Hugging Face's logo

rbelanec
/
train_stsb_1745333591

PEFT
Safetensors
llama-factory
prompt-tuning
Generated from Trainer
Model card Files
xet
 Community
rbelanec commited on
Commit
1ba6550
·
verified ·
1 Parent(s): ac849f7

Training in progress, step 200

Browse files
Files changed (10) hide show
  1. README.md +3 -2
  2. adapter_model.safetensors +1 -1
  3. all_results.json +13 -0
  4. eval_results.json +8 -0
  5. train_results.json +9 -0
  6. trainer_log.jsonl +0 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
  9. training_eval_loss.png +0 -0
  10. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3
4
  base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: train_stsb_1745333591
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # train_stsb_1745333591
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.1370
21
  - Num Input Tokens Seen: 54490336
22
 
23
  ## Model description
 
4
  base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
  tags:
6
  - llama-factory
7
+ - prompt-tuning
8
  - generated_from_trainer
9
  model-index:
10
  - name: train_stsb_1745333591
 
16
 
17
  # train_stsb_1745333591
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the stsb dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5494
22
  - Num Input Tokens Seen: 54490336
23
 
24
  ## Model description
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e16ee7164fe5a029ca539de2820b0101476fe210b99b39b526ffd402f3bfcd9
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7673eb52720760051bf527aa4b080bb31463618d6fef9b4aeb3ccc97c56eb8b5
3
  size 1638528
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 123.45749613601237,
3
+ "eval_loss": 0.5493518114089966,
4
+ "eval_runtime": 11.2648,
5
+ "eval_samples_per_second": 51.044,
6
+ "eval_steps_per_second": 12.783,
7
+ "num_input_tokens_seen": 54490336,
8
+ "total_flos": 2.453675202191819e+18,
9
+ "train_loss": 0.10362623064493919,
10
+ "train_runtime": 29327.4396,
11
+ "train_samples_per_second": 21.823,
12
+ "train_steps_per_second": 1.364
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 123.45749613601237,
3
+ "eval_loss": 0.5493518114089966,
4
+ "eval_runtime": 11.2648,
5
+ "eval_samples_per_second": 51.044,
6
+ "eval_steps_per_second": 12.783,
7
+ "num_input_tokens_seen": 54490336
8
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 123.45749613601237,
3
+ "num_input_tokens_seen": 54490336,
4
+ "total_flos": 2.453675202191819e+18,
5
+ "train_loss": 0.10362623064493919,
6
+ "train_runtime": 29327.4396,
7
+ "train_samples_per_second": 21.823,
8
+ "train_steps_per_second": 1.364
9
+ }
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a10f99305e28d32f36e0b16cb5f7f671e034c65e61c687a4602d50ba24343ea1
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c726b9b51540be6b51b70dec76feda3fc584943737015e9f4840ae838669d3
3
  size 5752
training_eval_loss.png ADDED
training_loss.png ADDED