happii commited on
Commit
73787bf
1 Parent(s): 340a6f6

End of training

Browse files
README.md CHANGED
@@ -2,11 +2,15 @@
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-v0.1
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  datasets:
9
- - generator
10
  model-index:
11
  - name: zephyr-7b-sft-full
12
  results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # zephyr-7b-sft-full
19
 
20
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 1.1126
23
 
 
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-v0.1
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
  - trl
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
+ - HuggingFaceH4/ultrachat_200k
14
  model-index:
15
  - name: zephyr-7b-sft-full
16
  results: []
 
21
 
22
  # zephyr-7b-sft-full
23
 
24
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 1.1126
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "total_flos": 456238269726720.0,
4
  "train_loss": 1.1632422284009862,
5
  "train_runtime": 29234.3114,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.1125566959381104,
4
+ "eval_runtime": 848.8094,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 72.71,
7
+ "eval_steps_per_second": 1.137,
8
  "total_flos": 456238269726720.0,
9
  "train_loss": 1.1632422284009862,
10
  "train_runtime": 29234.3114,
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
- "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
+ "use_cache": true,
25
  "vocab_size": 32000
26
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.9490520358085632,
4
- "eval_runtime": 757.9326,
5
  "eval_samples": 23109,
6
- "eval_samples_per_second": 20.359,
7
- "eval_steps_per_second": 0.637
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.1125566959381104,
4
+ "eval_runtime": 848.8094,
5
  "eval_samples": 23109,
6
+ "eval_samples_per_second": 72.71,
7
+ "eval_steps_per_second": 1.137
8
  }
runs/May24_19-38-16_ubuntu/events.out.tfevents.1716610591.ubuntu.2195002.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cde932c0f9dfa5b7fdc51b2ae44b14d8d0dbca98612757a36329bfa07b0bad
3
+ size 359