chansung commited on
Commit
6598555
1 Parent(s): 28d6d7b

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-2b
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: gemma2b-summarize-claude3sonnet-128k
13
  results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # gemma2b-summarize-claude3sonnet-128k
20
 
21
- This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 2.5270
24
 
 
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-2b
10
  datasets:
11
+ - llama-duo/synth_summarize_dataset_dedup
12
  model-index:
13
  - name: gemma2b-summarize-claude3sonnet-128k
14
  results: []
 
19
 
20
  # gemma2b-summarize-claude3sonnet-128k
21
 
22
+ This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the llama-duo/synth_summarize_dataset_dedup dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 2.5270
25
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 15.0,
 
 
 
 
 
3
  "total_flos": 3.5418612320488653e+18,
4
  "train_loss": 0.9510796088682083,
5
  "train_runtime": 20707.2957,
 
1
  {
2
  "epoch": 15.0,
3
+ "eval_loss": 2.5269672870635986,
4
+ "eval_runtime": 0.5011,
5
+ "eval_samples": 25,
6
+ "eval_samples_per_second": 19.954,
7
+ "eval_steps_per_second": 1.995,
8
  "total_flos": 3.5418612320488653e+18,
9
  "train_loss": 0.9510796088682083,
10
  "train_runtime": 20707.2957,
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2b",
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": null,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 16384,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 18,
20
+ "num_key_value_heads": 1,
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": "4.40.0",
42
+ "use_cache": true,
43
+ "vocab_size": 256000
44
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.0,
3
+ "eval_loss": 2.5269672870635986,
4
+ "eval_runtime": 0.5011,
5
+ "eval_samples": 25,
6
+ "eval_samples_per_second": 19.954,
7
+ "eval_steps_per_second": 1.995
8
+ }
runs/Jun05_18-23-59_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717600311.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.939605.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0a6cb24a02799827586358de04b702facd3d030d13f81fd648055e6fa83f5e
3
+ size 359