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: 2.1486
+- Loss: 2.1431
 
 ## Model description
 
@@ -40,13 +39,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0004
-- train_batch_size: 8
+- learning_rate: 0.0002
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -56,8 +55,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 2.1002        | 1.0   | 5390  | 2.1550          |
-| 2.0952        | 2.0   | 10780 | 2.1486          |
+| 2.1473        | 1.0   | 5904  | 2.1471          |
+| 2.1311        | 2.0   | 11808 | 2.1431          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f38a25a509f9f55ad8f422b6ee32bf204854b80b006ff35978c16d931c39c11
+oid sha256:af885d31489c18da260b57918756f5a4f9581c887b18c9d6862be26a8fa2e2a8
 size 25272360

all_results.json

@@ -1,13 +1,8 @@
 {
     "epoch": 2.0,
-    "eval_loss": 2.1485531330108643,
-    "eval_runtime": 170.3607,
-    "eval_samples": 6553,
-    "eval_samples_per_second": 28.463,
-    "eval_steps_per_second": 3.563,
-    "train_loss": 2.151964877841645,
-    "train_runtime": 21635.5911,
+    "train_loss": 2.1527459967507903,
+    "train_runtime": 22011.903,
     "train_samples": 116722,
-    "train_samples_per_second": 7.971,
-    "train_steps_per_second": 0.498
+    "train_samples_per_second": 4.292,
+    "train_steps_per_second": 0.536
 }

runs/May05_11-48-00_poseidon/events.out.tfevents.1714909696.poseidon.1464519.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f6cecb15cba8e0b57d27408333763af3b35b23e3ee895e99fd1f6589b23627
-size 503622
+oid sha256:18076ceccfe3ba634963dea3413f99bbd5ae3c8258096f6e40949ca2a1237a17
+size 504458

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
-    "train_loss": 2.151964877841645,
-    "train_runtime": 21635.5911,
+    "train_loss": 2.1527459967507903,
+    "train_runtime": 22011.903,
     "train_samples": 116722,
-    "train_samples_per_second": 7.971,
-    "train_steps_per_second": 0.498
+    "train_samples_per_second": 4.292,
+    "train_steps_per_second": 0.536
 }