End of training
Browse files
README.md
CHANGED
@@ -2,11 +2,18 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: HuggingFaceTB/SmolLM-360M
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
|
|
|
|
|
|
10 |
model-index:
|
11 |
- name: smollm-350M-instruct-test2
|
12 |
results: []
|
@@ -18,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/3q0xqph6)
|
19 |
# smollm-350M-instruct-test2
|
20 |
|
21 |
-
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 1.2029
|
24 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: HuggingFaceTB/SmolLM-360M
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- generated_from_trainer
|
12 |
datasets:
|
13 |
+
- HuggingFaceTB/Magpie-Pro-300K-Filtered-H4
|
14 |
+
- HuggingFaceTB/self-oss-instruct-sc2-H4
|
15 |
+
- HuggingFaceTB/OpenHermes-2.5-H4
|
16 |
+
- HuggingFaceTB/instruct-data-basics-H4
|
17 |
model-index:
|
18 |
- name: smollm-350M-instruct-test2
|
19 |
results: []
|
|
|
25 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/3q0xqph6)
|
26 |
# smollm-350M-instruct-test2
|
27 |
|
28 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the HuggingFaceTB/Magpie-Pro-300K-Filtered-H4, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/OpenHermes-2.5-H4 and the HuggingFaceTB/instruct-data-basics-H4 datasets.
|
29 |
It achieves the following results on the evaluation set:
|
30 |
- Loss: 1.2029
|
31 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 80063181619200.0,
|
4 |
"train_loss": 0.9145085595402063,
|
5 |
"train_runtime": 1902.7506,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.202902913093567,
|
4 |
+
"eval_runtime": 110.377,
|
5 |
+
"eval_samples": 82612,
|
6 |
+
"eval_samples_per_second": 189.723,
|
7 |
+
"eval_steps_per_second": 5.934,
|
8 |
"total_flos": 80063181619200.0,
|
9 |
"train_loss": 0.9145085595402063,
|
10 |
"train_runtime": 1902.7506,
|
config.json
CHANGED
@@ -25,6 +25,6 @@
|
|
25 |
"tie_word_embeddings": true,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.42.3",
|
28 |
-
"use_cache":
|
29 |
"vocab_size": 49152
|
30 |
}
|
|
|
25 |
"tie_word_embeddings": true,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.42.3",
|
28 |
+
"use_cache": true,
|
29 |
"vocab_size": 49152
|
30 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.202902913093567,
|
4 |
+
"eval_runtime": 110.377,
|
5 |
+
"eval_samples": 82612,
|
6 |
+
"eval_samples_per_second": 189.723,
|
7 |
+
"eval_steps_per_second": 5.934
|
8 |
+
}
|
runs/Aug12_13-29-20_ip-26-0-165-24/events.out.tfevents.1723471980.ip-26-0-165-24.482336.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c59ec58c933c0ff51aba54786c8ed9c2338a5c0e93c45c635888da371279df15
|
3 |
+
size 359
|