End of training

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 trainer_log.jsonl filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- prefix-tuning
 - generated_from_trainer
 model-index:
 - name: train_sst2_1755694489
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_sst2_1755694489
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the sst2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1429
-- Num Input Tokens Seen: 29056064
+- Loss: 0.1434
+- Num Input Tokens Seen: 30587136
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.1433778703212738,
+    "eval_runtime": 103.7534,
+    "eval_samples_per_second": 64.914,
+    "eval_steps_per_second": 32.462,
+    "num_input_tokens_seen": 30587136,
+    "total_flos": 1.3773249096733164e+18,
+    "train_loss": 0.10993818389397388,
+    "train_runtime": 27429.5461,
+    "train_samples_per_second": 22.098,
+    "train_steps_per_second": 11.049
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.1433778703212738,
+    "eval_runtime": 103.7534,
+    "eval_samples_per_second": 64.914,
+    "eval_steps_per_second": 32.462,
+    "num_input_tokens_seen": 30587136
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 30587136,
+    "total_flos": 1.3773249096733164e+18,
+    "train_loss": 0.10993818389397388,
+    "train_runtime": 27429.5461,
+    "train_samples_per_second": 22.098,
+    "train_steps_per_second": 11.049
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b3e0ba09e3bdc3d1c20976c9a4e618ceb1c3b8c3ce2b84b167b6209df1aab0
+size 13175929