chansung commited on
Commit
d90f718
1 Parent(s): becc4f8

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-gemini1_5flash-256k
13
  results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # gemma2b-summarize-gemini1_5flash-256k
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: 2.5669
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-gemini1_5flash-256k
14
  results: []
 
19
 
20
  # gemma2b-summarize-gemini1_5flash-256k
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: 2.5669
25
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 9.975903614457831,
 
 
 
 
 
3
  "total_flos": 3.290190024938619e+18,
4
  "train_loss": 0.9333097650233099,
5
  "train_runtime": 14306.303,
 
1
  {
2
  "epoch": 9.975903614457831,
3
+ "eval_loss": 2.566892147064209,
4
+ "eval_runtime": 0.495,
5
+ "eval_samples": 25,
6
+ "eval_samples_per_second": 20.203,
7
+ "eval_steps_per_second": 2.02,
8
  "total_flos": 3.290190024938619e+18,
9
  "train_loss": 0.9333097650233099,
10
  "train_runtime": 14306.303,
config.json CHANGED
@@ -9,7 +9,7 @@
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,
@@ -38,7 +38,7 @@
38
  "rope_scaling": null,
39
  "rope_theta": 10000.0,
40
  "torch_dtype": "bfloat16",
41
- "transformers_version": "4.40.1",
42
  "use_cache": true,
43
  "vocab_size": 256000
44
  }
 
9
  "eos_token_id": 1,
10
  "head_dim": 256,
11
  "hidden_act": "gelu",
12
+ "hidden_activation": "gelu_pytorch_tanh",
13
  "hidden_size": 2048,
14
  "initializer_range": 0.02,
15
  "intermediate_size": 16384,
 
38
  "rope_scaling": null,
39
  "rope_theta": 10000.0,
40
  "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.41.2",
42
  "use_cache": true,
43
  "vocab_size": 256000
44
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 14.981905910735826,
3
- "eval_loss": 2.503845453262329,
4
- "eval_runtime": 0.5015,
5
  "eval_samples": 25,
6
- "eval_samples_per_second": 19.941,
7
- "eval_steps_per_second": 1.994
8
  }
 
1
  {
2
+ "epoch": 9.975903614457831,
3
+ "eval_loss": 2.566892147064209,
4
+ "eval_runtime": 0.495,
5
  "eval_samples": 25,
6
+ "eval_samples_per_second": 20.203,
7
+ "eval_steps_per_second": 2.02
8
  }
runs/Jun10_09-38-09_48ddfe8e991f/events.out.tfevents.1718026885.48ddfe8e991f.334310.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3095239cf49932245ec8fc7708990560317784a18ee1ebf278a8cc4b8cf4955
3
+ size 359