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: 2.1440
+- Loss: 2.1479
 
 ## Model description
 
@@ -40,24 +39,26 @@ 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
-- num_epochs: 2
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 2.1266        | 1.0   | 5403  | 2.1504          |
-| 2.1084        | 2.0   | 10806 | 2.1440          |
+| 2.1066        | 1.0   | 10792 | 2.1614          |
+| 2.144         | 2.0   | 21584 | 2.1491          |
+| 2.1212        | 3.0   | 32376 | 2.1476          |
+| 2.0543        | 4.0   | 43168 | 2.1479          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822b959609d94aa7419802e2f55c86eb9b1684ef005106ac3ff32a70c5363c90
+oid sha256:f4c1a3caa3685a65acbe6d90ee1bba0f15b694282fd68a959427c61afb59b1e9
 size 25272360

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 2.1439597606658936,
-    "eval_runtime": 190.2983,
-    "eval_samples": 6553,
-    "eval_samples_per_second": 25.555,
-    "eval_steps_per_second": 3.195,
-    "train_loss": 2.1470370752908954,
-    "train_runtime": 23954.8129,
+    "epoch": 4.0,
+    "train_loss": 2.0942285917837413,
+    "train_runtime": 51337.8051,
     "train_samples": 116722,
-    "train_samples_per_second": 7.217,
-    "train_steps_per_second": 0.451
+    "train_samples_per_second": 6.727,
+    "train_steps_per_second": 0.841
 }

runs/May04_00-40-05_poseidon/events.out.tfevents.1714783215.poseidon.1378242.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3d02674f5341791eac668be4751c1ab670ad8cd0ff8619d114834e116d513c
-size 1812542
+oid sha256:6c33a15ea2d21cc3c25c70c4331e3dd45282e0f3150270b51126984a03fefed5
+size 1815973

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "train_loss": 2.1470370752908954,
-    "train_runtime": 23954.8129,
+    "epoch": 4.0,
+    "train_loss": 2.0942285917837413,
+    "train_runtime": 51337.8051,
     "train_samples": 116722,
-    "train_samples_per_second": 7.217,
-    "train_steps_per_second": 0.451
+    "train_samples_per_second": 6.727,
+    "train_steps_per_second": 0.841
 }