ale-bay commited on
Commit
c9fa5de
1 Parent(s): 364529d

End of training

Browse files
README.md CHANGED
@@ -2,12 +2,16 @@
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-qlora
13
  results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # zephyr-7b-sft-qlora
20
 
21
- 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.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.9499
24
 
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
  - trl
10
  - sft
11
  - generated_from_trainer
12
  base_model: mistralai/Mistral-7B-v0.1
13
  datasets:
14
+ - HuggingFaceH4/ultrachat_200k
15
  model-index:
16
  - name: zephyr-7b-sft-qlora
17
  results: []
 
22
 
23
  # zephyr-7b-sft-qlora
24
 
25
+ 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.
26
  It achieves the following results on the evaluation set:
27
  - Loss: 0.9499
28
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "train_loss": 0.9569843266025059,
4
  "train_runtime": 33545.7523,
5
  "train_samples": 207865,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.9498828649520874,
4
+ "eval_runtime": 985.6149,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 15.656,
7
+ "eval_steps_per_second": 0.49,
8
  "train_loss": 0.9569843266025059,
9
  "train_runtime": 33545.7523,
10
  "train_samples": 207865,
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "float16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": false,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_theta": 10000.0,
34
+ "sliding_window": 4096,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.38.2",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9498828649520874,
4
+ "eval_runtime": 985.6149,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 15.656,
7
+ "eval_steps_per_second": 0.49
8
+ }
runs/Mar06_16-31-59_ale-llm-4-0-0/events.out.tfevents.1709777287.ale-llm-4-0-0.1626.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735908d779efb46af53d3fa15c1c6cb4d789252575c401d5c2c612d7e3db5103
3
+ size 359