Model save

README.md

@@ -2,13 +2,12 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 datasets:
-- martimfasantos/openai-tldr-filtered
+- generator
 model-index:
 - name: tinyllama-1.1b-sum-sft-qlora
   results: []
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-sum-sft-qlora
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the martimfasantos/openai-tldr-filtered dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1271
+- Loss: 2.2356
 
 ## Model description
 
@@ -40,24 +39,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
+- learning_rate: 6.35e-05
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1288        | 1.0   | 2952 | 2.1320          |
-| 2.1251        | 2.0   | 5904 | 2.1271          |
+| 2.2321        | 1.0   | 670  | 2.2356          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ca33e967d67a795b21d147f448d1003ae77016f9944bb8db2188644fefbf2c
+oid sha256:22a8a7c2fae54e7e1fb04a3e6ddf98dcb845a0117c116e7df8ad179f4b8e31de
 size 25272360

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 2.12707781791687,
-    "eval_runtime": 173.5137,
-    "eval_samples": 6553,
-    "eval_samples_per_second": 7.654,
-    "eval_steps_per_second": 0.957,
-    "train_loss": 2.1395558682560596,
-    "train_runtime": 23055.2544,
+    "epoch": 1.0,
+    "train_loss": 2.275535515884855,
+    "train_runtime": 10859.5951,
     "train_samples": 116722,
-    "train_samples_per_second": 2.049,
-    "train_steps_per_second": 0.256
+    "train_samples_per_second": 7.898,
+    "train_steps_per_second": 0.062
 }

runs/May02_00-07-24_poseidon/events.out.tfevents.1714608457.poseidon.372487.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd65e487baa6187d0cb6963090c0d1bd0cbba9d1bff29e9f007dcee0c044797
-size 30713
+oid sha256:da704a700ec5529bd24c5e369c72aaa422f9818a86c3f08c6e994971cf2bcdc5
+size 34292

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "train_loss": 2.1395558682560596,
-    "train_runtime": 23055.2544,
+    "epoch": 1.0,
+    "train_loss": 2.275535515884855,
+    "train_runtime": 10859.5951,
     "train_samples": 116722,
-    "train_samples_per_second": 2.049,
-    "train_steps_per_second": 0.256
+    "train_samples_per_second": 7.898,
+    "train_steps_per_second": 0.062
 }