End of training

README.md

@@ -2,12 +2,13 @@
 license: gemma
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: google/gemma-2b
 datasets:
-- generator
+- llama-duo/synth_summarize_dataset_dedup
 model-index:
 - name: gemma2b-summarize-gemini1_5flash-128k
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-summarize-gemini1_5flash-128k
 
-This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the llama-duo/synth_summarize_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.5573
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 2.5572547912597656,
+    "eval_runtime": 0.4927,
+    "eval_samples": 25,
+    "eval_samples_per_second": 20.294,
+    "eval_steps_per_second": 2.029,
     "total_flos": 1.6530423313701274e+18,
     "train_loss": 0.977329820394516,
     "train_runtime": 7126.3412,

config.json

@@ -9,7 +9,7 @@
   "eos_token_id": 1,
   "head_dim": 256,
   "hidden_act": "gelu",
-  "hidden_activation": null,
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 16384,
@@ -38,7 +38,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 15.0,
-    "eval_loss": 2.511939525604248,
-    "eval_runtime": 0.5077,
+    "epoch": 10.0,
+    "eval_loss": 2.5572547912597656,
+    "eval_runtime": 0.4927,
     "eval_samples": 25,
-    "eval_samples_per_second": 19.697,
-    "eval_steps_per_second": 1.97
+    "eval_samples_per_second": 20.294,
+    "eval_steps_per_second": 2.029
 }

runs/Jun10_07-38-05_48ddfe8e991f/events.out.tfevents.1718012254.48ddfe8e991f.245392.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a739414cdc70f292b337a52d4e75eee04fa89ce3df387f11c223fce6c45f9f0
+size 359