Model save

README.md

@@ -1,11 +1,10 @@
 ---
 base_model: facebook/opt-350m
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 library_name: peft
 license: other
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -19,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt350
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the generator dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.7869
 
@@ -56,6 +55,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8289        | 0.9999 | 8068 | 1.7869          |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 0.9999380306128772,
-    "eval_loss": 1.7869231700897217,
-    "eval_runtime": 154.2674,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 92.56,
-    "eval_steps_per_second": 5.789,
-    "total_flos": 4248659495485440.0,
-    "train_loss": 0.0,
-    "train_runtime": 0.0126,
+    "total_flos": 4248917998829568.0,
+    "train_loss": 1.8640377591255577,
+    "train_runtime": 7899.8856,
     "train_samples": 207864,
-    "train_samples_per_second": 10236188.723,
-    "train_steps_per_second": 639727.105
+    "train_samples_per_second": 16.341,
+    "train_steps_per_second": 1.021
 }

runs/Nov05_11-16-57_gnode001.cluster/events.out.tfevents.1730834226.gnode001.cluster.293646.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37814a249ddf77695e7022cb35084e8c7be8ad07b98c4ef8d09ff1b42bacc74
-size 346064
+oid sha256:39ba9d18c9c4d5e0e829038940b39ac3e178cd890caad99e081b466fef5a3f7f
+size 346689

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9999380306128772,
-    "total_flos": 4248659495485440.0,
-    "train_loss": 0.0,
-    "train_runtime": 0.0126,
+    "total_flos": 4248917998829568.0,
+    "train_loss": 1.8640377591255577,
+    "train_runtime": 7899.8856,
     "train_samples": 207864,
-    "train_samples_per_second": 10236188.723,
-    "train_steps_per_second": 639727.105
+    "train_samples_per_second": 16.341,
+    "train_steps_per_second": 1.021
 }