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](https://huggingface.co/datasets/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: 2.1764
+- Loss: 2.1271
 
 ## Model description
 
@@ -40,23 +39,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 2
+- 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
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1651        | 1.0   | 2952 | 2.1764          |
+| 2.1288        | 1.0   | 2952 | 2.1320          |
+| 2.1251        | 2.0   | 5904 | 2.1271          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e91e6d42eef97101a4fb80ad7c0ad43030ce34ae68132b2c1a714353b4bc8e9
+oid sha256:07d2235035c018cae7b4a6f0537c942cda6425b4a4296f1e9f968c60920773b8
 size 25272360

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 1.0,
-    "eval_loss": 2.1763968467712402,
-    "eval_runtime": 178.0789,
-    "eval_samples": 6553,
-    "eval_samples_per_second": 14.92,
-    "eval_steps_per_second": 1.87,
-    "train_loss": 2.200481324176478,
-    "train_runtime": 12060.097,
+    "epoch": 2.0,
+    "train_loss": 2.1395558682560596,
+    "train_runtime": 23055.2544,
     "train_samples": 116722,
-    "train_samples_per_second": 3.917,
-    "train_steps_per_second": 0.245
+    "train_samples_per_second": 2.049,
+    "train_steps_per_second": 0.256
 }

runs/May01_17-02-13_poseidon/events.out.tfevents.1714583045.poseidon.313063.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517bc6460fa780b3776df2aa42613f567858c97cd0e6d5899abde56bea98f618
-size 254642
+oid sha256:8ed99096d1d5b7cbddd2a0379e2a3a46e4b5cc0869985c9b10f5f070b7a93ec2
+size 255267

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "train_loss": 2.200481324176478,
-    "train_runtime": 12060.097,
+    "epoch": 2.0,
+    "train_loss": 2.1395558682560596,
+    "train_runtime": 23055.2544,
     "train_samples": 116722,
-    "train_samples_per_second": 3.917,
-    "train_steps_per_second": 0.245
+    "train_samples_per_second": 2.049,
+    "train_steps_per_second": 0.256
 }