ShenaoZ commited on
Commit
3118301
·
verified ·
1 Parent(s): 93869ed

Model save

Browse files
README.md CHANGED
@@ -2,13 +2,9 @@
2
  license: mit
3
  base_model: HuggingFaceH4/mistral-7b-sft-beta
4
  tags:
5
- - alignment-handbook
6
- - generated_from_trainer
7
  - trl
8
  - dpo
9
  - generated_from_trainer
10
- datasets:
11
- - HuggingFaceH4/ultrafeedback_binarized
12
  model-index:
13
  - name: 0.000001_ablation_iter_1
14
  results: []
@@ -19,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # 0.000001_ablation_iter_1
21
 
22
- This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
23
 
24
  ## Model description
25
 
 
2
  license: mit
3
  base_model: HuggingFaceH4/mistral-7b-sft-beta
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
8
  model-index:
9
  - name: 0.000001_ablation_iter_1
10
  results: []
 
15
 
16
  # 0.000001_ablation_iter_1
17
 
18
+ This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
19
 
20
  ## Model description
21
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6063382550605438,
4
- "train_runtime": 2621.152,
5
  "train_samples": 20378,
6
- "train_samples_per_second": 7.774,
7
  "train_steps_per_second": 0.061
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6063382550605438,
4
+ "train_runtime": 2620.7563,
5
  "train_samples": 20378,
6
+ "train_samples_per_second": 7.776,
7
  "train_steps_per_second": 0.061
8
  }
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.36.2",
24
- "use_cache": true,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.36.2",
24
+ "use_cache": false,
25
  "vocab_size": 32000
26
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6063382550605438,
4
- "train_runtime": 2621.152,
5
  "train_samples": 20378,
6
- "train_samples_per_second": 7.774,
7
  "train_steps_per_second": 0.061
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6063382550605438,
4
+ "train_runtime": 2620.7563,
5
  "train_samples": 20378,
6
+ "train_samples_per_second": 7.776,
7
  "train_steps_per_second": 0.061
8
  }
trainer_state.json CHANGED
@@ -237,8 +237,8 @@
237
  "step": 159,
238
  "total_flos": 0.0,
239
  "train_loss": 0.6063382550605438,
240
- "train_runtime": 2621.152,
241
- "train_samples_per_second": 7.774,
242
  "train_steps_per_second": 0.061
243
  }
244
  ],
 
237
  "step": 159,
238
  "total_flos": 0.0,
239
  "train_loss": 0.6063382550605438,
240
+ "train_runtime": 2620.7563,
241
+ "train_samples_per_second": 7.776,
242
  "train_steps_per_second": 0.061
243
  }
244
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e65ab24a0e7545b465769e75de873282fdf1f177734c418bc7903471ad0aab2b
3
  size 6008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7a5f8d3c75ccc234c425ace0efd4a1eae2ef95c8362ae223710beac1d8c2f60
3
  size 6008