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-claude3sonnet-64k
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-summarize-claude3sonnet-64k
 
-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: 2.6980
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 9.975062344139651,
+    "eval_loss": 2.6979904174804688,
+    "eval_runtime": 0.4899,
+    "eval_samples": 25,
+    "eval_samples_per_second": 20.411,
+    "eval_steps_per_second": 2.041,
     "total_flos": 1.1920978083462513e+18,
     "train_loss": 0.9040022449493408,
     "train_runtime": 12134.7289,

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": "4.40.0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 14.962593516209477,
-    "eval_loss": 2.542728900909424,
-    "eval_runtime": 0.4882,
+    "epoch": 9.975062344139651,
+    "eval_loss": 2.6979904174804688,
+    "eval_runtime": 0.4899,
     "eval_samples": 25,
-    "eval_samples_per_second": 20.483,
-    "eval_steps_per_second": 2.048
+    "eval_samples_per_second": 20.411,
+    "eval_steps_per_second": 2.041
 }

runs/Jun10_15-41-34_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718013857.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.10374.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78851d81bdc6bb6ef0a6cfed275f43cf71a00ce9bfe86f8cab0a73d106d4f176
+size 359