End of training
Browse files
README.md
CHANGED
|
@@ -2,11 +2,19 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: HuggingFaceTB/SmolLM-1.7B
|
| 4 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: smollm-1.7B-instruct-v2
|
| 12 |
results: []
|
|
@@ -18,7 +26,7 @@ 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/e42pq2ir)
|
| 19 |
# smollm-1.7B-instruct-v2
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.0153
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: HuggingFaceTB/SmolLM-1.7B
|
| 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/everyday-topics-MT-conversations-H4
|
| 17 |
+
- HuggingFaceTB/instruct-data-basics-H4
|
| 18 |
model-index:
|
| 19 |
- name: smollm-1.7B-instruct-v2
|
| 20 |
results: []
|
|
|
|
| 26 |
[<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/e42pq2ir)
|
| 27 |
# smollm-1.7B-instruct-v2
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B) on the HuggingFaceTB/Magpie-Pro-300K-Filtered-H4, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/OpenHermes-2.5-H4, the HuggingFaceTB/everyday-topics-MT-conversations-H4 and the HuggingFaceTB/instruct-data-basics-H4 datasets.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
- Loss: 1.0153
|
| 32 |
|
all_results.json
CHANGED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"total_flos": 129231539404800.0,
|
| 4 |
"train_loss": 0.7394485170879062,
|
| 5 |
"train_runtime": 1679.86,
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.0153491497039795,
|
| 4 |
+
"eval_runtime": 98.3715,
|
| 5 |
+
"eval_samples": 82731,
|
| 6 |
+
"eval_samples_per_second": 213.395,
|
| 7 |
+
"eval_steps_per_second": 6.669,
|
| 8 |
"total_flos": 129231539404800.0,
|
| 9 |
"train_loss": 0.7394485170879062,
|
| 10 |
"train_runtime": 1679.86,
|
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": 1.0153491497039795,
|
| 4 |
+
"eval_runtime": 98.3715,
|
| 5 |
+
"eval_samples": 82731,
|
| 6 |
+
"eval_samples_per_second": 213.395,
|
| 7 |
+
"eval_steps_per_second": 6.669
|
| 8 |
+
}
|
runs/Aug23_10-05-42_ip-26-0-167-245/events.out.tfevents.1724410027.ip-26-0-167-245.868311.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34a379fedd9330e80b58e7f09e589b6365438c4d54278d4de93ecf1c07a10c6e
|
| 3 |
+
size 359
|