statking commited on
Commit
bb643ee
1 Parent(s): 198add3

End of training

Browse files
Files changed (4) hide show
  1. README.md +3 -2
  2. all_results.json +5 -0
  3. config.json +26 -0
  4. eval_results.json +8 -0
README.md CHANGED
@@ -2,12 +2,13 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: mistralai/Mistral-7B-v0.1
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: zephyr-7b-sft-qdora
13
  results: []
@@ -19,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
19
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/md7eikah)
20
  # zephyr-7b-sft-qdora
21
 
22
- 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.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 0.9432
25
 
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: mistralai/Mistral-7B-v0.1
10
  datasets:
11
+ - HuggingFaceH4/ultrachat_200k
12
  model-index:
13
  - name: zephyr-7b-sft-qdora
14
  results: []
 
20
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/md7eikah)
21
  # zephyr-7b-sft-qdora
22
 
23
+ 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.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 0.9432
26
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "total_flos": 5.850946088416051e+16,
4
  "train_loss": 0.9513995123872411,
5
  "train_runtime": 53950.0033,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.9432145357131958,
4
+ "eval_runtime": 1411.7173,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 10.931,
7
+ "eval_steps_per_second": 0.086,
8
  "total_flos": 5.850946088416051e+16,
9
  "train_loss": 0.9513995123872411,
10
  "train_runtime": 53950.0033,
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.41.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9432145357131958,
4
+ "eval_runtime": 1411.7173,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 10.931,
7
+ "eval_steps_per_second": 0.086
8
+ }