loubnabnl HF staff commited on
Commit
0693ae2
1 Parent(s): 20e85a3

End of training

Browse files
README.md CHANGED
@@ -1,9 +1,15 @@
1
  ---
2
  base_model: HuggingFaceTB/cosmo2-1.7B-webinst-sc2
3
  tags:
 
4
  - trl
5
  - dpo
6
  - generated_from_trainer
 
 
 
 
 
7
  model-index:
8
  - name: cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
9
  results: []
@@ -15,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
15
  [<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/xzcjqvtn)
16
  # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
17
 
18
- This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on an unknown dataset.
 
 
 
 
 
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
1
  ---
2
  base_model: HuggingFaceTB/cosmo2-1.7B-webinst-sc2
3
  tags:
4
+ - alignment-handbook
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
+ - trl
9
+ - dpo
10
+ - generated_from_trainer
11
+ datasets:
12
+ - HuggingFaceTB/Helpsteer
13
  model-index:
14
  - name: cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
15
  results: []
 
21
  [<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/xzcjqvtn)
22
  # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
23
 
24
+ This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.6675
27
+ - Rewards/chosen: -0.0462
28
+ - Rewards/rejected: -0.0926
29
+ - Rewards/accuracies: 0.5667
30
+ - Rewards/margins: 0.0464
31
+ - Logps/rejected: -149.4179
32
+ - Logps/chosen: -121.9775
33
+ - Logits/rejected: 0.8652
34
+ - Logits/chosen: 0.9563
35
 
36
  ## Model description
37
 
all_results.json CHANGED
@@ -1,5 +1,18 @@
1
  {
2
  "epoch": 0.9872958257713249,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "total_flos": 0.0,
4
  "train_loss": 0.6753217893488267,
5
  "train_runtime": 321.7901,
 
1
  {
2
  "epoch": 0.9872958257713249,
3
+ "eval_logits/chosen": 0.9563044309616089,
4
+ "eval_logits/rejected": 0.865182638168335,
5
+ "eval_logps/chosen": -121.97750854492188,
6
+ "eval_logps/rejected": -149.4178924560547,
7
+ "eval_loss": 0.6674867272377014,
8
+ "eval_rewards/accuracies": 0.5666666626930237,
9
+ "eval_rewards/chosen": -0.04618287831544876,
10
+ "eval_rewards/margins": 0.046417996287345886,
11
+ "eval_rewards/rejected": -0.09260086715221405,
12
+ "eval_runtime": 4.5645,
13
+ "eval_samples": 464,
14
+ "eval_samples_per_second": 101.654,
15
+ "eval_steps_per_second": 3.286,
16
  "total_flos": 0.0,
17
  "train_loss": 0.6753217893488267,
18
  "train_runtime": 321.7901,
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 ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9872958257713249,
3
+ "eval_logits/chosen": 0.9563044309616089,
4
+ "eval_logits/rejected": 0.865182638168335,
5
+ "eval_logps/chosen": -121.97750854492188,
6
+ "eval_logps/rejected": -149.4178924560547,
7
+ "eval_loss": 0.6674867272377014,
8
+ "eval_rewards/accuracies": 0.5666666626930237,
9
+ "eval_rewards/chosen": -0.04618287831544876,
10
+ "eval_rewards/margins": 0.046417996287345886,
11
+ "eval_rewards/rejected": -0.09260086715221405,
12
+ "eval_runtime": 4.5645,
13
+ "eval_samples": 464,
14
+ "eval_samples_per_second": 101.654,
15
+ "eval_steps_per_second": 3.286
16
+ }
runs/Jul15_23-02-15_ip-26-0-175-34/events.out.tfevents.1721085077.ip-26-0-175-34.1294397.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038d227d30387508a3dd8bb86a277ae6c97ddc940005a81c01cc74689ec17040
3
+ size 815