EllieS commited on
Commit
f5461fe
1 Parent(s): 20bd7ae

End of training

Browse files
README.md CHANGED
@@ -2,10 +2,13 @@
2
  license: other
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
  base_model: meta-llama/Meta-Llama-3-8B
 
 
9
  model-index:
10
  - name: llama3-L1-SFT-L2-DPO
11
  results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # llama3-L1-SFT-L2-DPO
18
 
19
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.0028
22
  - Rewards/chosen: -0.4016
 
2
  license: other
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
  base_model: meta-llama/Meta-Llama-3-8B
10
+ datasets:
11
+ - EllieS/Temp-L2-DPO
12
  model-index:
13
  - name: llama3-L1-SFT-L2-DPO
14
  results: []
 
19
 
20
  # llama3-L1-SFT-L2-DPO
21
 
22
+ This model is a fine-tuned version of [EllieS/TempReason-L1-llama3](https://huggingface.co/EllieS/TempReason-L1-llama3) on the EllieS/Temp-L2-DPO dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 0.0028
25
  - Rewards/chosen: -0.4016
all_results.json CHANGED
@@ -1,5 +1,18 @@
1
  {
2
  "epoch": 0.9999375663357682,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "total_flos": 0.0,
4
  "train_loss": 0.05122942747121405,
5
  "train_runtime": 6577.5594,
 
1
  {
2
  "epoch": 0.9999375663357682,
3
+ "eval_logits/chosen": 0.6540641784667969,
4
+ "eval_logits/rejected": 1.569779634475708,
5
+ "eval_logps/chosen": -84.51407623291016,
6
+ "eval_logps/rejected": -994.2071533203125,
7
+ "eval_loss": 0.00282670627348125,
8
+ "eval_rewards/accuracies": 1.0,
9
+ "eval_rewards/chosen": -0.40158194303512573,
10
+ "eval_rewards/margins": 8.929591178894043,
11
+ "eval_rewards/rejected": -9.33117389678955,
12
+ "eval_runtime": 0.6352,
13
+ "eval_samples": 5,
14
+ "eval_samples_per_second": 7.871,
15
+ "eval_steps_per_second": 7.871,
16
  "total_flos": 0.0,
17
  "train_loss": 0.05122942747121405,
18
  "train_runtime": 6577.5594,
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": true,
27
+ "vocab_size": 128256
28
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9999375663357682,
3
+ "eval_logits/chosen": 0.6540641784667969,
4
+ "eval_logits/rejected": 1.569779634475708,
5
+ "eval_logps/chosen": -84.51407623291016,
6
+ "eval_logps/rejected": -994.2071533203125,
7
+ "eval_loss": 0.00282670627348125,
8
+ "eval_rewards/accuracies": 1.0,
9
+ "eval_rewards/chosen": -0.40158194303512573,
10
+ "eval_rewards/margins": 8.929591178894043,
11
+ "eval_rewards/rejected": -9.33117389678955,
12
+ "eval_runtime": 0.6352,
13
+ "eval_samples": 5,
14
+ "eval_samples_per_second": 7.871,
15
+ "eval_steps_per_second": 7.871
16
+ }
runs/May10_08-42-30_612e66badb5c/events.out.tfevents.1715337276.612e66badb5c.57653.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc6331638ff561cca8f8b1b41a8024b40d531cbc7ad47921154041da9497b2b
3
+ size 828