Hugging Face's logo

adeo
/
smollm2-360M-sft

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Metrics Community
adeo commited on
Commit
36ab2b7
·
verified ·
1 Parent(s): ff52835

Model save

Browse files
Files changed (8) hide show
  1. README.md +1 -1
  2. all_results.json +6 -6
  3. model.safetensors +1 -1
  4. runs/Apr18_02-59-42_36bac17fa6cd/events.out.tfevents.1744946689.36bac17fa6cd.1717.0 +3 -0
  5. tokenizer.json +6 -1
  6. train_results.json +6 -6
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/q94wllqj)
31
 
32
  This model was trained with SFT.
33
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/r1j21b7y)
31
 
32
  This model was trained with SFT.
33
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 1.9995261786306564,
3
- "total_flos": 1.174779724933628e+18,
4
- "train_loss": 1.0698493373337514,
5
- "train_runtime": 77836.8266,
6
  "train_samples": 460142,
7
- "train_samples_per_second": 1.301,
8
- "train_steps_per_second": 0.081
9
  }
 
1
  {
2
+ "epoch": 1.9999304565527312,
3
+ "total_flos": 2.2817420700811264e+18,
4
+ "train_loss": 1.0877171853494143,
5
+ "train_runtime": 174429.7906,
6
  "train_samples": 460142,
7
+ "train_samples_per_second": 5.276,
8
+ "train_steps_per_second": 0.165
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05abbb502b69a004c24f32e108475eeeb2694852026cd58bdcfe3319c9665216
3
  size 723674912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282e370c4ee3bab93b7de4c087acca4077e3622f4dd269ae8078de26a17fcd2c
3
  size 723674912
runs/Apr18_02-59-42_36bac17fa6cd/events.out.tfevents.1744946689.36bac17fa6cd.1717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdeaeeee1f2c65ad7d94a26c705d624d3efea1c3a4ab036b3e59237564dd540d
3
+ size 1229967
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 8192,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 1.9995261786306564,
3
- "total_flos": 1.174779724933628e+18,
4
- "train_loss": 1.0698493373337514,
5
- "train_runtime": 77836.8266,
6
  "train_samples": 460142,
7
- "train_samples_per_second": 1.301,
8
- "train_steps_per_second": 0.081
9
  }
 
1
  {
2
+ "epoch": 1.9999304565527312,
3
+ "total_flos": 2.2817420700811264e+18,
4
+ "train_loss": 1.0877171853494143,
5
+ "train_runtime": 174429.7906,
6
  "train_samples": 460142,
7
+ "train_samples_per_second": 5.276,
8
+ "train_steps_per_second": 0.165
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9807ad48581fd1f16b2eb8e994fec16526cdca9d9f278e4cbce52b1e8fd15cf
3
  size 6904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b9f596fe8de5045e96083e46cdbdecf1d0836e24fc2227a02ac8eb45ea7466
3
  size 6904