End of training
Browse files
README.md
CHANGED
@@ -3,9 +3,15 @@ library_name: transformers
|
|
3 |
license: llama3.1
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
5 |
tags:
|
|
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: barc-llama3.1-8b-instruct-fft-transduction-gpt4omini20k_lr1e-5_epoch2
|
11 |
results: []
|
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# barc-llama3.1-8b-instruct-fft-transduction-gpt4omini20k_lr1e-5_epoch2
|
18 |
|
19 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.0623
|
22 |
|
|
|
3 |
license: llama3.1
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
5 |
tags:
|
6 |
+
- alignment-handbook
|
7 |
- trl
|
8 |
- sft
|
9 |
- generated_from_trainer
|
10 |
+
- trl
|
11 |
+
- sft
|
12 |
+
- generated_from_trainer
|
13 |
+
datasets:
|
14 |
+
- barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
|
15 |
model-index:
|
16 |
- name: barc-llama3.1-8b-instruct-fft-transduction-gpt4omini20k_lr1e-5_epoch2
|
17 |
results: []
|
|
|
22 |
|
23 |
# barc-llama3.1-8b-instruct-fft-transduction-gpt4omini20k_lr1e-5_epoch2
|
24 |
|
25 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
- Loss: 0.0623
|
28 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.993127147766323,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 8.781509506919629e+16,
|
4 |
"train_loss": 0.08342721785964637,
|
5 |
"train_runtime": 7557.4748,
|
|
|
1 |
{
|
2 |
"epoch": 1.993127147766323,
|
3 |
+
"eval_loss": 0.06226445734500885,
|
4 |
+
"eval_runtime": 107.317,
|
5 |
+
"eval_samples": 979,
|
6 |
+
"eval_samples_per_second": 9.123,
|
7 |
+
"eval_steps_per_second": 0.289,
|
8 |
"total_flos": 8.781509506919629e+16,
|
9 |
"train_loss": 0.08342721785964637,
|
10 |
"train_runtime": 7557.4748,
|
config.json
CHANGED
@@ -35,6 +35,6 @@
|
|
35 |
"tie_word_embeddings": false,
|
36 |
"torch_dtype": "bfloat16",
|
37 |
"transformers_version": "4.45.0.dev0",
|
38 |
-
"use_cache":
|
39 |
"vocab_size": 128256
|
40 |
}
|
|
|
35 |
"tie_word_embeddings": false,
|
36 |
"torch_dtype": "bfloat16",
|
37 |
"transformers_version": "4.45.0.dev0",
|
38 |
+
"use_cache": true,
|
39 |
"vocab_size": 128256
|
40 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.993127147766323,
|
3 |
+
"eval_loss": 0.06226445734500885,
|
4 |
+
"eval_runtime": 107.317,
|
5 |
+
"eval_samples": 979,
|
6 |
+
"eval_samples_per_second": 9.123,
|
7 |
+
"eval_steps_per_second": 0.289
|
8 |
+
}
|
runs/Sep23_06-23-32_ellis-compute-02.cs.cornell.edu/events.out.tfevents.1727094889.ellis-compute-02.cs.cornell.edu.2485545.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33bbd2ce248af6a12e0f7d1f8e844c99a43df34e19c27e5f840e1e9b348c4f72
|
3 |
+
size 359
|