End of training

README.md

@@ -2,11 +2,17 @@
 license: gemma
 base_model: google/gemma-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- masakhane/african-ultrachat
+- israel/untrachat_en
+- israel/sd
 model-index:
 - name: zephyr-7b-gemma-sft-african-ultraalpaca
   results: []
@@ -17,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-gemma-sft-african-ultraalpaca
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the masakhane/african-ultrachat, the israel/untrachat_en and the israel/sd datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.8875
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.8875364065170288,
+    "eval_runtime": 36.7278,
+    "eval_samples": 5900,
+    "eval_samples_per_second": 31.829,
+    "eval_steps_per_second": 4.002,
     "train_loss": 0.81574390725434,
     "train_runtime": 170799.3559,
     "train_samples": 1649746,

config.json

@@ -23,6 +23,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.8875364065170288,
+    "eval_runtime": 36.7278,
+    "eval_samples": 5900,
+    "eval_samples_per_second": 31.829,
+    "eval_steps_per_second": 4.002
+}