chansung commited on
Commit
d24b7d3
1 Parent(s): 2206256

End of training

Browse files
README.md CHANGED
@@ -2,12 +2,13 @@
2
  license: gemma
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: google/gemma-7b
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: gemma7b-summarize-claude3sonnet-30k
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/chansung18/huggingface/runs/62awpxu7)
20
  # gemma7b-summarize-claude3sonnet-30k
21
 
22
- This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 2.3268
25
 
 
2
  license: gemma
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: google/gemma-7b
10
  datasets:
11
+ - llama-duo/synth_summarize_dataset
12
  model-index:
13
  - name: gemma7b-summarize-claude3sonnet-30k
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/chansung18/huggingface/runs/62awpxu7)
21
  # gemma7b-summarize-claude3sonnet-30k
22
 
23
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 2.3268
26
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 5.0,
 
 
 
 
 
3
  "total_flos": 1.5670950020754964e+18,
4
  "train_loss": 1.4066738275202308,
5
  "train_runtime": 8016.4558,
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_loss": 2.326845407485962,
4
+ "eval_runtime": 1.0399,
5
+ "eval_samples": 25,
6
+ "eval_samples_per_second": 4.808,
7
+ "eval_steps_per_second": 1.923,
8
  "total_flos": 1.5670950020754964e+18,
9
  "train_loss": 1.4066738275202308,
10
  "train_runtime": 8016.4558,
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-7b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_activation": "gelu_pytorch_tanh",
13
+ "hidden_size": 3072,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 24576,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 16,
21
+ "pad_token_id": 0,
22
+ "quantization_config": {
23
+ "_load_in_4bit": true,
24
+ "_load_in_8bit": false,
25
+ "bnb_4bit_compute_dtype": "bfloat16",
26
+ "bnb_4bit_quant_storage": "uint8",
27
+ "bnb_4bit_quant_type": "nf4",
28
+ "bnb_4bit_use_double_quant": false,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": true,
34
+ "load_in_8bit": false,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": null,
39
+ "rope_theta": 10000.0,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.41.0",
42
+ "use_cache": true,
43
+ "vocab_size": 256000
44
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 2.326845407485962,
4
+ "eval_runtime": 1.0399,
5
+ "eval_samples": 25,
6
+ "eval_samples_per_second": 4.808,
7
+ "eval_steps_per_second": 1.923
8
+ }
runs/May19_11-55-30_deep-diver-main-fresh-rabbit-1-0-0/events.out.tfevents.1716142323.deep-diver-main-fresh-rabbit-1-0-0.385.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f22b2be8d1eb9ad6e44a9f507f0eb2fa73032659ba7b7140afe818168d0253
3
+ size 359