loubnabnl HF staff commited on
Commit
8d12e5b
1 Parent(s): a6ad044

End of training

Browse files
README.md CHANGED
@@ -2,12 +2,17 @@
2
  license: apache-2.0
3
  base_model: HuggingFaceTB/SmolLM-360M
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - alignment-handbook
8
  - generated_from_trainer
9
  datasets:
10
- - generator
 
11
  model-index:
12
  - name: smollm-350M-instruct-add-basics-only
13
  results: []
@@ -19,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
19
  [<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/6sdxeci4)
20
  # smollm-350M-instruct-add-basics-only
21
 
22
- This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the generator dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 1.4730
25
 
 
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
  - alignment-handbook
12
  - generated_from_trainer
13
  datasets:
14
+ - HuggingFaceTB/everyday-topics-MT-conversations-H4
15
+ - HuggingFaceTB/instruct-data-basics-H4
16
  model-index:
17
  - name: smollm-350M-instruct-add-basics-only
18
  results: []
 
24
  [<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/6sdxeci4)
25
  # smollm-350M-instruct-add-basics-only
26
 
27
+ This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the HuggingFaceTB/everyday-topics-MT-conversations-H4 and the HuggingFaceTB/instruct-data-basics-H4 datasets.
28
  It achieves the following results on the evaluation set:
29
  - Loss: 1.4730
30
 
all_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 2.857142857142857,
3
- "eval_loss": 2.1008596420288086,
4
- "eval_runtime": 0.1817,
5
  "eval_samples": 119,
6
- "eval_samples_per_second": 60.549,
7
- "eval_steps_per_second": 5.504,
8
  "total_flos": 466196889600.0,
9
  "train_loss": 2.3683324337005613,
10
  "train_runtime": 24.8838,
 
1
  {
2
  "epoch": 2.857142857142857,
3
+ "eval_loss": 1.4730318784713745,
4
+ "eval_runtime": 0.1815,
5
  "eval_samples": 119,
6
+ "eval_samples_per_second": 60.611,
7
+ "eval_steps_per_second": 5.51,
8
  "total_flos": 466196889600.0,
9
  "train_loss": 2.3683324337005613,
10
  "train_runtime": 24.8838,
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": false,
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 CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.7142857142857144,
3
- "eval_loss": 2.1008596420288086,
4
- "eval_runtime": 0.1817,
5
  "eval_samples": 119,
6
- "eval_samples_per_second": 60.549,
7
- "eval_steps_per_second": 5.504
8
  }
 
1
  {
2
+ "epoch": 2.857142857142857,
3
+ "eval_loss": 1.4730318784713745,
4
+ "eval_runtime": 0.1815,
5
  "eval_samples": 119,
6
+ "eval_samples_per_second": 60.611,
7
+ "eval_steps_per_second": 5.51
8
  }
runs/Aug13_00-20-24_ip-26-0-161-138/events.out.tfevents.1723508499.ip-26-0-161-138.2676503.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb006eb02222ca0bcca0f19d097be96532e507fedbcb8bb700ff7c500cce9de
3
+ size 354