Hugging Face's logo

RedMist137
/
DPO-Zephyr-7B

Safetensors
mistral
trl
dpo
Generated from Trainer
Model card Files
xet
Community
RedMist137 commited on
Commit
80ce57b
·
verified ·
1 Parent(s): 26b48a7

Model save

Browse files
Files changed (9) hide show
  1. README.md +1 -9
  2. all_results.json +6 -6
  3. config.json +2 -2
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. train_results.json +6 -6
  8. trainer_state.json +0 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -1,16 +1,8 @@
1
  ---
2
- license: mit
3
- base_model: HuggingFaceH4/mistral-7b-sft-beta
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - dpo
8
  - generated_from_trainer
9
- - trl
10
- - dpo
11
- - generated_from_trainer
12
- datasets:
13
- - RedMist137/Temp_AIHF
14
  model-index:
15
  - name: DPO-Zephyr-7B
16
  results: []
@@ -21,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  # DPO-Zephyr-7B
23
 
24
- This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the RedMist137/Temp_AIHF dataset.
25
 
26
  ## Model description
27
 
 
1
  ---
 
 
2
  tags:
 
3
  - trl
4
  - dpo
5
  - generated_from_trainer
 
 
 
 
 
6
  model-index:
7
  - name: DPO-Zephyr-7B
8
  results: []
 
13
 
14
  # DPO-Zephyr-7B
15
 
16
+ This model was trained from scratch on the None dataset.
17
 
18
  ## Model description
19
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.9993235625704623,
3
  "total_flos": 0.0,
4
- "train_loss": 0.6513021779835009,
5
- "train_runtime": 4537.7195,
6
- "train_samples": 35474,
7
- "train_samples_per_second": 7.818,
8
- "train_steps_per_second": 0.061
9
  }
 
1
  {
2
+ "epoch": 0.9935483870967742,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.6444497665801605,
5
+ "train_runtime": 1967.4135,
6
+ "train_samples": 9919,
7
+ "train_samples_per_second": 5.042,
8
+ "train_steps_per_second": 0.039
9
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
- "use_cache": true,
25
  "vocab_size": 32000
26
  }
 
1
  {
2
+ "_name_or_path": "/root/AIHF/IRL_Alignment_Project-master/AIHF_7B_code/data/AIHF_Mixed/checkpoint-200",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
+ "use_cache": false,
25
  "vocab_size": 32000
26
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5f179c427e1375727182574bc3a342b4caad2d6cd5f2069b3aa86ec52532fd4
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fafee4b8739243c35d15355c24548d39ea759f55ef9dfea2fd40e2b5189d2f6
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b624de65f7536e9d6ea0c2e0d27e3c8780ff109ea9e023473b5b772cefe86af
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9adf34d53485e3101610c90c2dceae5a7fb3097c0ed89b64b22016df3b498e84
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e548873358e30afd5304f376998d717d3306d3673b19b984a392ff738ead249
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacde297b3b77825ebb9a21c1e9850b2c1e61f51fa37be38b6bff65c7752137a
3
  size 4540516344
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.9993235625704623,
3
  "total_flos": 0.0,
4
- "train_loss": 0.6513021779835009,
5
- "train_runtime": 4537.7195,
6
- "train_samples": 35474,
7
- "train_samples_per_second": 7.818,
8
- "train_steps_per_second": 0.061
9
  }
 
1
  {
2
+ "epoch": 0.9935483870967742,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.6444497665801605,
5
+ "train_runtime": 1967.4135,
6
+ "train_samples": 9919,
7
+ "train_samples_per_second": 5.042,
8
+ "train_steps_per_second": 0.039
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:ffe33828a9d95943556f7447e05c9e5aa5a55fbf161b8aabd3cfce9a619b452f
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb119e4359a89a9bd0ada30f62936f3daa245d3bfcbca9ffe14a1454a531247f
3
  size 6264