chansung commited on
Commit
c5b2e26
1 Parent(s): 4a2dbcd

End of training

Browse files
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
2
  base_model: mistralai/Mistral-7B-v0.3
3
  datasets:
4
- - generator
5
  library_name: peft
6
  license: apache-2.0
7
  tags:
 
8
  - trl
9
  - sft
10
  - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # mistral_7b_0_3-closedqa-gpt4o-100k
20
 
21
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 1.7580
24
 
 
1
  ---
2
  base_model: mistralai/Mistral-7B-v0.3
3
  datasets:
4
+ - llama-duo/synth_closed_qa_dataset_dedup
5
  library_name: peft
6
  license: apache-2.0
7
  tags:
8
+ - alignment-handbook
9
  - trl
10
  - sft
11
  - generated_from_trainer
 
19
 
20
  # mistral_7b_0_3-closedqa-gpt4o-100k
21
 
22
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the llama-duo/synth_closed_qa_dataset_dedup dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 1.7580
25
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 10.0,
 
 
 
 
 
3
  "total_flos": 8.183666472539652e+18,
4
  "train_loss": 0.6181400966970888,
5
  "train_runtime": 11966.6323,
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_loss": 1.7579952478408813,
4
+ "eval_runtime": 0.6389,
5
+ "eval_samples": 15,
6
+ "eval_samples_per_second": 9.391,
7
+ "eval_steps_per_second": 1.565,
8
  "total_flos": 8.183666472539652e+18,
9
  "train_loss": 0.6181400966970888,
10
  "train_runtime": 11966.6323,
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.3",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 32768,
8
+ "eos_token_id": 32769,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 32769,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_theta": 1000000.0,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.44.0",
41
+ "use_cache": true,
42
+ "vocab_size": 32770
43
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_loss": 1.7579952478408813,
4
+ "eval_runtime": 0.6389,
5
+ "eval_samples": 15,
6
+ "eval_samples_per_second": 9.391,
7
+ "eval_steps_per_second": 1.565
8
+ }
runs/Aug10_05-21-27_e8f6cb577ded/events.out.tfevents.1723279864.e8f6cb577ded.180766.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381f511db7e12a318d6f1347dab7bb64210695cfea3c0c743d42b56f331c59ca
3
+ size 359