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: 2.2356
+- Loss: 2.1637
 
 ## Model description
 
@@ -40,23 +39,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6.35e-05
+- learning_rate: 0.0004
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2321        | 1.0   | 670  | 2.2356          |
+| 2.1729        | 1.0   | 1340 | 2.1778          |
+| 2.1327        | 2.0   | 2681 | 2.1632          |
+| 2.0989        | 3.0   | 4020 | 2.1637          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d7f5577fde7427d431fbd421e7834d5ebdb6f211830165cb775a194bd9e619
+oid sha256:a01995d6e4587c3194bf004a92ba178f15cd3c362591b2794519ccd38f3497cb
 size 25272360

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 1.0,
-    "eval_loss": 2.2356441020965576,
-    "eval_runtime": 186.9806,
-    "eval_samples": 6553,
-    "eval_samples_per_second": 25.789,
-    "eval_steps_per_second": 3.225,
-    "train_loss": 2.275535515884855,
-    "train_runtime": 10859.5951,
+    "epoch": 3.0,
+    "train_loss": 2.1598364234563725,
+    "train_runtime": 32657.7671,
     "train_samples": 116722,
-    "train_samples_per_second": 7.898,
-    "train_steps_per_second": 0.062
+    "train_samples_per_second": 7.879,
+    "train_steps_per_second": 0.123
 }

runs/May02_12-16-28_poseidon/events.out.tfevents.1714652205.poseidon.496628.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d1ebfb8ebeddb638baca56fc89700840e61e0baede73289f97dc3051651ace
-size 174733
+oid sha256:3de099420468f8d02ca68a8f8179707aef426ee6939d3e04027817dfe64ed615
+size 176202

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "train_loss": 2.275535515884855,
-    "train_runtime": 10859.5951,
+    "epoch": 3.0,
+    "train_loss": 2.1598364234563725,
+    "train_runtime": 32657.7671,
     "train_samples": 116722,
-    "train_samples_per_second": 7.898,
-    "train_steps_per_second": 0.062
+    "train_samples_per_second": 7.879,
+    "train_steps_per_second": 0.123
 }