Model save

README.md

@@ -3,16 +3,12 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- scottsuk0306/DepthQA
+- generator
 model-index:
 - name: zephyr-7b-stem-train
   results: []
@@ -23,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-stem-train
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the scottsuk0306/DepthQA dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0544
+- Loss: 0.4948
 
 ## Model description
 

all_results.json

@@ -7,8 +7,8 @@
     "eval_steps_per_second": 0.211,
     "total_flos": 8375186227200.0,
     "train_loss": 0.0,
-    "train_runtime": 1.4867,
-    "train_samples": 424,
-    "train_samples_per_second": 208.516,
-    "train_steps_per_second": 6.726
+    "train_runtime": 1.4498,
+    "train_samples": 851,
+    "train_samples_per_second": 331.078,
+    "train_steps_per_second": 6.897
 }

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 8375186227200.0,
     "train_loss": 0.0,
-    "train_runtime": 1.4867,
-    "train_samples": 424,
-    "train_samples_per_second": 208.516,
-    "train_steps_per_second": 6.726
+    "train_runtime": 1.4498,
+    "train_samples": 851,
+    "train_samples_per_second": 331.078,
+    "train_steps_per_second": 6.897
 }

trainer_state.json

@@ -106,9 +106,9 @@
       "step": 10,
       "total_flos": 8375186227200.0,
       "train_loss": 0.0,
-      "train_runtime": 1.4867,
-      "train_samples_per_second": 208.516,
-      "train_steps_per_second": 6.726
+      "train_runtime": 1.4498,
+      "train_samples_per_second": 331.078,
+      "train_steps_per_second": 6.897
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c932eb51d0afc6b0a54ae5af2685e50851245e4ce74b9d4302d9db0152f98346
+oid sha256:fafca06e48dba2cf4dbebe50db64deb5d5992b81d6b82eb5e94b3b870e96afb2
 size 6968