Hugging Face's logo

NicholasCorrado
/
uf-rlced-conifer_tulu-2-7b-dpo-full

Text Generation
Transformers
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
NicholasCorrado commited on
Commit
4b85518
·
verified ·
1 Parent(s): a2803a3

End of training

Browse files
Files changed (10) hide show
  1. README.md +1 -0
  2. all_results.json +16 -3
  3. config.json +1 -1
  4. eval_results.json +16 -0
  5. model-00001-of-00003.safetensors +1 -1
  6. model-00002-of-00003.safetensors +1 -1
  7. model-00003-of-00003.safetensors +1 -1
  8. train_results.json +3 -3
  9. trainer_state.json +3 -3
  10. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,7 @@ base_model: allenai/tulu-2-7b
4
  tags:
5
  - trl
6
  - dpo
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: uf-rlced-conifer_tulu-2-7b-dpo-full
 
4
  tags:
5
  - trl
6
  - dpo
7
+ - alignment-handbook
8
  - generated_from_trainer
9
  model-index:
10
  - name: uf-rlced-conifer_tulu-2-7b-dpo-full
all_results.json CHANGED
@@ -1,9 +1,22 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "total_flos": 0.0,
4
  "train_loss": 0.1732867956161499,
5
- "train_runtime": 84.0616,
6
  "train_samples": 50,
7
- "train_samples_per_second": 0.595,
8
- "train_steps_per_second": 0.012
9
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_logits/chosen": -1.3140687942504883,
4
+ "eval_logits/rejected": -1.1924079656600952,
5
+ "eval_logps/chosen": -316.60687255859375,
6
+ "eval_logps/rejected": -434.5618896484375,
7
+ "eval_loss": 0.6931471228599548,
8
+ "eval_rewards/accuracies": 0.0,
9
+ "eval_rewards/chosen": 0.0,
10
+ "eval_rewards/margins": 0.0,
11
+ "eval_rewards/rejected": 0.0,
12
+ "eval_runtime": 2.7893,
13
+ "eval_samples": 50,
14
+ "eval_samples_per_second": 17.926,
15
+ "eval_steps_per_second": 0.359,
16
  "total_flos": 0.0,
17
  "train_loss": 0.1732867956161499,
18
+ "train_runtime": 87.5332,
19
  "train_samples": 50,
20
+ "train_samples_per_second": 0.571,
21
+ "train_steps_per_second": 0.011
22
  }
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.1",
27
- "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.1",
27
+ "use_cache": false,
28
  "vocab_size": 32000
29
  }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -1.3140687942504883,
4
+ "eval_logits/rejected": -1.1924079656600952,
5
+ "eval_logps/chosen": -316.60687255859375,
6
+ "eval_logps/rejected": -434.5618896484375,
7
+ "eval_loss": 0.6931471228599548,
8
+ "eval_rewards/accuracies": 0.0,
9
+ "eval_rewards/chosen": 0.0,
10
+ "eval_rewards/margins": 0.0,
11
+ "eval_rewards/rejected": 0.0,
12
+ "eval_runtime": 2.7893,
13
+ "eval_samples": 50,
14
+ "eval_samples_per_second": 17.926,
15
+ "eval_steps_per_second": 0.359
16
+ }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d24d8e5f2d74688b57b67cb7f3a3cb48857d7da53a2b22e41699d7baf46219
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c95f04736951a02d7c6cb951b558cf29fb57e053481302fbebed33a80389a91
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fc45a397c714c50f1b4be003342d781274dc379b7260da620ff8309ab585b2c
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e1711d017d5929a34aefa4794dfd931dbf79a78fbba2b770749c4494b84f7e
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d7ce26565acdaef2d9ccea41ce48adada2955f61faea505be4a938b95ca614b
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028796c311524c39e27ac124f54c12c67cbd03045d99e621f4bbea4052e6c8fe
3
  size 3590488816
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.1732867956161499,
5
- "train_runtime": 84.0616,
6
  "train_samples": 50,
7
- "train_samples_per_second": 0.595,
8
- "train_steps_per_second": 0.012
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 0.0,
4
  "train_loss": 0.1732867956161499,
5
+ "train_runtime": 87.5332,
6
  "train_samples": 50,
7
+ "train_samples_per_second": 0.571,
8
+ "train_steps_per_second": 0.011
9
  }
trainer_state.json CHANGED
@@ -27,9 +27,9 @@
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.1732867956161499,
30
- "train_runtime": 84.0616,
31
- "train_samples_per_second": 0.595,
32
- "train_steps_per_second": 0.012
33
  }
34
  ],
35
  "logging_steps": 10,
 
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.1732867956161499,
30
+ "train_runtime": 87.5332,
31
+ "train_samples_per_second": 0.571,
32
+ "train_steps_per_second": 0.011
33
  }
34
  ],
35
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccfb1454676649d4bdc6a930b2796dfe423c459cc6b738ae8d9140ac84ee6645
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2437447f7418506fbd2418372dedfe2ef17ea51aef679348ff1a33fd2e1503ed
3
  size 7480