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
+- prompt-tuning
 - generated_from_trainer
 model-index:
 - name: train_record_123_1762842639
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_record_123_1762842639
 
-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 record dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2652
+- Loss: 0.2596
 - Num Input Tokens Seen: 928969984
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.25963324308395386,
+    "eval_runtime": 387.7605,
+    "eval_samples_per_second": 35.811,
+    "eval_steps_per_second": 8.954,
+    "num_input_tokens_seen": 928969984,
+    "total_flos": 4.183109851481427e+19,
+    "train_loss": 0.24436626470479683,
+    "train_runtime": 168643.8946,
+    "train_samples_per_second": 14.82,
+    "train_steps_per_second": 3.705
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.25963324308395386,
+    "eval_runtime": 387.7605,
+    "eval_samples_per_second": 35.811,
+    "eval_steps_per_second": 8.954,
+    "num_input_tokens_seen": 928969984
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 928969984,
+    "total_flos": 4.183109851481427e+19,
+    "train_loss": 0.24436626470479683,
+    "train_runtime": 168643.8946,
+    "train_samples_per_second": 14.82,
+    "train_steps_per_second": 3.705
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b7e535b275be9f63448e0dd146c7220ceb1f464db7a30840c1afd9de8cbab2
+size 26187701