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_qqp_1754652135
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_qqp_1754652135
 
-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 qqp dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1873
+- Loss: 0.1866
 - Num Input Tokens Seen: 250787112
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.18655052781105042,
+    "eval_runtime": 1568.4964,
+    "eval_samples_per_second": 23.197,
+    "eval_steps_per_second": 5.8,
+    "num_input_tokens_seen": 250787112,
+    "total_flos": 1.1292830305610564e+19,
+    "train_loss": 0.25612748204947167,
+    "train_runtime": 332664.6174,
+    "train_samples_per_second": 9.844,
+    "train_steps_per_second": 2.461
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.18655052781105042,
+    "eval_runtime": 1568.4964,
+    "eval_samples_per_second": 23.197,
+    "eval_steps_per_second": 5.8,
+    "num_input_tokens_seen": 250787112
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 250787112,
+    "total_flos": 1.1292830305610564e+19,
+    "train_loss": 0.25612748204947167,
+    "train_runtime": 332664.6174,
+    "train_samples_per_second": 9.844,
+    "train_steps_per_second": 2.461
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e72919f8ecdcbb1059dbb215fc0fc5ed6b31238b6d8a7eac82dc5d0c4d90743
+size 35553345