_runtime": 10.5489,
     "train_samples": 217,
-    "train_samples_per_second": 1.656,
-    "train_steps_per_second": 0.42
+    "train_samples_per_second": 411.417,
+    "train_steps_per_second": 104.276
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
     "eval_loss": 1.9851655960083008,
-    "eval_runtime": 4.9249,
+    "eval_runtime": 6.5053,
     "eval_samples": 23,
-    "eval_samples_per_second": 4.67,
-    "eval_steps_per_second": 1.218
+    "eval_samples_per_second": 3.536,
+    "eval_steps_per_second": 0.922
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.4608629340475256,
-    "train_runtime": 2621.4029,
+    "train_loss": 0.0,
+    "train_runtime": 10.5489,
     "train_samples": 217,
-    "train_samples_per_second": 1.656,
-    "train_steps_per_second": 0.42
+    "train_samples_per_second": 411.417,
+    "train_steps_per_second": 104.276
 }

trainer_state.json

@@ -1872,27 +1872,14 @@
       "loss": 1.302,
       "step": 1100
     },
-    {
-      "epoch": 20.0,
-      "gpt4_scores": 0.5666666666666667,
-      "step": 1100
-    },
-    {
-      "epoch": 20.0,
-      "eval_loss": 1.9851655960083008,
-      "eval_runtime": 4.9615,
-      "eval_samples_per_second": 4.636,
-      "eval_steps_per_second": 1.209,
-      "step": 1100
-    },
     {
       "epoch": 20.0,
       "step": 1100,
       "total_flos": 3.76665795378217e+16,
-      "train_loss": 0.4608629340475256,
-      "train_runtime": 2621.4029,
-      "train_samples_per_second": 1.656,
-      "train_steps_per_second": 0.42
+      "train_loss": 0.0,
+      "train_runtime": 10.5489,
+      "train_samples_per_second": 411.417,
+      "train_steps_per_second": 104.276
     }
   ],
   "logging_steps": 4,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e881c0023e35912658acadbed8b82b42ce8c9f483ec5f254d9ba8e488b487a05
+oid sha256:681e944a530e8d053a857fadfa7e90c8d15b31e2d7d369565dd6b10cc1b3084a
 size 4792