Hugging Face's logo

Sierkinhane
/
lvp_llama3_8b

TensorBoard
Safetensors
llama
llama-factory
full
Generated from Trainer
Model card Files Metrics Community
Sierkinhane commited on
Commit
d565b21
•
1 Parent(s): f109bc5

Add checkpoint

Browse files
Files changed (15) hide show
  1. README.md +4 -4
  2. all_results.json +9 -9
  3. eval_results.json +4 -4
  4. model-00001-of-00004.safetensors +1 -1
  5. model-00002-of-00004.safetensors +1 -1
  6. model-00003-of-00004.safetensors +1 -1
  7. model-00004-of-00004.safetensors +1 -1
  8. runs/Nov02_11-36-19_n124-167-248/events.out.tfevents.1730547445.n124-167-248.2750283.0 +3 -0
  9. runs/Nov02_11-36-19_n124-167-248/events.out.tfevents.1730588909.n124-167-248.2750283.1 +3 -0
  10. train_results.json +5 -5
  11. trainer_log.jsonl +0 -0
  12. trainer_state.json +0 -0
  13. training_args.bin +1 -1
  14. training_eval_loss.png +0 -0
  15. training_loss.png +0 -0
README.md CHANGED
@@ -13,12 +13,12 @@ model-index:
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- [<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/sierkinhane/huggingface/runs/sej9pkhd)
17
  # sft
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 storyboard20k dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5335
22
 
23
  ## Model description
24
 
@@ -55,12 +55,12 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:-----:|:---------------:|
58
- | 0.5652 | 0.7771 | 10000 | 0.5870 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - Transformers 4.43.2
64
- - Pytorch 2.3.0+cu121
65
  - Datasets 2.16.0
66
  - Tokenizers 0.19.1
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ [<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/sierkinhane/huggingface/runs/06jvgsys)
17
  # sft
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 storyboard20k dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4572
22
 
23
  ## Model description
24
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:-----:|:---------------:|
58
+ | 0.4899 | 0.7771 | 10000 | 0.5172 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - Transformers 4.43.2
64
+ - Pytorch 2.3.1+cu121
65
  - Datasets 2.16.0
66
  - Tokenizers 0.19.1
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.5335121750831604,
4
- "eval_runtime": 422.7122,
5
- "eval_samples_per_second": 25.637,
6
- "eval_steps_per_second": 3.205,
7
- "total_flos": 450352329523200.0,
8
- "train_loss": 0.8422004632789019,
9
- "train_runtime": 36238.6731,
10
- "train_samples_per_second": 5.682,
11
- "train_steps_per_second": 0.355
12
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.4571681022644043,
4
+ "eval_runtime": 470.7912,
5
+ "eval_samples_per_second": 23.019,
6
+ "eval_steps_per_second": 2.878,
7
+ "total_flos": 626183508787200.0,
8
+ "train_loss": 0.7687553066651168,
9
+ "train_runtime": 40960.0959,
10
+ "train_samples_per_second": 5.027,
11
+ "train_steps_per_second": 0.314
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.5335121750831604,
4
- "eval_runtime": 422.7122,
5
- "eval_samples_per_second": 25.637,
6
- "eval_steps_per_second": 3.205
7
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.4571681022644043,
4
+ "eval_runtime": 470.7912,
5
+ "eval_samples_per_second": 23.019,
6
+ "eval_steps_per_second": 2.878
7
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bde9deb8fec7a5be8337639579bec9854e312552259c3fbec3376ca26ae359ec
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f538567582c2690a4c8cc515e8bb3a5314a37694b85b5cdce909434f6b399c6d
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3ee89a92e0b2bc3e7342e0a8c836bba645ee24a6df4de6afd5e2ca8372420c7
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004d9467dc9a25dc2a3bf0462f6721a302a0de9b1d6eab3c7695e7ea6fdd1ae9
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6b2fa92d42e16c251dbb1a019a909267afe5df7d585d447105a76d49e89b120
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c618bd643771be4b19406ea5d63c729d9a84213bfedcae5f494a92182e6c4a1
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:007b8c655917d20b6197c550142756f1561497c02efa28798174052cf051b9d5
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1e546d9d59f8d602e393f3915006419d4d61b5cc366c8368a0422ea8421fd8
3
  size 1168138808
runs/Nov02_11-36-19_n124-167-248/events.out.tfevents.1730547445.n124-167-248.2750283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0910539d6fe4ad9b7351bdfb000b3ae136e02fe858d157cd1499ceef8bfa19d6
3
+ size 277095
runs/Nov02_11-36-19_n124-167-248/events.out.tfevents.1730588909.n124-167-248.2750283.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f04e47d9cb2071533f28bdcf8fb25caa78a34fb3a732a68dea6485f194f2c9
3
+ size 311
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "total_flos": 450352329523200.0,
4
- "train_loss": 0.8422004632789019,
5
- "train_runtime": 36238.6731,
6
- "train_samples_per_second": 5.682,
7
- "train_steps_per_second": 0.355
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "total_flos": 626183508787200.0,
4
+ "train_loss": 0.7687553066651168,
5
+ "train_runtime": 40960.0959,
6
+ "train_samples_per_second": 5.027,
7
+ "train_steps_per_second": 0.314
8
  }
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
trainer_state.json CHANGED
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 sha256:4e6129ee3ce7b8332b3b1c62acee882d7416aebb232e440d01882bf9ac07e78b
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a34e349a8d6fadfd31677dbafeefa4b8df29285519f825d66b67b02acbfca55
3
  size 7032
training_eval_loss.png CHANGED
training_loss.png CHANGED